Merge branch 'master' of asdf.us:megapixels_dev

4 files changed, 4 insertions, 4 deletions

diff --git a/site/datasets/unknown/coco.json b/site/datasets/unknown/coco.json
index 9149acf9..c61d3b1f 100644
--- a/site/datasets/unknown/coco.json
+++ b/site/datasets/unknown/coco.json
@@ -1 +1 @@
-{"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "citations": [{"id": "08f6b52317b34b60aa65f38b83e3d72deffa0473", "title": "Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/bae0/9864ea2c05bccf275cf824580ce212111e42.pdf"], "doi": []}, {"id": "ce9799830a24412f4bd9ad30a9d6e2a50215f8f8", "title": "Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.01972.pdf"], "doi": []}, {"id": "369c4a308ec9e56746f7cc1b164208b917e31a22", "title": "Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/369c/4a308ec9e56746f7cc1b164208b917e31a22.pdf"], "doi": []}, {"id": "35ebe95db7ab148e25904604d3b06a9412f6b4a4", "title": "Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/80d9/993e6abd22a58a4fedd63754a15085778367.pdf"], "doi": []}, {"id": "d4901683e2c2552fc2d62d4eb3b1f5d5fa60a5ff", "title": "ScaleNet: Scale Invariant Network for Semantic Segmentation in Urban Driving Scenes", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d490/1683e2c2552fc2d62d4eb3b1f5d5fa60a5ff.pdf"], "doi": []}, {"id": "254f7ef73629c18ff9ba13af59b2d78df3fda59d", "title": "Deep Object-Centric Representations for Generalizable Robot Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1708.04225.pdf"], "doi": []}, {"id": "0f08d62e882026ac83ebf26c0bd288c553873814", "title": "Multispecies Fruit Flower Detection Using a Refined Semantic Segmentation Network", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.10080.pdf"], "doi": []}, {"id": "89fff8387432878db240a044a98ff9c9200f3197", "title": "Learning Globally Optimized Object Detector via Policy Gradient", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Rao_Learning_Globally_Optimized_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578746", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00648", "http://doi.org/10.1109/CVPR.2018.00648"]}, {"id": "b955969e1077ca328018c9e4dcf27b87ed9f5076", "title": "Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.01887.pdf"], "doi": []}, {"id": "f56edb6f2bf4f5bc9d54284289212b8d4a437c1b", "title": "Detection and Localization of Texture-less Objects with Deep Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f56e/db6f2bf4f5bc9d54284289212b8d4a437c1b.pdf"], "doi": []}, {"id": "a345fc597b15c26f3f2823ccd5aac0d4c976279e", "title": "Adversarially Parameterized Optimization for 3D Human Pose Estimation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8374567", "http://doi.ieeecomputersociety.org/10.1109/3DV.2017.00026", "http://doi.org/10.1109/3DV.2017.00026"]}, {"id": "3d1e82b69663758a1db87fbebed6525d23090146", "title": "ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780713"]}, {"id": "7c2a6b27dd756fe851954e0c040bc87bbd39f098", "title": "Using Psychophysical Methods to Understand Mechanisms of Face Identification in a Deep Neural Network", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w39/Xu_Using_Psychophysical_Methods_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575433", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00266", "http://doi.org/10.1109/CVPRW.2018.00266"]}, {"id": "9595a267de2b0ecf7e4e2962a606c8854551e203", "title": "On the Relation between Color Image Denoising and Classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.01372.pdf"], "doi": []}, {"id": "94a76e349e43f09c863a9c77e47722c5ade3740e", "title": "WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Durand_WELDON_Weakly_Supervised_CVPR_2016_paper.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/supplemental/Durand_WELDON_Weakly_Supervised_2016_CVPR_supplemental.pdf", "http://webia.lip6.fr/~thomen/papers/Durand_CVPR_2016.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Durand_WELDON_Weakly_Supervised_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780882", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.513", "http://doi.org/10.1109/CVPR.2016.513", "https://hal.archives-ouvertes.fr/hal-01343785/document"]}, {"id": "f5f3faa71ed2b61fa3a99bde25d6e84bfbefbb0b", "title": "Automatic Fish Classification System Using Deep Learning", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8371919", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2017.00016", "http://doi.org/10.1109/ICTAI.2017.00016"]}, {"id": "3832a6d6b1f78cdadee6968d51c1c7c2922ab3cd", "title": "ISIA at the ImageCLEF 2017 Image Caption Task", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3832/a6d6b1f78cdadee6968d51c1c7c2922ab3cd.pdf"], "doi": []}, {"id": "6abdd7c4dea2d5d7ff82cd5e6e503be1589861df", "title": "Detection and Recognition of U.S. Warning Signs on Curves", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8372008", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2017.00105", "http://doi.org/10.1109/ICTAI.2017.00105"]}, {"id": "a49b309ba14ad00a3bcb7b99a45d5bcf9bbc0ab1", "title": "Guided Perturbations: Self-Corrective Behavior in Convolutional Neural Networks", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Sankaranarayanan_Guided_Perturbations_Self-Corrective_ICCV_2017_paper.pdf", "https://arxiv.org/pdf/1703.07928v1.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237647", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.385", "http://doi.org/10.1109/ICCV.2017.385"]}, {"id": "104dd4963f7f0ef03fe09d505d31966666f9281d", "title": "Salient Object Subitizing", "year": "2015", "pdf": ["https://arxiv.org/pdf/1607.07525.pdf"], "doi": []}, {"id": "041755d1c14077ce18d8553aa40a415283edc825", "title": "W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_W2F_A_Weakly-Supervised_CVPR_2018_paper.pdf", "https://ivul.kaust.edu.sa/Documents/Publications/2018/W2F%20A%20Weakly-Supervised%20to%20Fully-Supervised%20Framework.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578201", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00103", "http://doi.org/10.1109/CVPR.2018.00103"]}, {"id": "ce8c8e9fdbdd84adc096018bb0edb49b6913b946", "title": "Learning Discriminative Features for Speaker Identification and Verification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/ce8c/8e9fdbdd84adc096018bb0edb49b6913b946.pdf"], "doi": []}, {"id": "110556d073a4d930877edc597a92995f0ff9d294", "title": "Application of Faster R-CNN model on Human Running Pattern Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.05147.pdf"], "doi": []}, {"id": "549c719c4429812dff4d02753d2db11dd490b2ae", "title": "YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00824.pdf"], "doi": []}, {"id": "1295cbaf3b03de2eb8c79530289f5939d7819e5c", "title": "DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations", "year": "2017", "pdf": ["https://arxiv.org/pdf/1510.02927.pdf"], "doi": []}, {"id": "4cfd15e9d3c01028bcda22e68791a95aa54c2a7c", "title": "DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations", "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.01766.pdf"], "doi": []}, {"id": "25b9ef5c78dbf17c71e6fd94054dd55d66c39264", "title": "Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.01606.pdf"], "doi": []}, {"id": "0b2c543e0c47454c4512569175094e6cb6ae02a9", "title": "The VizWiz Grand Challenge : A Large Visual Question Answering Dataset from Blind People Anonymous CVPR submission", "year": "", "pdf": ["https://pdfs.semanticscholar.org/0b2c/543e0c47454c4512569175094e6cb6ae02a9.pdf"], "doi": []}, {"id": "efb01e07ee994fec890ad83b89c9b652349da50e", "title": "What am I searching for", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.11926.pdf"], "doi": []}, {"id": "1c9333bcf523388d75f852e0689b0e7f5a04faa4", "title": "Person Part Segmentation based on Weak Supervision", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1c93/33bcf523388d75f852e0689b0e7f5a04faa4.pdf"], "doi": []}, {"id": "325093f2c5b33d7507c10aa422e96aa5b10a33f1", "title": "In-place Activated BatchNorm for Memory-Optimized Training of DNNs", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578689"]}, {"id": "c399c0089fb134d1476fadf5f0426e0e8b70eebd", "title": "The Lov\u00e1sz Hinge: A Novel Convex Surrogate for Submodular Losses.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1512.07797.pdf"], "doi": []}, {"id": "c98e5a582e9f1b11bf5244ed16c78a7cbccf36b9", "title": "Towards Semantic SLAM: Points, Planes and Objects", "year": "2018", "pdf": [], "doi": []}, {"id": "b0d52bb1c9cff9416fe766e9cba94ceeab12d51f", "title": "Object detection using deep CNNs trained on synthetic images", "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.06782.pdf"], "doi": []}, {"id": "1d21ec277d2a72e506a9665f19ec5478dbedc20f", "title": "A Semi-Automatic Annotation Technology for Traffic Scene Image Labeling Based on Deep Learning Preprocessing", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8005815", "http://doi.ieeecomputersociety.org/10.1109/CSE-EUC.2017.63", "http://doi.org/10.1109/CSE-EUC.2017.63"]}, {"id": "619701bb7d73171d6311c9e14b8ac5919692d03e", "title": "Semantic Edge Detection with Diverse Deep Supervision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02864.pdf"], "doi": []}, {"id": "68f6b329044b01cce1660e953875ece2c3778c68", "title": "Intelligent Surveillance as an Edge Network Service: from Harr-Cascade, SVM to a Lightweight CNN", "year": "2018", "pdf": [], "doi": []}, {"id": "22aa426aeffb77339646cc03da8e94de22396efc", "title": "S HAKES HAKE REGULARIZATION OF 3-BRANCH RESIDUAL NETWORKS", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/22aa/426aeffb77339646cc03da8e94de22396efc.pdf"], "doi": []}, {"id": "19f73120fa314666c841ea88cb2b627aa67251b4", "title": "Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.06006.pdf"], "doi": []}, {"id": "3fea412361b2d14cb3c6723968b421c1c8cb38e8", "title": "Shake-Shake regularization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.07485.pdf"], "doi": []}, {"id": "332339c32d41cc8176d360082b4d9faa90dadffa", "title": "UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory", "year": "2017", "pdf": ["https://arxiv.org/pdf/1609.02132.pdf"], "doi": []}, {"id": "76b61ccb488ad7861e9e36054f96195877f4c9f6", "title": "Automatic image annotation: the quirks and what works", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-018-6247-3"]}, {"id": "05e9e85b5137016c93d042170e82f77bb551a108", "title": "A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation", "year": "2016", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Perazzi_A_Benchmark_Dataset_CVPR_2016_paper.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_poster_cvpr_2016.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_supplementary.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780454", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.85", "http://doi.org/10.1109/CVPR.2016.85"]}, {"id": "8899094797e82c5c185a0893896320ef77f60e64", "title": "Non-local Neural Networks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578911"]}, {"id": "12660f0defc6580e566c0fa2ac909971d6c6883b", "title": "The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780721", "http://doi.org/10.1109/CVPR.2016.352", "https://www.wikidata.org/entity/Q57840870"]}, {"id": "bf881e53510b230879aa0d3b02576043b8f881e7", "title": "Automated Image Captioning Using Nearest-Neighbors Approach Driven by Top-Object Detections", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/bf88/1e53510b230879aa0d3b02576043b8f881e7.pdf"], "doi": []}, {"id": "10beef48f3a9b2c4a6c863edefe2cac8bf09b50c", "title": "Fine-Level Semantic Labeling of Large-Scale 3D Model by Active Learning", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8491004", "http://doi.ieeecomputersociety.org/10.1109/3DV.2018.00066", "http://doi.org/10.1109/3DV.2018.00066"]}, {"id": "761de31c575bf30162b6e0d92a1800eb406e96b5", "title": "A Flexible Convolutional Solver with Application to Photorealistic Style Transfer", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.05285.pdf"], "doi": []}, {"id": "96d1bf51b3aa118696ce18dc45924e5ca8b9d885", "title": "Insulator Detection in Aerial Images for Transmission Line Inspection Using Single Shot Multibox Detector", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8603728"]}, {"id": "10c4b2489d7e1ee43a1d19724d3c1e9c33ca3f29", "title": "A Question-Answering framework for plots using Deep learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.04655.pdf"], "doi": []}, {"id": "dbc359e95d999bf119353f51edcb53b2beb5b3fe", "title": "Object Detection in Real-Time Systems: Going Beyond Precision", "year": "2018", "pdf": ["https://www.iiitd.edu.in/~chetan/papers/obj-det-wacv18.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354221", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00117", "http://doi.org/10.1109/WACV.2018.00117"]}, {"id": "de1505819e145b5c22a6e09002510413019f7228", "title": "DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.05675.pdf"], "doi": []}, {"id": "0b888196dda951287dddb60bd44798aab16d6fca", "title": "Learning Common Sense through Visual Abstraction", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Vedantam_Learning_Common_Sense_ICCV_2015_paper.pdf", "http://oui.csail.mit.edu/camera_readys/21.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Vedantam_Learning_Common_Sense_ICCV_2015_paper.pdf", "https://filebox.ece.vt.edu/~parikh/Publications/ICCV2015_commonsense.pdf", "https://www.cc.gatech.edu/~parikh/Publications/ICCV2015_commonsense.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410649", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.292", "http://doi.org/10.1109/ICCV.2015.292"]}, {"id": "85cace98e07e190494a5d88eba5e5b11538dc3b1", "title": "Hierarchical Semantic Mapping Using Convolutional Neural Networks for Intelligent Service Robotics", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8490234", "http://doi.org/10.1109/ACCESS.2018.2873597"]}, {"id": "2dd853b617c176810e3dda008f7cacea6473f0ae", "title": "Image captioning using deep neural architectures", "year": "2017", "pdf": ["https://arxiv.org/pdf/1801.05568.pdf"], "doi": []}, {"id": "25894be540936562953f37fbbcff69e5ac17a494", "title": "Semantic Image Retrieval via Active Grounding of Visual Situations", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.00088.pdf"], "doi": []}, {"id": "28949c94c8457e570ba65c8382c993600f8404e7", "title": "Efficient Video Object Segmentation via Network Modulation", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578778"]}, {"id": "ba60b642a558858325f50d38a345b6bb85114ce1", "title": "Imbalanced Deep Learning by Minority Class Incremental Rectification", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.10851.pdf"], "doi": []}, {"id": "a4aa145b519a9515e1162ca017d80d460002ba5a", "title": "HandyNet: A One-stop Solution to Detect, Segment, Localize & Analyze Driver Hands", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575312"]}, {"id": "442b6114ae8316c95f59acabe6de26f2b569cc02", "title": "Edit me: A Corpus and a Framework for Understanding Natural Language Image Editing", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1205/8e0de3dadc1469035ddb3c82e1b7ba722960.pdf"], "doi": []}, {"id": "729a9d35bc291cc7117b924219bef89a864ce62c", "title": "Recognizing Material Properties from Images.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.03127.pdf"], "doi": []}, {"id": "144ba4e9e64d4f9a5bb436c80c3c02b40e4092e0", "title": "Learning Video Features for Multi-label Classification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/144b/a4e9e64d4f9a5bb436c80c3c02b40e4092e0.pdf"], "doi": []}, {"id": "9c0ff1f1e2c83f089cb6b42a91869428fe9a92b2", "title": "Commonsense LocatedNear Relation Extraction", "year": "2017", "pdf": [], "doi": []}, {"id": "e5918229f44f0215d73a0b9d5eb13eb56764a2e4", "title": "Counting Vehicles with Cameras", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e591/8229f44f0215d73a0b9d5eb13eb56764a2e4.pdf"], "doi": []}, {"id": "f7cf4e0b1e371efca045e71996956be19aef0577", "title": "C L ] 3 D ec 2 01 7 Adversarial Ranking for Language Generation", "year": "2017", "pdf": [], "doi": []}, {"id": "0199150ccad6479eac9d693a7cc0406935d877a8", "title": "Towards Real-Time Accurate Object Detection in Both Images and Videos Based on Dual Refinement.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08638.pdf"], "doi": []}, {"id": "4c8dfc4720186799b2baf53c282a32ba3f312bcc", "title": "A Mask Regional Convolutional Neural Network Model for Segmenting Real Time Traffic Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8493883"]}, {"id": "b29be8ae91eff7ccf001d48adf518bae86129be3", "title": "OmniDetector: With Neural Networks to Bounding Boxes", "year": "2018", "pdf": [], "doi": []}, {"id": "2fcd5cff2b4743ea640c4af68bf4143f4a2cccb1", "title": "Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering", "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.05612.pdf"], "doi": []}, {"id": "6a1b76f1ef876061ec479ab9bc13fcd517eb4188", "title": "Large Kernel Matters \u2014 Improve Semantic Segmentation by Global Convolutional Network", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02719.pdf"], "doi": []}, {"id": "3bcca85ad84806be6d38d3882f7a6aac0ad90253", "title": "Video captioning with recurrent networks based on frame- and video-level features and visual content classification", "year": "2015", "pdf": ["https://arxiv.org/pdf/1512.02949.pdf"], "doi": []}, {"id": "39978ba7c83333475d6825d0ff897692933895fc", "title": "Conditional Random Fields as Recurrent Neural Networks", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410536"]}, {"id": "6ee2173c06c84cae6aae2912a4439ec956ecc3bb", "title": "Zero-shot Sim-to-Real Transfer with Modular Priors", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07480.pdf"], "doi": []}, {"id": "fd0769033b18038b9baf9e762f16973ee27be626", "title": "MobileNetV2: Inverted Residuals and Linear Bottlenecks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578572"]}, {"id": "b408b939c0f3be9cce0f84871a78a71d1684cd77", "title": "Identifying spatial relations in images using convolutional neural networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.04215.pdf"], "doi": []}, {"id": "8aa9d9ccbdf37fd1d9fb4f3adb778b3c2c9baa45", "title": "POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infrared Sensors", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575327"]}, {"id": "ed7de328e2191463d42d745d8ac8f16024f95f25", "title": "Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237354"]}, {"id": "37b207d2c4a82a57f80e96353f79ecd71320a854", "title": "Person Search with Natural Language Description", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.05729.pdf"], "doi": []}, {"id": "54f688ea5de7b9156db28b2821e5f5ed0148605a", "title": "Contextual Memory Trees", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.06473.pdf"], "doi": []}, {"id": "4a88237199595feaa3f0e3289cbdd201a3ce28ff", "title": "Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08338.pdf"], "doi": []}, {"id": "3979e8ddcf95fedf7a220b7d39a72fa120d436f8", "title": "Deep Learning Applied to Image and Text Matching", "year": "2015", "pdf": ["https://arxiv.org/pdf/1601.03478.pdf"], "doi": []}, {"id": "df9a102288582d8edadeddcb8d55068a06cc471c", "title": "Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension", "year": "2017", "pdf": ["http://ai2-website.s3.amazonaws.com/publications/CVPR17_TQA.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/papers/Kembhavi_Are_You_Smarter_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100054", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.571", "http://doi.org/10.1109/CVPR.2017.571"]}, {"id": "9bddd98289ecc7a8dc5517122d21d5c6f5a9a01a", "title": "DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.10733.pdf"], "doi": []}, {"id": "d951ff5f378b2a5f878423029123ad6b3491b444", "title": "Foveal Vision for Instance Segmentation of Road Images", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c33e/a181e9cd13ad3f11f459d5d1f7b7bf114033.pdf"], "doi": []}, {"id": "9645e8b4829c04879a642d8dd6b3cdf5cf264afb", "title": "Finding Beans in Burgers: Deep Semantic-Visual Embedding with Localization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.01720.pdf"], "doi": []}, {"id": "1e2d9ea6fe9c50a5c26a629b94446250e1be4e7d", "title": "The Freiburg Groceries Dataset", "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.05799.pdf"], "doi": []}, {"id": "40c6a2b1cb312f11f8225a733545fdabd436e347", "title": "Deep Co-Training for Semi-Supervised Image Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.05984.pdf"], "doi": []}, {"id": "1f0c7b93636f879bd5ef3dd915a02dcd813a053d", "title": "Interpreting Deep Visual Representations via Network Dissection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.05611.pdf"], "doi": []}, {"id": "402056b2d10b27c1b17dbb5eb82b95fd1cfd8fa5", "title": "Deriving Privacy and Security Considerations for CORE: An Indoor IoT Adaptive Context Environment", "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3267363"]}, {"id": "5b3dc81a490b1d9e69d7be20c4e8e1de886b5ca3", "title": "Improving Object Localization with Fitness NMS and Bounded IoU Loss", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.00164.pdf"], "doi": []}, {"id": "b7c2798e136feb85847c8a9aa693d75bc3f9b08c", "title": "Classifying a specific image region using convolutional nets with an ROI mask as input", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00291.pdf"], "doi": []}, {"id": "372026896229c870f11bcecc1c81c80dad9c6761", "title": "Draw and Tell: Multimodal Descriptions Outperform Verbal- or Sketch-Only Descriptions in an Image Retrieval Task", "year": "2017", "pdf": [], "doi": ["https://aclanthology.info/papers/I17-2061/i17-2061", "http://aclweb.org/anthology/I17-2061", "https://pub.uni-bielefeld.de/download/2913598/2914382"]}, {"id": "8d384e8c45a429f5c5f6628e8ba0d73c60a51a89", "title": "Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.00666.pdf"], "doi": []}, {"id": "6f77ff9990973a6cdad6b5b6022323bff9d03965", "title": "Action Recognition in Still Images Using Word Embeddings from Natural Language Descriptions", "year": "2017", "pdf": ["http://cobweb.cs.uga.edu/~csc/papers/wacv17_1.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7912210", "http://doi.org/10.1109/WACVW.2017.17"]}, {"id": "146f6f6ed688c905fb6e346ad02332efd5464616", "title": "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention", "year": "2015", "pdf": ["https://arxiv.org/pdf/1502.03044.pdf"], "doi": []}, {"id": "e20daf69526c5da9cffb252d043fdc765f37a89e", "title": "Relating images and 3D models with convolutional neural networks. (Mise en relation d'images et de mod\u00e8les 3D avec des r\u00e9seaux de neurones convolutifs)", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/e20d/af69526c5da9cffb252d043fdc765f37a89e.pdf"], "doi": []}, {"id": "fb732b15fd5235893228ad3249cf04e1809034c9", "title": "CBVMR: Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.06761.pdf"], "doi": []}, {"id": "eaf8c104ab14600ecc5e9cce739b55280eef7ad4", "title": "Abstractive Compression of Captions with Attentive Recurrent Neural Networks", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/eaf8/c104ab14600ecc5e9cce739b55280eef7ad4.pdf"], "doi": []}, {"id": "dc4682cd15ccb7ebcbc8d2ba21b613e34a9af8ca", "title": "Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics using CNNs", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08960.pdf"], "doi": []}, {"id": "478a1ed7dc1890ca9476dcc1befe7f21c9bf9149", "title": "Learning to Learn from Noisy Labeled Data", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05214.pdf"], "doi": []}, {"id": "1e17202d6de18d5e1965edce5fee79744b717d0b", "title": "MIML-FCN+: Multi-Instance Multi-Label Learning via Fully Convolutional Networks with Privileged Information", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.08681.pdf"], "doi": []}, {"id": "542289d1acfebb9d79ea7a10c8e1516924e09973", "title": "Video Highlight Prediction Using Audience Chat Reactions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.08559.pdf"], "doi": []}, {"id": "2badc4c87a7751dd5ae1797bc4091d10d1acf442", "title": "Multimodal Retrieval with Asymmetrically Weighted Regularized Canonical Correla- Tion Analysis", "year": "", "pdf": ["https://pdfs.semanticscholar.org/2bad/c4c87a7751dd5ae1797bc4091d10d1acf442.pdf"], "doi": []}, {"id": "9b45e9a40313096abf530df3b98a1dfa1553f17b", "title": "Comprehension-Guided Referring Expressions", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099816"]}, {"id": "66837b29270f3e03df64941a081d70c687c7955c", "title": "ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12126.pdf"], "doi": []}, {"id": "7d035e6c6b5ef1267dff23845009284677c16a4d", "title": "AlphaGAN: Generative adversarial networks for natural image matting", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.10088.pdf"], "doi": []}, {"id": "655f587a59c835a7b6b5017016ea1c2123f266e6", "title": "Separating Self-Expression and Visual Content in Hashtag Supervision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09825.pdf"], "doi": []}, {"id": "3ca194773fe583661b988fbdf33f7680764438b3", "title": "Exploring Nearest Neighbor Approaches for Image Captioning", "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.04467.pdf"], "doi": []}, {"id": "f43463770d361e55fb6f6eb801a6e8530ab668cd", "title": "Corpus Construction and Semantic Analysis of Indonesian Image Description", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f434/63770d361e55fb6f6eb801a6e8530ab668cd.pdf"], "doi": []}, {"id": "46d8531797d8913b05f9124def1ef81ac30423c1", "title": "MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer", "year": "2019", "pdf": ["https://arxiv.org/pdf/1812.05233.pdf"], "doi": []}, {"id": "f5748711db00d82469ff60e05f62319f1eac90c5", "title": "Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.07169.pdf"], "doi": []}, {"id": "cfc22c35ad191cf9d70f4a3655840748b0e1322c", "title": "Real-Time Dense Mapping for Self-driving Vehicles using Fisheye Cameras", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.06132.pdf"], "doi": []}, {"id": "6bfae88bea2301f2abeb6d1ed62c8b9a99b251c0", "title": "CNRS TELECOM ParisTech at ImageCLEF 2015 Scalable Concept Image Annotation Task: Concept Detection with Blind Localization Proposals", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/6bfa/e88bea2301f2abeb6d1ed62c8b9a99b251c0.pdf"], "doi": []}, {"id": "478261574ddc6cf297611000735aa9808f8f0030", "title": "ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.04405.pdf"], "doi": []}, {"id": "12d9a4233a16ea08fbb1de853b6a97b4f4952c23", "title": "Tractable Structured Prediction using the Permutohedral Lattice", "year": "2017", "pdf": ["https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-01.pdf?isAllowed=y&sequence=1", "https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-02.pdf?isAllowed=y&sequence=2"], "doi": ["https://doi.org/10.3929/ethz-a-010882665"]}, {"id": "e654320739770029ec5cb22174772c935478b237", "title": "Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.05505.pdf"], "doi": []}, {"id": "b80f43b42b5320578d4c1e214fe1a8b6b45352ae", "title": "MSR-VTT: A Large Video Description Dataset for Bridging Video and Language", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Xu_MSR-VTT_A_Large_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Xu_MSR-VTT_A_Large_CVPR_2016_paper.pdf", "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/06/cvpr16.msr-vtt.tmei_-1.pdf", "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/10/cvpr16.supplementary.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780940", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.571", "http://doi.org/10.1109/CVPR.2016.571"]}, {"id": "81cb69e401b3b51e49ec378dba4bc0c8e33448e1", "title": "Applying Domain Randomization to Synthetic Data for Object Category Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09834.pdf"], "doi": []}, {"id": "7b1dd2708e1d7bf0fdcda437de1970a9a6facc0d", "title": "Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.07174.pdf"], "doi": []}, {"id": "18087bfafbe471f346c8b739522e64fa11e48b13", "title": "Visual Madlibs: Fill in the Blank Description Generation and Question Answering", "year": "2015", "pdf": ["http://acberg.com/papers/madlibs.pdf", "http://openaccess.thecvf.com/content_iccv_2015/papers/Yu_Visual_Madlibs_Fill_ICCV_2015_paper.pdf", "http://tamaraberg.com/papers/madlibs.pdf", "http://www.cs.unc.edu/~licheng/papers/iccv15_madlibs.pdf", "http://www.cs.unc.edu/~licheng/papers/iccv15_madlibs_supp.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Yu_Visual_Madlibs_Fill_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410640", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.283", "http://doi.org/10.1109/ICCV.2015.283"]}, {"id": "ad8642e186c5c81d06934d4e6fc249b7cbca40e8", "title": "Learning Transferable Architectures for Scalable Image Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1707.07012.pdf"], "doi": []}, {"id": "04427d8371cb9e66e2cdcd2035756203398a8bf1", "title": "Learning Answer Embeddings for Visual Question Answering", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578667"]}, {"id": "189b02caa2bb9ffb303154e35f60797ec8576f84", "title": "CRRN: Multi-scale Guided Concurrent Reflection Removal Network", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578600"]}, {"id": "3b8ad1f2335fc755e5cd75ee5922b8a0d432018a", "title": "A Fast and Compact Saliency Score Regression Network Based on Fully Convolutional Network", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00615.pdf"], "doi": []}, {"id": "2a5667702b0f1ff77dde8fb3e2e10d4e05e8de9d", "title": "Scene Parsing through ADE20K Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhou_Scene_Parsing_Through_CVPR_2017_paper.pdf", "http://people.csail.mit.edu/bzhou/publication/scene-parse-camera-ready.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100027", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.544", "http://doi.org/10.1109/CVPR.2017.544"]}, {"id": "10bb4ef7a6719ea132e00f0ab5680919a4131d99", "title": "BAM: Bottleneck Attention Module", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.06514.pdf"], "doi": []}, {"id": "a6e695ddd07aad719001c0fc1129328452385949", "title": "The New Data and New Challenges in Multimedia Research", "year": "2015", "pdf": [], "doi": []}, {"id": "f795b4ff67d3ecce0b988ecfc0589cc7e54f5dfa", "title": "Grounded Human-Object Interaction Hotspots from Video", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04558.pdf"], "doi": []}, {"id": "30f78071ac2bc965ffbf452a7b315d6dfddae30e", "title": "Lingusitic Analysis of Multi-Modal Recurrent Neural Networks", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/30f7/8071ac2bc965ffbf452a7b315d6dfddae30e.pdf"], "doi": []}, {"id": "10554295addeae86571a26de6c2ad7e274963953", "title": "Re-ranking Object Proposals for Object Detection in Automatic Driving", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05904.pdf"], "doi": []}, {"id": "af95ba2c08cf3317291dad554488dd951cd6ff80", "title": "Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04002.pdf"], "doi": []}, {"id": "c4cca330ec7289fac16d0793da98f705f6513219", "title": "Knowledge Projection for Effective Design of Thinner and Faster Deep Neural Networks", "year": "2017", "pdf": [], "doi": []}, {"id": "22a8b7ca2e6449cad31ae4f71bb3587751087e77", "title": "DeepBox: Learning Objectness with Convolutional Networks", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410642"]}, {"id": "0dcc768631d9ede8a3679e980b37204b782781b2", "title": "Stating the Obvious: Extracting Visual Common Sense Knowledge", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/55b9/251541eb09a6be4a317d4db1bc8d5dba07f7.pdf"], "doi": []}, {"id": "c1e714a9ec329629798a88ebff8657c349fec739", "title": "WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation", "year": "2017", "pdf": ["http://cedric.cnam.fr/~thomen/papers/Durand_CVPR_2017.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/papers/Durand_WILDCAT_Weakly_Supervised_CVPR_2017_paper.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/supplemental/Durand_WILDCAT_Weakly_Supervised_2017_CVPR_supplemental.pdf", "http://webia.lip6.fr/~durandt/pdfs/2017_CVPR/Durand_WILDCAT_CVPR_2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100114", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.631", "http://doi.org/10.1109/CVPR.2017.631"]}, {"id": "01959ef569f74c286956024866c1d107099199f7", "title": "VQA: Visual Question Answering", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410636"]}, {"id": "5c8ad080ccb3f5e3c999c2948029f0bd005d5635", "title": "Engaging Image Captioning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/5c8a/d080ccb3f5e3c999c2948029f0bd005d5635.pdf"], "doi": []}, {"id": "284be8be0c6bedc36dfe43229bc84345ab0aedc2", "title": "Faster Training of Mask R-CNN by Focusing on Instance Boundaries", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07069.pdf"], "doi": []}, {"id": "b6b9d29d25de42d78f09217c9cc457247d90fc70", "title": "Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints from Limited Training Data", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11823.pdf"], "doi": []}, {"id": "2198a3d3342442d6ed6608f2e2b0687f644b67d6", "title": "Dynamic High Resolution Deformable Articulated Tracking", "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07999.pdf"], "doi": []}, {"id": "340e55a44793226a51ad06612f340f2c520e3575", "title": "G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Wang_G2DeNet_Global_Gaussian_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100172", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.689", "http://doi.org/10.1109/CVPR.2017.689"]}, {"id": "833ada09759039b7c620b8930a50a0521d70b2c7", "title": "Attend in Groups: A Weakly-Supervised Deep Learning Framework for Learning from Web Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.09960.pdf"], "doi": []}, {"id": "fbb9cdd699baf86e9d616b259ada02449c2322ca", "title": "Active Testing: An Efficient and Robust Framework for Estimating Accuracy", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.00493.pdf"], "doi": []}, {"id": "f1d8c377093ecf64afd7f17383738e81666fe5ae", "title": "Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.10805.pdf"], "doi": []}, {"id": "858a2e0ca7ba129fda1a92959abe8770eb303bbe", "title": "Input Features Output Features Input Features Output Features Input Features Output Features Selected and", "year": "2017", "pdf": [], "doi": []}, {"id": "f5ce3c9eb539d2f4a85880db65ba3890a0fd8c6c", "title": "Zero-shot object prediction and context modeling using semantic scene knowledge", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/f5ce/3c9eb539d2f4a85880db65ba3890a0fd8c6c.pdf"], "doi": []}, {"id": "9634348d3bc7b86d0b644f6c14ab0c4294341905", "title": "Investigating Redundancy in Emoji Use: Study on a Twitter Based Corpus", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9634/348d3bc7b86d0b644f6c14ab0c4294341905.pdf"], "doi": []}, {"id": "068171535ac18a4b7b65be0748d483ce4c71a9a4", "title": "Event Specific Multimodal Pattern Mining with Image-Caption Pairs", "year": "2015", "pdf": ["https://arxiv.org/pdf/1601.00022.pdf"], "doi": []}, {"id": "346a877564351e4014441a1dc174b0369a759ba5", "title": "CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Kozerawski_CLEAR_Cumulative_LEARning_CVPR_2018_paper.pdf", "http://www-inst.cs.berkeley.edu/~ee290t/fa18/readings/Kozerawski_CLEAR_Cumulative_LEARning_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578461", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00363", "http://doi.org/10.1109/CVPR.2018.00363"]}, {"id": "2b45c35aa63180ef83e7f8e6f55405db9c688b0e", "title": "Unsupervised Domain Adaptation with Similarity Learning", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578933"]}, {"id": "a8420e7fa53b81b8069ced8d9c743c141e2fc432", "title": "Real-Time Multiple Object Tracking - A Study on the Importance of Speed", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.03572.pdf"], "doi": []}, {"id": "ea743597a5f48babef1982259566d76a9bf66bf2", "title": "Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/CameraReady/1276.pdf", "http://openaccess.thecvf.com/content_cvpr_2018/papers/Ding_Context_Contrasted_Feature_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578352", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00254", "http://doi.org/10.1109/CVPR.2018.00254"]}, {"id": "2770af2c74f9b82f2167cf5773ccc94d482ac8d4", "title": "Gossip training for deep learning", "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.09726.pdf"], "doi": []}, {"id": "ff5869f420d33511c22e60bbcff072c3cde3ebc4", "title": "Regional Interactive Image Segmentation Networks", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Liew_Regional_Interactive_Image_ICCV_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237559", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.297", "http://doi.org/10.1109/ICCV.2017.297"]}, {"id": "3aa66f2829ef440842c71a52cdaff30398a90ccb", "title": "Pointly-Supervised Action Localization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.11333.pdf"], "doi": []}, {"id": "15a148957469bc8b91bd7cc31aa1f0c6584a1571", "title": "DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575485"]}, {"id": "ccba451687f83c463deeefb69c1f4a781de2d638", "title": "Full-Network Embedding in a Multimodal Embedding Pipeline", "year": "2017", "pdf": [], "doi": []}, {"id": "0219ced7a3afcd8e7584b24809bac30304f9288e", "title": "L ] 3 1 M ay 2 01 7 Adversarial Ranking for Language Generation", "year": "2017", "pdf": [], "doi": []}, {"id": "59f4df3087c22e0e13574bb7d20e9d41e74cb9a5", "title": "Visual Re-ranking with Natural Language Understanding for Text Spotting", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12738.pdf"], "doi": []}, {"id": "3fb61e0d133d0971c853b8435fea99150e15cdbb", "title": "Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)", "year": "2018", "pdf": ["https://arxiv.org/pdf/1705.00366.pdf"], "doi": []}, {"id": "cb8f1f77a8b19d99dfe0c7b50dae3978cf646aa9", "title": "Adaptive attention fusion network for visual question answering", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8019540", "http://doi.ieeecomputersociety.org/10.1109/ICME.2017.8019540", "http://doi.org/10.1109/ICME.2017.8019540"]}, {"id": "4f6d8d4d460517297b419242a7e9ab3f9a307a72", "title": "Feature Extraction for Image Selection Using Machine Learning", "year": "2017", "pdf": [], "doi": []}, {"id": "0c36c988acc9ec239953ff1b3931799af388ef70", "title": "Face Detection Using Improved Faster RCNN", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02142.pdf"], "doi": []}, {"id": "1baa9fdfb27f561be67c52ef55b0e3587f306cff", "title": "Image Captioning with Attention", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/1baa/9fdfb27f561be67c52ef55b0e3587f306cff.pdf"], "doi": []}, {"id": "8b35c00edfa4edfd7a99d816e671023d2c000d55", "title": "AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578241"]}, {"id": "a0e03c5b647438299c79c71458e6b1776082a37b", "title": "Areas of Attention for Image Captioning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.01033.pdf"], "doi": []}, {"id": "9976b88d15f89b6c82b16564735d489a7524821d", "title": "Learning Visual N-Grams from Web Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.09161.pdf"], "doi": []}, {"id": "0b938c4a993e7e2fda81426924cb91c108a7830c", "title": "Which Emoji Talks Best for My Picture?", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8609639"]}, {"id": "4041cf003f797007fe53ac89fd57072f97257abd", "title": "End-to-end policy learning for active visual categorization.", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4041/cf003f797007fe53ac89fd57072f97257abd.pdf"], "doi": []}, {"id": "f741cba061655581f6fbb628613d0669c4bdecd5", "title": "Deep Cosine Metric Learning for Person Re-identification", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354191"]}, {"id": "c91e94e981084f5d9c3c1479fa90b8b091826d1d", "title": "Variational Bayesian Multiple Instance Learning with Gaussian Processes", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099576"]}, {"id": "03c820f35afdc38dd05e4c663d2877e2602bcde0", "title": "Semantically Guided Visual Question Answering", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354309", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00205", "http://doi.org/10.1109/WACV.2018.00205"]}, {"id": "23a0cfaceb35413bd6caad437e37d566fcfdcc64", "title": "MindCamera: Interactive Sketch-Based Image Retrieval and Synthesis", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8267031"]}, {"id": "9d5a5517650d5f9a7d9818bcc1eb59ba65d316e1", "title": "Conditional Generative Adversarial Network for Structured Domain Adaptation", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Hong_Conditional_Generative_Adversarial_CVPR_2018_paper.pdf", "https://weixianghong.github.io/publications/papers/CVPR_18.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578243", "http://doi.org/10.1109/cvpr.2018.00145"]}, {"id": "f87aa7d7b746e24e3b08fd3375331068ecd13311", "title": "Mask-SLAM: Robust Feature-Based Monocular SLAM by Masking Using Semantic Segmentation", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575524"]}, {"id": "3bb0ab7ebe1ffb83aa9775ffe2602407c9d6329d", "title": "Active Decision Boundary Annotation with Deep Generative Models", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237827"]}, {"id": "93adca9ce6f4a0fab9ea027c90b4df828cfa10d7", "title": "Learning Actionable Representations from Visual Observations", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593951"]}, {"id": "6962505b78d0cec04b992a059cc58870c361c971", "title": "Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1811.00218.pdf"], "doi": []}, {"id": "747e9b36c5a1b0b8a9572da0ab416ddd1e1d2d33", "title": "Augmentation for Visual Question Answering", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/747e/9b36c5a1b0b8a9572da0ab416ddd1e1d2d33.pdf"], "doi": []}, {"id": "85473d7bd0b73488f22d8443583165fdbd3d221d", "title": "Product Quantized Translation for Fast Nearest Neighbor Search", "year": "2018", "pdf": [], "doi": ["https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16953", "https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewFile/16953/16702"]}, {"id": "86d9f836c5fc542e987601a102c2b6cdbca1d64f", "title": "Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780602"]}, {"id": "c719a941d3ab00e45d1d74e7533ed59cc0740ae2", "title": "Does Optical Character Recognition and Caption Generation Improve Emotion Detection in Microblog Posts?", "year": "2017", "pdf": ["http://www.romanklinger.de/publications/klinger2017-nldb.pdf", "http://www.romanklinger.de/talks/nldb.pdf"], "doi": ["https://doi.org/10.1007/978-3-319-59569-6_39"]}, {"id": "4f618cbf19917ce5b8703adbc14e15b0bf0d35cc", "title": "Multi-View Dynamic Facial Action Unit Detection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.07863.pdf"], "doi": []}, {"id": "1f2b28dc48c8f2c0349dce728d7b6a0681f58aea", "title": "A Dataset for Lane Instance Segmentation in Urban Environments", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.01347.pdf"], "doi": []}, {"id": "7d6132a884d2b154059c461e107c7a8c41603ef7", "title": "Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00872.pdf"], "doi": []}, {"id": "8e06f628d0566e31366cf046b4a83ac4724ea7c3", "title": "Categorizing Concepts with Basic Level for Vision-to-Language", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Categorizing_Concepts_With_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578619", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00521", "http://doi.org/10.1109/CVPR.2018.00521"]}, {"id": "72048081cfe678f700c52e1c7a56713a8e0865b6", "title": "Unsupervised Adversarial Visual Level Domain Adaptation for Learning Video Object Detectors from Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02074.pdf"], "doi": []}, {"id": "974aa04b051bd2493bf4aaa5cd410dcb8f3b264d", "title": "Red Hen Lab: Dataset and Tools for Multimodal Human Communication Research", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1007/s13218-017-0505-9"]}, {"id": "13ad6164dba75845f0f397e9314ad596e74eb946", "title": "Learning to Estimate 3D Human Pose and Shape from a Single Color Image", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578153"]}, {"id": "91e89cedd4093bfe176532530ddb960f2767aca5", "title": "Cross-Domain Self-Supervised Multi-task Feature Learning Using Synthetic Imagery", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578184"]}, {"id": "f28e2bb46e49799589787e466c3ca966a0897bf7", "title": "Textually Customized Video Summaries", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.01528.pdf"], "doi": []}, {"id": "bcb35a8eb4cea46755c7430618e4ecfa4647b360", "title": "Deep Joint Semantic-Embedding Hashing", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bcb3/5a8eb4cea46755c7430618e4ecfa4647b360.pdf"], "doi": []}, {"id": "4b59e1fbcd68d616c9e5d02a62d332b0b2c268c5", "title": "Training Recurrent Neural Network through Moment Matching for NLP Applications", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4b59/e1fbcd68d616c9e5d02a62d332b0b2c268c5.pdf"], "doi": []}, {"id": "b8ccc5341a1b0214e9d155b019962023f344c2ee", "title": "Incremental Learning of Object Detectors without Catastrophic Forgetting", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06977.pdf"], "doi": []}, {"id": "45dd2a3cd7c27f2e9509b023d702408f5ac11c9d", "title": "Stacked Cross Attention for Image-Text Matching", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08024.pdf"], "doi": []}, {"id": "02a4e2569b8033eff87099ad402f251d02213cfe", "title": "Learning-Based Cloth Material Recovery from Video", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237732"]}, {"id": "ff23167f18723faf41265cd36ee2cf1de45a3048", "title": "Straight to Shapes: Real-Time Detection of Encoded Shapes", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099931"]}, {"id": "47b4c33621bc0e636d6c268ad6acb319e12abbee", "title": "StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1710.10916.pdf"], "doi": []}, {"id": "26d27a6de0360ed690248a9dd08e4ec0818472b0", "title": "DehazeGAN: When Image Dehazing Meets Differential Programming", "year": "2018", "pdf": ["http://www.pengxi.me/wp-content/uploads/Papers/2018-IJCAI-DehazeGAN.pdf"], "doi": ["https://doi.org/10.24963/ijcai.2018%2F172", "https://doi.org/10.24963/ijcai.2018/172"]}, {"id": "2284ba28bd3b1afaf06afb8c2a94638e350b3ecb", "title": "Boosting Object Proposals: From Pascal to COCO", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01226.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410538", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.181", "http://doi.org/10.1109/ICCV.2015.181"]}, {"id": "21d7130230162af2a4cc1b9375bfe9b37dbbd499", "title": "Origami: A 803-GOp/s/W Convolutional Network Accelerator", "year": "2017", "pdf": ["https://arxiv.org/pdf/1512.04295.pdf"], "doi": []}, {"id": "efbac99adf8628aae7f070e5b4388a295956f9d2", "title": "CondenseNet: An Efficient DenseNet Using Learned Group Convolutions", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578389"]}, {"id": "015d25f66514ce0a966300944201d45968a104ba", "title": "SIMPLE IMAGE DESCRIPTION GENERATOR VIA A LINEAR PHRASE-BASED MODEL R\u00e9mi Lebret", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/015d/25f66514ce0a966300944201d45968a104ba.pdf"], "doi": []}, {"id": "47f8a217de3df8d70c3ac7fac73696a9104b1294", "title": "Weakly-supervised image captioning based on rich contextual information", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-017-5236-2"]}, {"id": "1fefc1d288a87fe218ba25024c4b2b6ef345738e", "title": "Self-ensembling for domain adaptation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/1fef/c1d288a87fe218ba25024c4b2b6ef345738e.pdf"], "doi": []}, {"id": "688cb9fd33769b152806c04ef6fc276629a9f300", "title": "LocNet: Improving Localization Accuracy for Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.07763.pdf"], "doi": []}, {"id": "c96f012f4915398259e7e223810c57898b5e1a76", "title": "Fast LIDAR-based Road Detection Using Convolutional Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c96f/012f4915398259e7e223810c57898b5e1a76.pdf"], "doi": []}, {"id": "c562e95b7906066be4210d00c4f6187475e6e13a", "title": "Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.10535.pdf"], "doi": []}, {"id": "a24a0126f76ba1423ac3548ef95aa24ac4e670dd", "title": "How Would You Say It ? Eliciting Lexically Diverse Data for Supervised Semantic Parsing", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3870/0128bc3ce57a04c46458c3898eaaa1166508.pdf"], "doi": []}, {"id": "99975f84728140154a35b0763753b35bc44e1d5a", "title": "Video Description: A Survey of Methods, Datasets and Evaluation Metrics", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.00186.pdf"], "doi": []}, {"id": "a6a6cfae45e8633c01793debf43592b7d515f65d", "title": "From ImageNet to Mining: Adapting Visual Object Detection with Minimal Supervision", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/a6a6/cfae45e8633c01793debf43592b7d515f65d.pdf"], "doi": []}, {"id": "acf13c52c86a3b38642ba0c6cbcd1b771778965c", "title": "NAACL HLT 2018 Generalization in the Age of Deep Learning Proceedings of the Workshop", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e255/eb6d8e46275387f71986a26d81fd746e0147.pdf"], "doi": []}, {"id": "fd716faea00fb6ec433a62c79aced17d51de8d23", "title": "Cascaded Contextual Region-based Convolutional Neural Network for Event Detection from Time Series Signals: A Seismic Application", "year": "2017", "pdf": [], "doi": []}, {"id": "64bff565c83c6ce3fac783d8d67191af99803701", "title": "Learning to Co-Generate Object Proposals with a Deep Structured Network", "year": "2016", "pdf": ["http://infoscience.epfl.ch/record/217984/files/HayderHeSalzmannCVPR16.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780650", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.281", "http://doi.org/10.1109/CVPR.2016.281"]}, {"id": "1779b6a17ee68afafb6801477b165f19901689b2", "title": "Object Contour Detection with a Fully Convolutional Encoder-Decoder Network", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780397"]}, {"id": "5ac18d505ed6d10e8692cbb7d33f6852e6782692", "title": "The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00982.pdf"], "doi": []}, {"id": "f2b95f135b95c3df4f6ebe6015098a2e1667711d", "title": "Weakly Supervised Object Localization Using Things and Stuff Transfer", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.08000.pdf"], "doi": []}, {"id": "e2c122bea06dfa067712cdb58ce474144f93af07", "title": "Phrase-based Image Captioning with Hierarchical LSTM Model", "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.05557.pdf"], "doi": []}, {"id": "acd26d5b85e979d73101ac790bfdedf17bfe8ed1", "title": "Learning from PhotoShop Operation Videos : the PSOV Dataset", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/acd2/6d5b85e979d73101ac790bfdedf17bfe8ed1.pdf"], "doi": []}, {"id": "0e0900b88c33b671be5dd2ded9885b6526d6b429", "title": "From captions to visual concepts and back", "year": "2015", "pdf": ["https://arxiv.org/pdf/1411.4952.pdf"], "doi": []}, {"id": "3e08a3912ebe494242f6bcd772929cc65307129c", "title": "Few-Shot Image Recognition by Predicting Parameters from Activations", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578853"]}, {"id": "47a2b1ba7e4275174a017a290f2e5de7de0acb00", "title": "Semantically Coherent Co-Segmentation and Reconstruction of Dynamic Scenes", "year": "2017", "pdf": ["http://epubs.surrey.ac.uk/813877/1/cvprFinalOpenAccess.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/papers/Mustafa_Semantically_Coherent_Co-Segmentation_CVPR_2017_paper.pdf", "https://arminmustafa.github.io/docs/cvpr17/ArminCVPR2017.pdf", "https://arminmustafa.github.io/docs/cvpr17/ppt.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100075", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.592", "http://doi.org/10.1109/CVPR.2017.592"]}, {"id": "6c0c368fca391b4456e64d2943d0bcbe6d8e1ecc", "title": "A Pipeline for Creative Visual Storytelling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08077.pdf"], "doi": []}, {"id": "dc7a4d5ba20ca07d29c360b26e1e72afae9a77be", "title": "The ApolloScape Open Dataset for Autonomous Driving and its Application", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06184.pdf"], "doi": []}, {"id": "9120d59f2ca86954b45d254cae1409cb0806d9c7", "title": "DenseFuse: A Fusion Approach to Infrared and Visible Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.08361.pdf"], "doi": []}, {"id": "428017f7a6df4d667275c7ac9b3feba39b70e4ae", "title": "CNN-RNN: A Unified Framework for Multi-label Image Classification", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.04573.pdf"], "doi": []}, {"id": "aa74e63360c341f47a921e0043c5d58d55807fe4", "title": "Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.05672.pdf"], "doi": []}, {"id": "ecbaa92c289f4f5ff9a57b19a2725036a92311f5", "title": "Focused Evaluation for Image Description with Binary Forced-Choice Tasks", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ecba/a92c289f4f5ff9a57b19a2725036a92311f5.pdf"], "doi": []}, {"id": "b3eb61c3542e0c6bafb4c1acd05cffc0970faa85", "title": "Region-Based Image Retrieval Revisited", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.09106.pdf"], "doi": []}, {"id": "904b322a61d9be9c0b1023946320f9245533085e", "title": "Multi-Residual Networks", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/95cd/6df1b921859103f2eea702e8d3622a862a08.pdf"], "doi": []}, {"id": "62a5f2a142fe636632f6467176ab18bb86e6398e", "title": "Pixelated Semantic Colorization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.10889.pdf"], "doi": []}, {"id": "a0e286f3c6a72c857ffd03bd8ab9a9f9b98c4432", "title": "AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04452.pdf"], "doi": []}, {"id": "333be4858994e6d9364341aeb520f7800a0f6a07", "title": "Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.05424.pdf"], "doi": []}, {"id": "23ef40af4fda9c7db8fd7596d34446303c378793", "title": "Towards a Generalized Approach for Deep Neural Network Based Event Processing for the Internet of Multimedia Things", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8331844", "http://doi.org/10.1109/ACCESS.2018.2823590"]}, {"id": "b0760764dc573b519f76d5a79531d49af333c67a", "title": "Neural Style Transfer: A Review", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.04058.pdf"], "doi": []}, {"id": "5fa587381a9e4308163b3a5395985f0375c3cf7d", "title": "Deep Extreme Cut: From Extreme Points to Object Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09081.pdf"], "doi": []}, {"id": "2f005b31b41face8a8b157e2ce7f97ece5b61391", "title": "L 1 Graph Based Sparse Model for Label Denoising", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/2f00/5b31b41face8a8b157e2ce7f97ece5b61391.pdf"], "doi": []}, {"id": "ede3af38e30ca332af0c1ce3bd5144070f7fb7f3", "title": "SGN: Sequential Grouping Networks for Instance Segmentation", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Liu_SGN_Sequential_Grouping_ICCV_2017_paper.pdf", "http://www.cs.toronto.edu/~fidler/papers/sgn_iccv17.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237640", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.378", "http://doi.org/10.1109/ICCV.2017.378"]}, {"id": "284af686292a6119129b410413831f8d2363fcc6", "title": "Learning Representation for Scene Understanding: Epitomes, CRFs, and CNNs", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/284a/f686292a6119129b410413831f8d2363fcc6.pdf"], "doi": []}, {"id": "73f1a3d88defbd5481214e27da7df501d0e31fb1", "title": "Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.01703.pdf"], "doi": []}, {"id": "2eef20a11324686099ee6f9b1a7613444b0d2112", "title": "Dual-Path Convolutional Image-Text Embedding with Instance Loss", "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.05535.pdf"], "doi": []}, {"id": "f9255703f0a89c9ca2e9256595a0526829ff4402", "title": "On the Importance of Visual Context for Data Augmentation in Scene Understanding", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.02492.pdf"], "doi": []}, {"id": "e8e43abbc8bee64a53af64ceca90bfb687f7bb9d", "title": "Fast Object Class Labelling via Speech", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.09461.pdf"], "doi": []}, {"id": "3f775e3be9e1a00ebf4fd281e524932e88cec0ae", "title": "Deep Contextual Recurrent Residual Networks for Scene Labeling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.03594.pdf"], "doi": []}, {"id": "c5b9a96fcb07f538be3181922e5f1a24a7936783", "title": "Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.09563.pdf"], "doi": []}, {"id": "d5673c53b3643372dd8d35136769ecd73a6dede3", "title": "A Deep Learning Framework for Smart Street Cleaning", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7944927", "http://doi.ieeecomputersociety.org/10.1109/BigDataService.2017.49", "http://doi.org/10.1109/BigDataService.2017.49"]}, {"id": "456983805a8781d6429bed1ed66dc9f3902767af", "title": "Seeing with Humans : Gaze-Assisted Neural Image", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/4569/83805a8781d6429bed1ed66dc9f3902767af.pdf"], "doi": []}, {"id": "a759570e6ef674cd93068020c2e6bd036961f7c6", "title": "SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.08435.pdf"], "doi": []}, {"id": "e7b92fc6e2f1a13a3076a48a78e03badacb0465b", "title": "Deep Cauchy Hashing for Hamming Space Retrieval", "year": "2018", "pdf": ["http://ise.thss.tsinghua.edu.cn/~mlong/doc/deep-cauchy-hashing-cvpr18.pdf", "http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_Deep_Cauchy_Hashing_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578232", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00134", "http://doi.org/10.1109/CVPR.2018.00134"]}, {"id": "7892606127c94d0be5c9bea5b6cb539f7fe3bf39", "title": "Combining Multiple Cues for Visual Madlibs Question Answering", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11263-018-1096-0"]}, {"id": "e42b2981f4e8de54213d624d1ef12bad4fe02f0a", "title": "Through-Wall Human Pose Estimation Using Radio Signals", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578866"]}, {"id": "c896502edcdec38466e7d66f38fb53a57c8e05db", "title": "Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.00116.pdf"], "doi": []}, {"id": "30a68bea6a43c239d899d7f02bb8ef9f3c5a8f47", "title": "Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild", "year": "2018", "pdf": ["https://arxiv.org/pdf/1709.01305.pdf"], "doi": []}, {"id": "fdce9cbe5c726201575b3c8a8c1af0752f1af53f", "title": "MAttNet: Modular Attention Network for Referring Expression Comprehension", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578240"]}, {"id": "91bb3680cee8cd37b80e07644f66f9cccf1b1aff", "title": "PASCAL Boundaries: A Semantic Boundary Dataset with a Deep Semantic Boundary Detector", "year": "2017", "pdf": ["http://www.cs.jhu.edu/~alanlab/Pubs17/premachandran2017pascalboundaries.pdf", "https://www.computer.org/csdl/proceedings/wacv/2017/4822/00/07926599.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7926599", "http://doi.org/10.1109/WACV.2017.16"]}, {"id": "09b2e7af73689dbdba1547e19111a6ee06767906", "title": "PoseTrack: A Benchmark for Human Pose Estimation and Tracking", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578640"]}, {"id": "38e3c26829e38c6b56f7c541e0c4445820fab0fe", "title": "BOLD5000: A public fMRI dataset of 5000 images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.01281.pdf"], "doi": []}, {"id": "57bfbd06e94c5def35c1dde901bb4f1c839dbcdf", "title": "Deep patch learning for weakly supervised object classification and discovery", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02429.pdf"], "doi": []}, {"id": "165ef2b5f86b9b2c68b652391db5ece8c5a0bc7e", "title": "Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780717"]}, {"id": "944faf7f14f1bead911aeec30cc80c861442b610", "title": "Action Tubelet Detector for Spatio-Temporal Action Localization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01861.pdf"], "doi": []}, {"id": "729a30040132909cda0eab2c6c4ba60d6d1941b5", "title": "Image-based Plant Species Identification with Deep Convolutional Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/729a/30040132909cda0eab2c6c4ba60d6d1941b5.pdf"], "doi": []}, {"id": "28af8e1a3cb3a158f8a642c8493fcfb207743d0a", "title": "Better Image Segmentation by Exploiting Dense Semantic Predictions", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.01481.pdf"], "doi": []}, {"id": "139ab79a0aae5d4346f907b7b29288d09ef373fa", "title": "A Baseline for Multi-Label Image Classification Using Ensemble Deep CNN", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08412.pdf"], "doi": []}, {"id": "24aee34d1fb3cf5b1cddc2c6ef9259506be4e9c0", "title": "Visual Context Learning with Big Data Analytics", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7836722", "http://doi.org/10.1109/ICDMW.2016.0091"]}, {"id": "9b18cc5c938062161a4b6b0c71ee7a6c550a15f7", "title": "A Scalable Optimization Mechanism for Pairwise based Discrete Hashing.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10810.pdf"], "doi": []}, {"id": "ad9b3dc6c0e54070cec79df86458ed38566da1ff", "title": "Automated Image Captioning for Rapid Prototyping and Resource Constrained Environments", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.01393.pdf"], "doi": []}, {"id": "2a74b00daa80e64cde5256bc014d1b011926b97b", "title": "Shake-Shake regularization", "year": "2017", "pdf": [], "doi": []}, {"id": "40c1aec7e0830bf9dd8a689d671024567311ae72", "title": "Interact as You Intend: Intention-Driven Human-Object Interaction Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.09796.pdf"], "doi": []}, {"id": "4d1e28368e1121872bcd4ce75bc7ba5e43bd42d0", "title": "Attend to You: Personalized Image Captioning with Context Sequence Memory Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.06485.pdf"], "doi": []}, {"id": "b6f682648418422e992e3ef78a6965773550d36b", "title": "CBMM Memo No . 061 February 8 , 2017 Full interpretation of minimal images", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/b6f6/82648418422e992e3ef78a6965773550d36b.pdf"], "doi": []}, {"id": "2595319371a06449e3f8cef251303aecbb9e731e", "title": "A Review on Object Recognition for Blind People Based on Deep Learning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2595/319371a06449e3f8cef251303aecbb9e731e.pdf"], "doi": []}, {"id": "e7df750805d6c025d0a1a74a05a83bcf8cc63dd7", "title": "Assessment of crowdsourcing and gamification loss in user-assisted object segmentation", "year": "2015", "pdf": ["http://upcommons.upc.edu/bitstream/handle/2117/81293/asknseek.pdf;jsessionid=469B72384B7C56D4A331D68A53942294?sequence=1"], "doi": ["https://doi.org/10.1007/s11042-015-2897-6"]}, {"id": "abd4152773ebb97b90163b9a6bbdf2075e825481", "title": "Procedural Text Generation from an Execution Video", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/abd4/152773ebb97b90163b9a6bbdf2075e825481.pdf"], "doi": []}, {"id": "72f8df596eb9bb3a8c8206329083c42e70fcd9fd", "title": "Will People Like Your Image?", "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.05203.pdf"], "doi": []}, {"id": "9684a54d9ff94855a40a2dc3eeb1ff16b44795fe", "title": "Human, Object and Scene Centric Image Retrieval Engine to Enhance Image Management", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8261019"]}, {"id": "b3b85d0a697c9b0309965151dcc396eb70adf46e", "title": "Shallowing Deep Networks: Layer-wise Pruning based on Feature Representations.", "year": "2018", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/30296213", "http://doi.org/10.1109/TPAMI.2018.2874634"]}, {"id": "5925a25dfe107c49c636eccb8f9fd1aeef7b438c", "title": "Temporal Shift Module for Efficient Video Understanding", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08383.pdf"], "doi": []}, {"id": "821ba3eba1e36a29cc482f5378f4a0d0f6893159", "title": "Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.07926.pdf"], "doi": []}, {"id": "1ca06a9c5e80bc0d4011f0d6f6ccc1a5ee746844", "title": "Automatic Image Cropping: A Computational Complexity Study", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Chen_Automatic_Image_Cropping_CVPR_2016_paper.pdf", "http://pages.cs.wisc.edu/~liangz/12_Chen_Automatic_Image_Cropping_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780430", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.61", "http://doi.org/10.1109/CVPR.2016.61"]}, {"id": "64a336f952ec67f85fe00092847d50dd29e4cddc", "title": "Fast Screening Algorithm for Template Matching FAST SCREENING ALGORITHM FOR TEMPLATE MATCHING", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/64a3/36f952ec67f85fe00092847d50dd29e4cddc.pdf"], "doi": []}, {"id": "cd8398e82e0c0cc4276a1694fd333214ede337ea", "title": "Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02563.pdf"], "doi": []}, {"id": "8e416d760feb5f23bc1a6dab98eb1f6e75ab8907", "title": "Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.08251.pdf"], "doi": []}, {"id": "f7186eb3d717694d4ab1730a8d0f662e90c44d6f", "title": "A Computational Study on Word Meanings and Their Distributed Representations via Polymodal Embedding", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f718/6eb3d717694d4ab1730a8d0f662e90c44d6f.pdf"], "doi": []}, {"id": "35c5b84fa47e5b6cee201f831507f62482ccebcc", "title": "CUNI System for the WMT 17 Multimodal Traslation Task", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/35c5/b84fa47e5b6cee201f831507f62482ccebcc.pdf"], "doi": []}, {"id": "b63041d05b78a66724fbcb2803508999bf885d6b", "title": "Deep Sets", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06114.pdf"], "doi": []}, {"id": "d318f3ca49f7f2159b9fc0face08eb284d5442dc", "title": "Scene Text Detection via Holistic, Multi-Channel Prediction", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.09002.pdf"], "doi": []}, {"id": "f81f5da2a1e4eb80b465b8dffca4c9e583a8a8a6", "title": "Rapid Object Detection Systems , Utilising Deep Learning and Unmanned Aerial Systems ( Uas ) for Civil Engineering Applications", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f81f/5da2a1e4eb80b465b8dffca4c9e583a8a8a6.pdf"], "doi": []}, {"id": "45e2aa7706fcedcbb2d93304a9824fe762b8b3b0", "title": "DAC-SDC Low Power Object Detection Challenge for UAV Applications", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.00110.pdf"], "doi": []}, {"id": "8f45907fba8fce5e9d958cf66cb68b406858fbb6", "title": "Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.05477.pdf"], "doi": []}, {"id": "f672bf42dbefb6b40921c00a05f60284934e9948", "title": "LDS-Inspired Residual Networks", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f672/bf42dbefb6b40921c00a05f60284934e9948.pdf"], "doi": []}, {"id": "c0343f9cc5f16166bda83815812c4c71ab3258e3", "title": "Hierarchical LSTMs with Adaptive Attention for Visual Captioning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.11004.pdf"], "doi": []}, {"id": "e075c5ef9d7d4ef77c92008ffaa7ac12e60383c1", "title": "Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.03905.pdf"], "doi": []}, {"id": "fb6bcf5763fe7ec7366f5991400090fa503613a7", "title": "Reduce Cognitive Burden on Drivers through Contextualising Environments", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8417781", "http://doi.org/10.1109/VTCSpring.2018.8417781"]}, {"id": "a133374b9630bbe6eb2b7de8c3204aa57e75c582", "title": "A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping.", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/a133/374b9630bbe6eb2b7de8c3204aa57e75c582.pdf"], "doi": []}, {"id": "ccbd7e417158e7ae0f9f61c3b6d1e5a3317cce34", "title": "Object Proposals in Computer Vision", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/7fb4/19f28652e4d1b1ddab1a19bdc5be1c7bbb62.pdf"], "doi": []}, {"id": "aa09ade36424fd83f067f234baffde294800e705", "title": "Is a Picture Worth Ten Thousand Words in a Review Dataset?", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.07496.pdf"], "doi": []}, {"id": "30ccfd2b4b6d5b30581356ccefcf96fd77c1766a", "title": "Overview of the ImageCLEF 2014 Scalable Concept Image Annotation Task", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/a346/060e3b71a0553eaa4bc28fbc0114b1798fec.pdf"], "doi": []}, {"id": "a25c32ea0292af5eacd6e9e0ed53b9ff7e65433f", "title": "Learning to Learn from Web Data Through Deep Semantic Embeddings", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.06368.pdf"], "doi": []}, {"id": "247b14570940601f5c7a2da1db532ecf1c302288", "title": "Dual Attention Networks for Multimodal Reasoning and Matching", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.00471.pdf"], "doi": []}, {"id": "bb021f58f8822d12f5747d583a46005ade4a0b10", "title": "Breaking Microsoft \u2019 s CAPTCHA", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/bb02/1f58f8822d12f5747d583a46005ade4a0b10.pdf"], "doi": []}, {"id": "a7066c13ba21817abcf8ff955740493adf95b02c", "title": "Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.09280.pdf"], "doi": []}, {"id": "c06447df3e50ec451240205cefa0708caee8ab8c", "title": "Picture it in your mind: generating high level visual representations from textual descriptions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.07287.pdf"], "doi": []}, {"id": "4ecaa651722a98c2847377f3ae1c70294b4791ce", "title": "Few-Example Object Detection with Model Communication.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.08249.pdf"], "doi": []}, {"id": "0b4d3e59a0107f0dad22e74054bab1cf1ad9c32e", "title": "Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.07332.pdf"], "doi": []}, {"id": "28b72ad9229f38ec61f950e1d794d6af070d1800", "title": "Zero-shot Object Prediction using Semantic Scene Knowledge", "year": "2017", "pdf": ["https://arxiv.org/pdf/1604.07952.pdf"], "doi": []}, {"id": "877c5a3ad915c2bbb5595252d08163f34ce58957", "title": "LCR-Net: Localization-Classification-Regression for Human Pose", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Rogez_LCR-Net_Localization-Classification-Regression_for_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099617", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.134", "http://doi.org/10.1109/CVPR.2017.134"]}, {"id": "e8e662e45e39249756d2b0090782434a5cf1f4aa", "title": "VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Hou_VegFru_A_Domain-Specific_ICCV_2017_paper.pdf", "http://openaccess.thecvf.com/content_ICCV_2017/supplemental/Hou_VegFru_A_Domain-Specific_ICCV_2017_supplemental.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237328", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.66", "http://doi.org/10.1109/ICCV.2017.66"]}, {"id": "1db6a35c42e86d5cd64ad2a4803fd683647fab96", "title": "Tiny Transform Net for Mobile Image Stylization", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3079034"]}, {"id": "8efb48fdb8616da5133efb8659cd96c53529f76a", "title": "Active Vision Dataset Benchmark", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w40/Ammirato_Active_Vision_Dataset_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575447", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00277", "http://doi.org/10.1109/CVPRW.2018.00277"]}, {"id": "71afbb37a81a44299872bee9ae888f4129962e18", "title": "RECURRENT NEURAL FEEDBACK MODEL FOR AUTOMATED IMAGE ANNOTATION", "year": "2017", "pdf": [], "doi": []}, {"id": "9d8747468f0fed8e335656d7fe9737e4dc21c798", "title": "RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.03353.pdf"], "doi": []}, {"id": "9f545b9006970f7626b7b121c5c3c66204f1ba40", "title": "Improving Pairwise Ranking for Multi-label Image Classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.03135.pdf"], "doi": []}, {"id": "2ba540ca70c7dee81e13768792aa7571952987f6", "title": "Drivable Road Detection Based on Dilated FPN with Feature Aggregation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8372075", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2017.00172", "http://doi.org/10.1109/ICTAI.2017.00172"]}, {"id": "2e8b08c8df95d2ef8c0d03820094608e9cf456ab", "title": "License Plate Detection and Recognition in Unconstrained Scenarios", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2e8b/08c8df95d2ef8c0d03820094608e9cf456ab.pdf"], "doi": []}, {"id": "8331fb280f083767fe85ba476862e519e0275233", "title": "OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.02611.pdf"], "doi": []}, {"id": "54e0b4f63e6ed966d76b6ef83488249fd09d3a43", "title": "Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099857"]}, {"id": "f11f609facfb650ed8e659236a04bc0a664cb665", "title": "An Analysis of Scale Invariance in Object Detection - SNIP", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578475"]}, {"id": "a8773da25b133d258132d646024bf5ffd5694302", "title": "A Bottom-Up Approach Based on Semantics for the Interpretation of the Main Camera Stream in Soccer Games", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575392"]}, {"id": "666e08b6921a28fed75f35dd70d322f0edc06e41", "title": "Rain Removal in Traffic Surveillance: Does it Matter?", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12574.pdf"], "doi": []}, {"id": "1ac6a33f04f6c5a8084c15c85295f987cc8e3d72", "title": "FVQA: Fact-Based Visual Question Answering", "year": "2018", "pdf": ["https://arxiv.org/pdf/1606.05433.pdf"], "doi": []}, {"id": "3ab5d67310aa3592b68e9ef55df4603507d0d486", "title": "Learning Spatial Transforms for Refining Object Segment Proposals", "year": "2017", "pdf": ["https://www.computer.org/csdl/proceedings/wacv/2017/4822/00/07926595.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7926595", "http://doi.org/10.1109/WACV.2017.12"]}, {"id": "757b27a3ceb2293b8284fc24a7084a0c3fc2ae21", "title": "Data Distillation: Towards Omni-Supervised Learning", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578531"]}, {"id": "0d4dbd59e42e615ccf6cd4f71203be97afac48fb", "title": "End-to-End Joint Semantic Segmentation of Actors and Actions in Video", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0d4d/bd59e42e615ccf6cd4f71203be97afac48fb.pdf"], "doi": []}, {"id": "81d327ec41c67728b15438bca86d10b72de1d88f", "title": "Visual Affordance and Function Understanding: A Survey", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.06775.pdf"], "doi": []}, {"id": "df5094b2e8cf7e3bde3943ca7a56eb879b8e34ab", "title": "A Concatenated Residual Convolutional Network for Image Deblurring", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/df50/94b2e8cf7e3bde3943ca7a56eb879b8e34ab.pdf"], "doi": []}, {"id": "b8298cf0056af5afa3185181ddd5f6bb03181696", "title": "Training for Diversity in Image Paragraph Captioning", "year": "2018", "pdf": [], "doi": ["https://aclanthology.info/papers/D18-1084/d18-1084", "http://aclweb.org/anthology/D18-1084"]}, {"id": "7a9fe5781220cca6ca600833015f200a9c03d50e", "title": "Teaching Machines to Describe Images via Natural Language Feedback", "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.00130.pdf"], "doi": []}, {"id": "08f46d6a91e513edd57a0ef15d5367b5d0545c1b", "title": "How do targets, nontargets, and scene context influence real-world object detection?", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/08f4/6d6a91e513edd57a0ef15d5367b5d0545c1b.pdf"], "doi": []}, {"id": "0612745dbd292fc0a548a16d39cd73e127faedde", "title": "Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models", "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.04870.pdf"], "doi": []}, {"id": "4b4a174f46ce03caf1ffa4addd074aaa70539f35", "title": "BlazeIt: Fast Exploratory Video Queries using Neural Networks.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.01046.pdf"], "doi": []}, {"id": "aa6f094f17d78380f927555a348ad514a505cc3b", "title": "SlowFast Networks for Video Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.03982.pdf"], "doi": []}, {"id": "885d589101ab3c09bda20ee9578f2c6d2f6cddfa", "title": "Learning to Guide Decoding for Image Captioning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00887.pdf"], "doi": []}, {"id": "1553084dcbf2235428e7dbf57b57e567c5ea4d1f", "title": "AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.10583.pdf"], "doi": []}, {"id": "d7d2a1d42f0e3182d538cf8fb4d55f3e9d7ce779", "title": "Setting an attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.08711.pdf"], "doi": []}, {"id": "e56c99e8a94d3e585166fcd66f2ab6da60932f09", "title": "Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech", "year": "2018", "pdf": ["https://arxiv.org/pdf/1710.01949.pdf"], "doi": []}, {"id": "135c71101af5d030f8cf470c454e7b655d699920", "title": "Stacked Latent Attention for Multimodal Reasoning", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Fan_Stacked_Latent_Attention_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578216", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00118", "http://doi.org/10.1109/CVPR.2018.00118"]}, {"id": "9d17e897e8344d1cf42a322359b48d1ff50b4aef", "title": "Learning to Fuse Things and Stuff", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.01192.pdf"], "doi": []}, {"id": "185e7191dc5eca046d90205527da597b6ba9ae3c", "title": "Fast Self-Attentive Multimodal Retrieval", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354311", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00207", "http://doi.org/10.1109/WACV.2018.00207"]}, {"id": "6fdc0bc13f2517061eaa1364dcf853f36e1ea5ae", "title": "DAISEE: Dataset for Affective States in E-Learning Environments", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/6fdc/0bc13f2517061eaa1364dcf853f36e1ea5ae.pdf"], "doi": []}, {"id": "947c973846f2c5f8f42225c1108810bcdb4a7015", "title": "Grounded language understanding for manipulation instructions using GAN-based classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1801.05096.pdf"], "doi": []}, {"id": "d082f64b8a0a07d105207eb822be58ffb61b353a", "title": "EMOTIC: Emotions in Context Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w41/papers/Lapedriza_EMOTIC_Emotions_in_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8015019", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.285", "http://doi.org/10.1109/CVPRW.2017.285"]}, {"id": "1e55e9c647832c969e449da28a391205a9704c60", "title": "Actor and Action Video Segmentation from a Sentence", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578722"]}, {"id": "b705ca751a947e3b761e2305b41891051525d9df", "title": "Exploring Context with Deep Structured Models for Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1603.03183.pdf"], "doi": []}, {"id": "7c7af300c4780ad01e7db4d60fbf89771672585b", "title": "Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.02518.pdf"], "doi": []}, {"id": "f4c45108cb41051010d8a5175b8da23eb246c967", "title": "Improving Image Captioning by Leveraging Knowledge Graphs", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8658870"]}, {"id": "2c28c95066b1df918f956f3cc072e29fd452dcad", "title": "Generalized Multi-View Embedding for Visual Recognition and Cross-Modal Retrieval", "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.09696.pdf"], "doi": []}, {"id": "356ac139eb92753d710c1cd6bbb84403b8cd711b", "title": "A virtual reality platform for dynamic human-scene interaction", "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2992144"]}, {"id": "d3a545bb8008a717ef95aa981295f38e6cee0d9d", "title": "Art painting detection and identification based on deep learning and image local features", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-018-6387-5"]}, {"id": "3b1860cacfd59893bb0f7e131e982e9bbeb21e87", "title": "Defect Detection from UAV Images Based on Region-Based CNNs", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8637492"]}, {"id": "bd4b5fcdf801b13d51083f3f7809366751c81c09", "title": "c-RNN: A Fine-Grained Language Model for Image Captioning", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11063-018-9836-2"]}, {"id": "3f10b9d98a276fb9e21e5742ce88bc7f48629715", "title": "Imparare a Quantificare Guardando (Learning to Quantify by Watching)", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3f10/b9d98a276fb9e21e5742ce88bc7f48629715.pdf"], "doi": []}, {"id": "bb60196acdd4b0870cd0dd7f5a7c712aa042b1d1", "title": "A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.00799.pdf"], "doi": []}, {"id": "afc4cc092f990644ff7a11dc7ab60519920cbc9d", "title": "Learning Rich Features for Image Manipulation Detection", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578214"]}, {"id": "09222c50d8ffcc74bbb7462400bd021772850bba", "title": "Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.02189.pdf"], "doi": []}, {"id": "7d39d69b23424446f0400ef603b2e3e22d0309d6", "title": "YOLO9000: Better, Faster, Stronger", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.08242.pdf"], "doi": []}, {"id": "bc6a01ea112d45bdded0bb2d34a4782e4f6f16be", "title": "Real-world Multi-object, Multi-grasp Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.00520.pdf"], "doi": []}, {"id": "bbe3d39adcb41ad2824204c0b0d299d77c2d8363", "title": "SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579079"]}, {"id": "d7443ed614548498a390aa1b83c74069aa923074", "title": "Dataless Black-Box Model Comparison", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1134/S1054661818040272"]}, {"id": "b20dc4906fc021aaf8353df98f8828d99f951c3c", "title": "Good View Hunting: Learning Photo Composition from Dense View Pairs", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578668"]}, {"id": "f42099bcd6cd13146d96d1ed15353a4ebc1f4d9a", "title": "Single-Shot Refinement Neural Network for Object Detection", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578540"]}, {"id": "d05825a394f11a391c8815f6b0d394cdb4cfaa95", "title": "I2T2I: Learning text to image synthesis with textual data augmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06676.pdf"], "doi": []}, {"id": "7985ac55e170273dd0ffa6bd756e588bab301d57", "title": "Mind's eye: A recurrent visual representation for image caption generation", "year": "2015", "pdf": ["http://www.cs.cmu.edu/~xinleic/docs/rvr/RVR-1.pdf", "http://www.cs.cmu.edu/~xinleic/papers/cvpr15_rnn.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2A_022.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2A_022_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/2A_022_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Chen_Minds_Eye_A_2015_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298856", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7298856", "http://doi.org/10.1109/CVPR.2015.7298856"]}, {"id": "5979acf247d8af73b41da0eab6d8a7eda1036c9a", "title": "A Fully-Convolutional Framework for Semantic Segmentation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8227388", "http://doi.org/10.1109/DICTA.2017.8227388"]}, {"id": "05357b8c05b5bc020e871fc330a88910c3177e4d", "title": "Multiple Instance Detection Network with Online Instance Classifier Refinement", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099809"]}, {"id": "2ce76250731cb19ccc5ffff43e4c6abec8f5af79", "title": "Learning to Segment Affordances", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w14/Luddecke_Learning_to_Segment_ICCV_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265305", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2017.96", "http://doi.org/10.1109/ICCVW.2017.96"]}, {"id": "3468740e4a9fc72a269f4f0ca8470ccd60925f92", "title": "Robustness Analysis of Visual QA Models by Basic Questions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.04625.pdf"], "doi": []}, {"id": "9c11b1552748c697bbfd33c157f7b7875686eb10", "title": "Application of deep learning in object detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7960069"]}, {"id": "bf2793fc09176f8bf23b3a2b3c6b32185e8a8329", "title": "Multi-level Fusion Based 3D Object Detection from Monocular Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578347"]}, {"id": "9a33c33190ce0c1bfffe2896ce162b3be05bc9e8", "title": "Using Explanations to Improve Ensembling of Visual Question Answering Systems", "year": "2017", "pdf": [], "doi": []}, {"id": "052373d7fd12145c41377f9a05513596d32e409c", "title": "Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780377"]}, {"id": "21ff1d20dd7b3e6b1ea02036c0176d200ec5626d", "title": "Loss Max-Pooling for Semantic Image Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.02966.pdf"], "doi": []}, {"id": "82451d0ae2e0154b5f9cd096af199c35319e911a", "title": "Image spam filtering using convolutional neural networks", "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s00779-018-1168-8"]}, {"id": "5fe7add7bb041eb52c9983fbdd792bfad1af9992", "title": "ELASTIC: Improving CNNs with Instance Specific Scaling Policies", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05262.pdf"], "doi": []}, {"id": "c2021d9652bf3ec3921bf9c13a06e1ea51588d54", "title": "Multimodal Image Captioning for Marketing Analysis", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8396991"]}, {"id": "c88c233c50f49b4b85a8702d5ee384d96fca8c23", "title": "Object-Proposal Evaluation Protocol is \u2018Gameable\u2019", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780466"]}, {"id": "bd37ff771acd72ebdf4024043cb62fcacdd3a82b", "title": "Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval", "year": "2019", "pdf": ["https://arxiv.org/pdf/1804.11013.pdf"], "doi": []}, {"id": "a9b219bd6ad71394ad21929fb5c50387698f340d", "title": "Geometry-Aware Traffic Flow Analysis by Detection and Tracking", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575394"]}, {"id": "e8b2a98f87b7b2593b4a046464c1ec63bfd13b51", "title": "CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.05413.pdf"], "doi": []}, {"id": "79a05184a6689800fee40bbb95554ffeffafeee2", "title": "Deep Image Harmonization", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099782"]}, {"id": "4d86a4c74201c0d5df9a4b259a70f2221a5cb0cb", "title": "Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099901"]}, {"id": "8067d5d3fc80abb010b239bbe012b50bae8e6611", "title": "On the Robustness of Semantic Segmentation Models to Adversarial Attacks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09856.pdf"], "doi": []}, {"id": "87fe38a79ee12531bb618d4006a476b3a5256f3e", "title": "Relative Saliency and Ranking: Models, Metrics, Data, and Benchmarks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02426.pdf"], "doi": []}, {"id": "04a5b47caca62d9351219726e92c08e60f74d652", "title": "A Novel Co-design Peta-scale Heterogeneous Cluster for Deep Learning Training.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02326.pdf"], "doi": []}, {"id": "fc09e358a130e88dead33bf6bb2cbc0e94c88291", "title": "Single-Shot Object Detection with Enriched Semantics", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578707"]}, {"id": "ca673e6c11000459e3ac27dc4ab5f29177d04fea", "title": "A detection method for low-pixel ratio object", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-018-6653-6"]}, {"id": "e4a5ff03ac258f1bcc9c214c30497610b3d5faa2", "title": "DropBlock: A regularization method for convolutional networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12890.pdf"], "doi": []}, {"id": "d7cb7ca97a665f23165b3c5420e848563cdf1f15", "title": "Pooling Pyramid Network for Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.03284.pdf"], "doi": []}, {"id": "38b2e523828a1f23ad5ad4306a0f9fedca167c90", "title": "Satellite Imagery Multiscale Rapid Detection with Windowed Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.09978.pdf"], "doi": []}, {"id": "1b7a7d291235e4b6e5f97722124070feb26f3cc1", "title": "Learning Two-Branch Neural Networks for Image-Text Matching Tasks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.03470.pdf"], "doi": []}, {"id": "c27c2fe9642fb82a3dfc314ce6003fe7a88eb1ec", "title": "Interpretable R-CNN", "year": "2017", "pdf": [], "doi": []}]}
\ No newline at end of file
+{"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "citations": [{"id": "08f6b52317b34b60aa65f38b83e3d72deffa0473", "title": "Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/bae0/9864ea2c05bccf275cf824580ce212111e42.pdf"], "doi": []}, {"id": "ce9799830a24412f4bd9ad30a9d6e2a50215f8f8", "title": "Beef Cattle Instance Segmentation Using Fully Convolutional Neural Network", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.01972.pdf"], "doi": []}, {"id": "369c4a308ec9e56746f7cc1b164208b917e31a22", "title": "Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/369c/4a308ec9e56746f7cc1b164208b917e31a22.pdf"], "doi": []}, {"id": "35ebe95db7ab148e25904604d3b06a9412f6b4a4", "title": "Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/80d9/993e6abd22a58a4fedd63754a15085778367.pdf"], "doi": []}, {"id": "d4901683e2c2552fc2d62d4eb3b1f5d5fa60a5ff", "title": "ScaleNet: Scale Invariant Network for Semantic Segmentation in Urban Driving Scenes", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d490/1683e2c2552fc2d62d4eb3b1f5d5fa60a5ff.pdf"], "doi": []}, {"id": "254f7ef73629c18ff9ba13af59b2d78df3fda59d", "title": "Deep Object-Centric Representations for Generalizable Robot Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1708.04225.pdf"], "doi": []}, {"id": "0f08d62e882026ac83ebf26c0bd288c553873814", "title": "Multispecies Fruit Flower Detection Using a Refined Semantic Segmentation Network", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.10080.pdf"], "doi": []}, {"id": "89fff8387432878db240a044a98ff9c9200f3197", "title": "Learning Globally Optimized Object Detector via Policy Gradient", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Rao_Learning_Globally_Optimized_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578746", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00648", "http://doi.org/10.1109/CVPR.2018.00648"]}, {"id": "b955969e1077ca328018c9e4dcf27b87ed9f5076", "title": "Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.01887.pdf"], "doi": []}, {"id": "f56edb6f2bf4f5bc9d54284289212b8d4a437c1b", "title": "Detection and Localization of Texture-less Objects with Deep Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f56e/db6f2bf4f5bc9d54284289212b8d4a437c1b.pdf"], "doi": []}, {"id": "a345fc597b15c26f3f2823ccd5aac0d4c976279e", "title": "Adversarially Parameterized Optimization for 3D Human Pose Estimation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8374567", "http://doi.ieeecomputersociety.org/10.1109/3DV.2017.00026", "http://doi.org/10.1109/3DV.2017.00026"]}, {"id": "3d1e82b69663758a1db87fbebed6525d23090146", "title": "ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780713"]}, {"id": "7c2a6b27dd756fe851954e0c040bc87bbd39f098", "title": "Using Psychophysical Methods to Understand Mechanisms of Face Identification in a Deep Neural Network", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w39/Xu_Using_Psychophysical_Methods_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575433", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00266", "http://doi.org/10.1109/CVPRW.2018.00266"]}, {"id": "9595a267de2b0ecf7e4e2962a606c8854551e203", "title": "On the Relation between Color Image Denoising and Classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.01372.pdf"], "doi": []}, {"id": "94a76e349e43f09c863a9c77e47722c5ade3740e", "title": "WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Durand_WELDON_Weakly_Supervised_CVPR_2016_paper.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/supplemental/Durand_WELDON_Weakly_Supervised_2016_CVPR_supplemental.pdf", "http://webia.lip6.fr/~thomen/papers/Durand_CVPR_2016.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Durand_WELDON_Weakly_Supervised_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780882", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.513", "http://doi.org/10.1109/CVPR.2016.513", "https://hal.archives-ouvertes.fr/hal-01343785/document"]}, {"id": "f5f3faa71ed2b61fa3a99bde25d6e84bfbefbb0b", "title": "Automatic Fish Classification System Using Deep Learning", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8371919", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2017.00016", "http://doi.org/10.1109/ICTAI.2017.00016"]}, {"id": "3832a6d6b1f78cdadee6968d51c1c7c2922ab3cd", "title": "ISIA at the ImageCLEF 2017 Image Caption Task", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3832/a6d6b1f78cdadee6968d51c1c7c2922ab3cd.pdf"], "doi": []}, {"id": "6abdd7c4dea2d5d7ff82cd5e6e503be1589861df", "title": "Detection and Recognition of U.S. Warning Signs on Curves", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8372008", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2017.00105", "http://doi.org/10.1109/ICTAI.2017.00105"]}, {"id": "a49b309ba14ad00a3bcb7b99a45d5bcf9bbc0ab1", "title": "Guided Perturbations: Self-Corrective Behavior in Convolutional Neural Networks", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Sankaranarayanan_Guided_Perturbations_Self-Corrective_ICCV_2017_paper.pdf", "https://arxiv.org/pdf/1703.07928v1.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237647", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.385", "http://doi.org/10.1109/ICCV.2017.385"]}, {"id": "104dd4963f7f0ef03fe09d505d31966666f9281d", "title": "Salient Object Subitizing", "year": "2015", "pdf": ["https://arxiv.org/pdf/1607.07525.pdf"], "doi": []}, {"id": "041755d1c14077ce18d8553aa40a415283edc825", "title": "W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_W2F_A_Weakly-Supervised_CVPR_2018_paper.pdf", "https://ivul.kaust.edu.sa/Documents/Publications/2018/W2F%20A%20Weakly-Supervised%20to%20Fully-Supervised%20Framework.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578201", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00103", "http://doi.org/10.1109/CVPR.2018.00103"]}, {"id": "ce8c8e9fdbdd84adc096018bb0edb49b6913b946", "title": "Learning Discriminative Features for Speaker Identification and Verification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/ce8c/8e9fdbdd84adc096018bb0edb49b6913b946.pdf"], "doi": []}, {"id": "110556d073a4d930877edc597a92995f0ff9d294", "title": "Application of Faster R-CNN model on Human Running Pattern Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.05147.pdf"], "doi": []}, {"id": "549c719c4429812dff4d02753d2db11dd490b2ae", "title": "YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00824.pdf"], "doi": []}, {"id": "1295cbaf3b03de2eb8c79530289f5939d7819e5c", "title": "DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations", "year": "2017", "pdf": ["https://arxiv.org/pdf/1510.02927.pdf"], "doi": []}, {"id": "4cfd15e9d3c01028bcda22e68791a95aa54c2a7c", "title": "DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations", "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.01766.pdf"], "doi": []}, {"id": "25b9ef5c78dbf17c71e6fd94054dd55d66c39264", "title": "Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.01606.pdf"], "doi": []}, {"id": "0b2c543e0c47454c4512569175094e6cb6ae02a9", "title": "The VizWiz Grand Challenge : A Large Visual Question Answering Dataset from Blind People Anonymous CVPR submission", "year": "", "pdf": ["https://pdfs.semanticscholar.org/0b2c/543e0c47454c4512569175094e6cb6ae02a9.pdf"], "doi": []}, {"id": "efb01e07ee994fec890ad83b89c9b652349da50e", "title": "What am I searching for", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.11926.pdf"], "doi": []}, {"id": "1c9333bcf523388d75f852e0689b0e7f5a04faa4", "title": "Person Part Segmentation based on Weak Supervision", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1c93/33bcf523388d75f852e0689b0e7f5a04faa4.pdf"], "doi": []}, {"id": "325093f2c5b33d7507c10aa422e96aa5b10a33f1", "title": "In-place Activated BatchNorm for Memory-Optimized Training of DNNs", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578689"]}, {"id": "c399c0089fb134d1476fadf5f0426e0e8b70eebd", "title": "The Lov\u00e1sz Hinge: A Novel Convex Surrogate for Submodular Losses.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1512.07797.pdf"], "doi": []}, {"id": "c98e5a582e9f1b11bf5244ed16c78a7cbccf36b9", "title": "Towards Semantic SLAM: Points, Planes and Objects", "year": "2018", "pdf": [], "doi": []}, {"id": "b0d52bb1c9cff9416fe766e9cba94ceeab12d51f", "title": "Object detection using deep CNNs trained on synthetic images", "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.06782.pdf"], "doi": []}, {"id": "1d21ec277d2a72e506a9665f19ec5478dbedc20f", "title": "A Semi-Automatic Annotation Technology for Traffic Scene Image Labeling Based on Deep Learning Preprocessing", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8005815", "http://doi.ieeecomputersociety.org/10.1109/CSE-EUC.2017.63", "http://doi.org/10.1109/CSE-EUC.2017.63"]}, {"id": "619701bb7d73171d6311c9e14b8ac5919692d03e", "title": "Semantic Edge Detection with Diverse Deep Supervision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.02864.pdf"], "doi": []}, {"id": "68f6b329044b01cce1660e953875ece2c3778c68", "title": "Intelligent Surveillance as an Edge Network Service: from Harr-Cascade, SVM to a Lightweight CNN", "year": "2018", "pdf": [], "doi": []}, {"id": "22aa426aeffb77339646cc03da8e94de22396efc", "title": "S HAKES HAKE REGULARIZATION OF 3-BRANCH RESIDUAL NETWORKS", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/22aa/426aeffb77339646cc03da8e94de22396efc.pdf"], "doi": []}, {"id": "19f73120fa314666c841ea88cb2b627aa67251b4", "title": "Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.06006.pdf"], "doi": []}, {"id": "3fea412361b2d14cb3c6723968b421c1c8cb38e8", "title": "Shake-Shake regularization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.07485.pdf"], "doi": []}, {"id": "332339c32d41cc8176d360082b4d9faa90dadffa", "title": "UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory", "year": "2017", "pdf": ["https://arxiv.org/pdf/1609.02132.pdf"], "doi": []}, {"id": "76b61ccb488ad7861e9e36054f96195877f4c9f6", "title": "Automatic image annotation: the quirks and what works", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-018-6247-3"]}, {"id": "05e9e85b5137016c93d042170e82f77bb551a108", "title": "A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation", "year": "2016", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Perazzi_A_Benchmark_Dataset_CVPR_2016_paper.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_poster_cvpr_2016.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_supplementary.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780454", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.85", "http://doi.org/10.1109/CVPR.2016.85"]}, {"id": "8899094797e82c5c185a0893896320ef77f60e64", "title": "Non-local Neural Networks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578911"]}, {"id": "12660f0defc6580e566c0fa2ac909971d6c6883b", "title": "The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780721", "http://doi.org/10.1109/CVPR.2016.352", "https://www.wikidata.org/entity/Q57840870"]}, {"id": "bf881e53510b230879aa0d3b02576043b8f881e7", "title": "Automated Image Captioning Using Nearest-Neighbors Approach Driven by Top-Object Detections", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/bf88/1e53510b230879aa0d3b02576043b8f881e7.pdf"], "doi": []}, {"id": "10beef48f3a9b2c4a6c863edefe2cac8bf09b50c", "title": "Fine-Level Semantic Labeling of Large-Scale 3D Model by Active Learning", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8491004", "http://doi.ieeecomputersociety.org/10.1109/3DV.2018.00066", "http://doi.org/10.1109/3DV.2018.00066"]}, {"id": "761de31c575bf30162b6e0d92a1800eb406e96b5", "title": "A Flexible Convolutional Solver with Application to Photorealistic Style Transfer", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.05285.pdf"], "doi": []}, {"id": "96d1bf51b3aa118696ce18dc45924e5ca8b9d885", "title": "Insulator Detection in Aerial Images for Transmission Line Inspection Using Single Shot Multibox Detector", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8603728"]}, {"id": "10c4b2489d7e1ee43a1d19724d3c1e9c33ca3f29", "title": "A Question-Answering framework for plots using Deep learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.04655.pdf"], "doi": []}, {"id": "dbc359e95d999bf119353f51edcb53b2beb5b3fe", "title": "Object Detection in Real-Time Systems: Going Beyond Precision", "year": "2018", "pdf": ["https://www.iiitd.edu.in/~chetan/papers/obj-det-wacv18.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354221", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00117", "http://doi.org/10.1109/WACV.2018.00117"]}, {"id": "de1505819e145b5c22a6e09002510413019f7228", "title": "DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.05675.pdf"], "doi": []}, {"id": "0b888196dda951287dddb60bd44798aab16d6fca", "title": "Learning Common Sense through Visual Abstraction", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Vedantam_Learning_Common_Sense_ICCV_2015_paper.pdf", "http://oui.csail.mit.edu/camera_readys/21.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Vedantam_Learning_Common_Sense_ICCV_2015_paper.pdf", "https://filebox.ece.vt.edu/~parikh/Publications/ICCV2015_commonsense.pdf", "https://www.cc.gatech.edu/~parikh/Publications/ICCV2015_commonsense.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410649", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.292", "http://doi.org/10.1109/ICCV.2015.292"]}, {"id": "85cace98e07e190494a5d88eba5e5b11538dc3b1", "title": "Hierarchical Semantic Mapping Using Convolutional Neural Networks for Intelligent Service Robotics", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8490234", "http://doi.org/10.1109/ACCESS.2018.2873597"]}, {"id": "2dd853b617c176810e3dda008f7cacea6473f0ae", "title": "Image captioning using deep neural architectures", "year": "2017", "pdf": ["https://arxiv.org/pdf/1801.05568.pdf"], "doi": []}, {"id": "25894be540936562953f37fbbcff69e5ac17a494", "title": "Semantic Image Retrieval via Active Grounding of Visual Situations", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.00088.pdf"], "doi": []}, {"id": "28949c94c8457e570ba65c8382c993600f8404e7", "title": "Efficient Video Object Segmentation via Network Modulation", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578778"]}, {"id": "ba60b642a558858325f50d38a345b6bb85114ce1", "title": "Imbalanced Deep Learning by Minority Class Incremental Rectification", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.10851.pdf"], "doi": []}, {"id": "a4aa145b519a9515e1162ca017d80d460002ba5a", "title": "HandyNet: A One-stop Solution to Detect, Segment, Localize & Analyze Driver Hands", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575312"]}, {"id": "442b6114ae8316c95f59acabe6de26f2b569cc02", "title": "Edit me: A Corpus and a Framework for Understanding Natural Language Image Editing", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1205/8e0de3dadc1469035ddb3c82e1b7ba722960.pdf"], "doi": []}, {"id": "729a9d35bc291cc7117b924219bef89a864ce62c", "title": "Recognizing Material Properties from Images.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.03127.pdf"], "doi": []}, {"id": "144ba4e9e64d4f9a5bb436c80c3c02b40e4092e0", "title": "Learning Video Features for Multi-label Classification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/144b/a4e9e64d4f9a5bb436c80c3c02b40e4092e0.pdf"], "doi": []}, {"id": "9c0ff1f1e2c83f089cb6b42a91869428fe9a92b2", "title": "Commonsense LocatedNear Relation Extraction", "year": "2017", "pdf": [], "doi": []}, {"id": "e5918229f44f0215d73a0b9d5eb13eb56764a2e4", "title": "Counting Vehicles with Cameras", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e591/8229f44f0215d73a0b9d5eb13eb56764a2e4.pdf"], "doi": []}, {"id": "f7cf4e0b1e371efca045e71996956be19aef0577", "title": "C L ] 3 D ec 2 01 7 Adversarial Ranking for Language Generation", "year": "2017", "pdf": [], "doi": []}, {"id": "0199150ccad6479eac9d693a7cc0406935d877a8", "title": "Towards Real-Time Accurate Object Detection in Both Images and Videos Based on Dual Refinement.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08638.pdf"], "doi": []}, {"id": "4c8dfc4720186799b2baf53c282a32ba3f312bcc", "title": "A Mask Regional Convolutional Neural Network Model for Segmenting Real Time Traffic Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8493883"]}, {"id": "b29be8ae91eff7ccf001d48adf518bae86129be3", "title": "OmniDetector: With Neural Networks to Bounding Boxes", "year": "2018", "pdf": [], "doi": []}, {"id": "2fcd5cff2b4743ea640c4af68bf4143f4a2cccb1", "title": "Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering", "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.05612.pdf"], "doi": []}, {"id": "6a1b76f1ef876061ec479ab9bc13fcd517eb4188", "title": "Large Kernel Matters \u2014 Improve Semantic Segmentation by Global Convolutional Network", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02719.pdf"], "doi": []}, {"id": "3bcca85ad84806be6d38d3882f7a6aac0ad90253", "title": "Video captioning with recurrent networks based on frame- and video-level features and visual content classification", "year": "2015", "pdf": ["https://arxiv.org/pdf/1512.02949.pdf"], "doi": []}, {"id": "39978ba7c83333475d6825d0ff897692933895fc", "title": "Conditional Random Fields as Recurrent Neural Networks", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410536"]}, {"id": "6ee2173c06c84cae6aae2912a4439ec956ecc3bb", "title": "Zero-shot Sim-to-Real Transfer with Modular Priors", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07480.pdf"], "doi": []}, {"id": "fd0769033b18038b9baf9e762f16973ee27be626", "title": "MobileNetV2: Inverted Residuals and Linear Bottlenecks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578572"]}, {"id": "b408b939c0f3be9cce0f84871a78a71d1684cd77", "title": "Identifying spatial relations in images using convolutional neural networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.04215.pdf"], "doi": []}, {"id": "8aa9d9ccbdf37fd1d9fb4f3adb778b3c2c9baa45", "title": "POL-LWIR Vehicle Detection: Convolutional Neural Networks Meet Polarised Infrared Sensors", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575327"]}, {"id": "ed7de328e2191463d42d745d8ac8f16024f95f25", "title": "Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237354"]}, {"id": "37b207d2c4a82a57f80e96353f79ecd71320a854", "title": "Person Search with Natural Language Description", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.05729.pdf"], "doi": []}, {"id": "54f688ea5de7b9156db28b2821e5f5ed0148605a", "title": "Contextual Memory Trees", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.06473.pdf"], "doi": []}, {"id": "4a88237199595feaa3f0e3289cbdd201a3ce28ff", "title": "Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08338.pdf"], "doi": []}, {"id": "3979e8ddcf95fedf7a220b7d39a72fa120d436f8", "title": "Deep Learning Applied to Image and Text Matching", "year": "2015", "pdf": ["https://arxiv.org/pdf/1601.03478.pdf"], "doi": []}, {"id": "df9a102288582d8edadeddcb8d55068a06cc471c", "title": "Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension", "year": "2017", "pdf": ["http://ai2-website.s3.amazonaws.com/publications/CVPR17_TQA.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/papers/Kembhavi_Are_You_Smarter_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100054", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.571", "http://doi.org/10.1109/CVPR.2017.571"]}, {"id": "9bddd98289ecc7a8dc5517122d21d5c6f5a9a01a", "title": "DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.10733.pdf"], "doi": []}, {"id": "d951ff5f378b2a5f878423029123ad6b3491b444", "title": "Foveal Vision for Instance Segmentation of Road Images", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c33e/a181e9cd13ad3f11f459d5d1f7b7bf114033.pdf"], "doi": []}, {"id": "9645e8b4829c04879a642d8dd6b3cdf5cf264afb", "title": "Finding Beans in Burgers: Deep Semantic-Visual Embedding with Localization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.01720.pdf"], "doi": []}, {"id": "1e2d9ea6fe9c50a5c26a629b94446250e1be4e7d", "title": "The Freiburg Groceries Dataset", "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.05799.pdf"], "doi": []}, {"id": "40c6a2b1cb312f11f8225a733545fdabd436e347", "title": "Deep Co-Training for Semi-Supervised Image Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.05984.pdf"], "doi": []}, {"id": "1f0c7b93636f879bd5ef3dd915a02dcd813a053d", "title": "Interpreting Deep Visual Representations via Network Dissection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.05611.pdf"], "doi": []}, {"id": "402056b2d10b27c1b17dbb5eb82b95fd1cfd8fa5", "title": "Deriving Privacy and Security Considerations for CORE: An Indoor IoT Adaptive Context Environment", "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3267363"]}, {"id": "5b3dc81a490b1d9e69d7be20c4e8e1de886b5ca3", "title": "Improving Object Localization with Fitness NMS and Bounded IoU Loss", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.00164.pdf"], "doi": []}, {"id": "b7c2798e136feb85847c8a9aa693d75bc3f9b08c", "title": "Classifying a specific image region using convolutional nets with an ROI mask as input", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00291.pdf"], "doi": []}, {"id": "372026896229c870f11bcecc1c81c80dad9c6761", "title": "Draw and Tell: Multimodal Descriptions Outperform Verbal- or Sketch-Only Descriptions in an Image Retrieval Task", "year": "2017", "pdf": [], "doi": ["https://aclanthology.info/papers/I17-2061/i17-2061", "http://aclweb.org/anthology/I17-2061", "https://pub.uni-bielefeld.de/download/2913598/2914382"]}, {"id": "8d384e8c45a429f5c5f6628e8ba0d73c60a51a89", "title": "Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.00666.pdf"], "doi": []}, {"id": "6f77ff9990973a6cdad6b5b6022323bff9d03965", "title": "Action Recognition in Still Images Using Word Embeddings from Natural Language Descriptions", "year": "2017", "pdf": ["http://cobweb.cs.uga.edu/~csc/papers/wacv17_1.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7912210", "http://doi.org/10.1109/WACVW.2017.17"]}, {"id": "146f6f6ed688c905fb6e346ad02332efd5464616", "title": "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention", "year": "2015", "pdf": ["https://arxiv.org/pdf/1502.03044.pdf"], "doi": []}, {"id": "e20daf69526c5da9cffb252d043fdc765f37a89e", "title": "Relating images and 3D models with convolutional neural networks. (Mise en relation d'images et de mod\u00e8les 3D avec des r\u00e9seaux de neurones convolutifs)", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/e20d/af69526c5da9cffb252d043fdc765f37a89e.pdf"], "doi": []}, {"id": "fb732b15fd5235893228ad3249cf04e1809034c9", "title": "CBVMR: Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.06761.pdf"], "doi": []}, {"id": "eaf8c104ab14600ecc5e9cce739b55280eef7ad4", "title": "Abstractive Compression of Captions with Attentive Recurrent Neural Networks", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/eaf8/c104ab14600ecc5e9cce739b55280eef7ad4.pdf"], "doi": []}, {"id": "dc4682cd15ccb7ebcbc8d2ba21b613e34a9af8ca", "title": "Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics using CNNs", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08960.pdf"], "doi": []}, {"id": "478a1ed7dc1890ca9476dcc1befe7f21c9bf9149", "title": "Learning to Learn from Noisy Labeled Data", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05214.pdf"], "doi": []}, {"id": "1e17202d6de18d5e1965edce5fee79744b717d0b", "title": "MIML-FCN+: Multi-Instance Multi-Label Learning via Fully Convolutional Networks with Privileged Information", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.08681.pdf"], "doi": []}, {"id": "542289d1acfebb9d79ea7a10c8e1516924e09973", "title": "Video Highlight Prediction Using Audience Chat Reactions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.08559.pdf"], "doi": []}, {"id": "2badc4c87a7751dd5ae1797bc4091d10d1acf442", "title": "Multimodal Retrieval with Asymmetrically Weighted Regularized Canonical Correla- Tion Analysis", "year": "", "pdf": ["https://pdfs.semanticscholar.org/2bad/c4c87a7751dd5ae1797bc4091d10d1acf442.pdf"], "doi": []}, {"id": "9b45e9a40313096abf530df3b98a1dfa1553f17b", "title": "Comprehension-Guided Referring Expressions", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099816"]}, {"id": "66837b29270f3e03df64941a081d70c687c7955c", "title": "ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12126.pdf"], "doi": []}, {"id": "7d035e6c6b5ef1267dff23845009284677c16a4d", "title": "AlphaGAN: Generative adversarial networks for natural image matting", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.10088.pdf"], "doi": []}, {"id": "655f587a59c835a7b6b5017016ea1c2123f266e6", "title": "Separating Self-Expression and Visual Content in Hashtag Supervision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09825.pdf"], "doi": []}, {"id": "3ca194773fe583661b988fbdf33f7680764438b3", "title": "Exploring Nearest Neighbor Approaches for Image Captioning", "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.04467.pdf"], "doi": []}, {"id": "f43463770d361e55fb6f6eb801a6e8530ab668cd", "title": "Corpus Construction and Semantic Analysis of Indonesian Image Description", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f434/63770d361e55fb6f6eb801a6e8530ab668cd.pdf"], "doi": []}, {"id": "46d8531797d8913b05f9124def1ef81ac30423c1", "title": "MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer", "year": "2019", "pdf": ["https://arxiv.org/pdf/1812.05233.pdf"], "doi": []}, {"id": "f5748711db00d82469ff60e05f62319f1eac90c5", "title": "Comparing Apples and Oranges: Off-Road Pedestrian Detection on the NREC Agricultural Person-Detection Dataset", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.07169.pdf"], "doi": []}, {"id": "cfc22c35ad191cf9d70f4a3655840748b0e1322c", "title": "Real-Time Dense Mapping for Self-driving Vehicles using Fisheye Cameras", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.06132.pdf"], "doi": []}, {"id": "6bfae88bea2301f2abeb6d1ed62c8b9a99b251c0", "title": "CNRS TELECOM ParisTech at ImageCLEF 2015 Scalable Concept Image Annotation Task: Concept Detection with Blind Localization Proposals", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/6bfa/e88bea2301f2abeb6d1ed62c8b9a99b251c0.pdf"], "doi": []}, {"id": "478261574ddc6cf297611000735aa9808f8f0030", "title": "ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.04405.pdf"], "doi": []}, {"id": "12d9a4233a16ea08fbb1de853b6a97b4f4952c23", "title": "Tractable Structured Prediction using the Permutohedral Lattice", "year": "2017", "pdf": ["https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-01.pdf?isAllowed=y&sequence=1", "https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-02.pdf?isAllowed=y&sequence=2"], "doi": ["https://doi.org/10.3929/ethz-a-010882665"]}, {"id": "e654320739770029ec5cb22174772c935478b237", "title": "Paraphrase Thought: Sentence Embedding Module Imitating Human Language Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.05505.pdf"], "doi": []}, {"id": "b80f43b42b5320578d4c1e214fe1a8b6b45352ae", "title": "MSR-VTT: A Large Video Description Dataset for Bridging Video and Language", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Xu_MSR-VTT_A_Large_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Xu_MSR-VTT_A_Large_CVPR_2016_paper.pdf", "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/06/cvpr16.msr-vtt.tmei_-1.pdf", "https://www.microsoft.com/en-us/research/wp-content/uploads/2016/10/cvpr16.supplementary.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780940", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.571", "http://doi.org/10.1109/CVPR.2016.571"]}, {"id": "81cb69e401b3b51e49ec378dba4bc0c8e33448e1", "title": "Applying Domain Randomization to Synthetic Data for Object Category Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.09834.pdf"], "doi": []}, {"id": "7b1dd2708e1d7bf0fdcda437de1970a9a6facc0d", "title": "Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.07174.pdf"], "doi": []}, {"id": "18087bfafbe471f346c8b739522e64fa11e48b13", "title": "Visual Madlibs: Fill in the Blank Description Generation and Question Answering", "year": "2015", "pdf": ["http://acberg.com/papers/madlibs.pdf", "http://openaccess.thecvf.com/content_iccv_2015/papers/Yu_Visual_Madlibs_Fill_ICCV_2015_paper.pdf", "http://tamaraberg.com/papers/madlibs.pdf", "http://www.cs.unc.edu/~licheng/papers/iccv15_madlibs.pdf", "http://www.cs.unc.edu/~licheng/papers/iccv15_madlibs_supp.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Yu_Visual_Madlibs_Fill_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410640", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.283", "http://doi.org/10.1109/ICCV.2015.283"]}, {"id": "ad8642e186c5c81d06934d4e6fc249b7cbca40e8", "title": "Learning Transferable Architectures for Scalable Image Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1707.07012.pdf"], "doi": []}, {"id": "04427d8371cb9e66e2cdcd2035756203398a8bf1", "title": "Learning Answer Embeddings for Visual Question Answering", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578667"]}, {"id": "189b02caa2bb9ffb303154e35f60797ec8576f84", "title": "CRRN: Multi-scale Guided Concurrent Reflection Removal Network", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578600"]}, {"id": "3b8ad1f2335fc755e5cd75ee5922b8a0d432018a", "title": "A Fast and Compact Saliency Score Regression Network Based on Fully Convolutional Network", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00615.pdf"], "doi": []}, {"id": "2a5667702b0f1ff77dde8fb3e2e10d4e05e8de9d", "title": "Scene Parsing through ADE20K Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhou_Scene_Parsing_Through_CVPR_2017_paper.pdf", "http://people.csail.mit.edu/bzhou/publication/scene-parse-camera-ready.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100027", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.544", "http://doi.org/10.1109/CVPR.2017.544"]}, {"id": "10bb4ef7a6719ea132e00f0ab5680919a4131d99", "title": "BAM: Bottleneck Attention Module", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.06514.pdf"], "doi": []}, {"id": "a6e695ddd07aad719001c0fc1129328452385949", "title": "The New Data and New Challenges in Multimedia Research", "year": "2015", "pdf": [], "doi": []}, {"id": "f795b4ff67d3ecce0b988ecfc0589cc7e54f5dfa", "title": "Grounded Human-Object Interaction Hotspots from Video", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.04558.pdf"], "doi": []}, {"id": "30f78071ac2bc965ffbf452a7b315d6dfddae30e", "title": "Lingusitic Analysis of Multi-Modal Recurrent Neural Networks", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/30f7/8071ac2bc965ffbf452a7b315d6dfddae30e.pdf"], "doi": []}, {"id": "10554295addeae86571a26de6c2ad7e274963953", "title": "Re-ranking Object Proposals for Object Detection in Automatic Driving", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05904.pdf"], "doi": []}, {"id": "af95ba2c08cf3317291dad554488dd951cd6ff80", "title": "Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04002.pdf"], "doi": []}, {"id": "c4cca330ec7289fac16d0793da98f705f6513219", "title": "Knowledge Projection for Effective Design of Thinner and Faster Deep Neural Networks", "year": "2017", "pdf": [], "doi": []}, {"id": "22a8b7ca2e6449cad31ae4f71bb3587751087e77", "title": "DeepBox: Learning Objectness with Convolutional Networks", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410642"]}, {"id": "0dcc768631d9ede8a3679e980b37204b782781b2", "title": "Stating the Obvious: Extracting Visual Common Sense Knowledge", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/55b9/251541eb09a6be4a317d4db1bc8d5dba07f7.pdf"], "doi": []}, {"id": "c1e714a9ec329629798a88ebff8657c349fec739", "title": "WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation", "year": "2017", "pdf": ["http://cedric.cnam.fr/~thomen/papers/Durand_CVPR_2017.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/papers/Durand_WILDCAT_Weakly_Supervised_CVPR_2017_paper.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/supplemental/Durand_WILDCAT_Weakly_Supervised_2017_CVPR_supplemental.pdf", "http://webia.lip6.fr/~durandt/pdfs/2017_CVPR/Durand_WILDCAT_CVPR_2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100114", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.631", "http://doi.org/10.1109/CVPR.2017.631"]}, {"id": "01959ef569f74c286956024866c1d107099199f7", "title": "VQA: Visual Question Answering", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410636"]}, {"id": "5c8ad080ccb3f5e3c999c2948029f0bd005d5635", "title": "Engaging Image Captioning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/5c8a/d080ccb3f5e3c999c2948029f0bd005d5635.pdf"], "doi": []}, {"id": "284be8be0c6bedc36dfe43229bc84345ab0aedc2", "title": "Faster Training of Mask R-CNN by Focusing on Instance Boundaries", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07069.pdf"], "doi": []}, {"id": "b6b9d29d25de42d78f09217c9cc457247d90fc70", "title": "Semantic Part Detection via Matching: Learning to Generalize to Novel Viewpoints from Limited Training Data", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11823.pdf"], "doi": []}, {"id": "2198a3d3342442d6ed6608f2e2b0687f644b67d6", "title": "Dynamic High Resolution Deformable Articulated Tracking", "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.07999.pdf"], "doi": []}, {"id": "340e55a44793226a51ad06612f340f2c520e3575", "title": "G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Wang_G2DeNet_Global_Gaussian_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100172", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.689", "http://doi.org/10.1109/CVPR.2017.689"]}, {"id": "833ada09759039b7c620b8930a50a0521d70b2c7", "title": "Attend in Groups: A Weakly-Supervised Deep Learning Framework for Learning from Web Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.09960.pdf"], "doi": []}, {"id": "fbb9cdd699baf86e9d616b259ada02449c2322ca", "title": "Active Testing: An Efficient and Robust Framework for Estimating Accuracy", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.00493.pdf"], "doi": []}, {"id": "f1d8c377093ecf64afd7f17383738e81666fe5ae", "title": "Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.10805.pdf"], "doi": []}, {"id": "858a2e0ca7ba129fda1a92959abe8770eb303bbe", "title": "Input Features Output Features Input Features Output Features Input Features Output Features Selected and", "year": "2017", "pdf": [], "doi": []}, {"id": "f5ce3c9eb539d2f4a85880db65ba3890a0fd8c6c", "title": "Zero-shot object prediction and context modeling using semantic scene knowledge", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/f5ce/3c9eb539d2f4a85880db65ba3890a0fd8c6c.pdf"], "doi": []}, {"id": "9634348d3bc7b86d0b644f6c14ab0c4294341905", "title": "Investigating Redundancy in Emoji Use: Study on a Twitter Based Corpus", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9634/348d3bc7b86d0b644f6c14ab0c4294341905.pdf"], "doi": []}, {"id": "068171535ac18a4b7b65be0748d483ce4c71a9a4", "title": "Event Specific Multimodal Pattern Mining with Image-Caption Pairs", "year": "2015", "pdf": ["https://arxiv.org/pdf/1601.00022.pdf"], "doi": []}, {"id": "346a877564351e4014441a1dc174b0369a759ba5", "title": "CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Kozerawski_CLEAR_Cumulative_LEARning_CVPR_2018_paper.pdf", "http://www-inst.cs.berkeley.edu/~ee290t/fa18/readings/Kozerawski_CLEAR_Cumulative_LEARning_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578461", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00363", "http://doi.org/10.1109/CVPR.2018.00363"]}, {"id": "2b45c35aa63180ef83e7f8e6f55405db9c688b0e", "title": "Unsupervised Domain Adaptation with Similarity Learning", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578933"]}, {"id": "a8420e7fa53b81b8069ced8d9c743c141e2fc432", "title": "Real-Time Multiple Object Tracking - A Study on the Importance of Speed", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.03572.pdf"], "doi": []}, {"id": "ea743597a5f48babef1982259566d76a9bf66bf2", "title": "Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/CameraReady/1276.pdf", "http://openaccess.thecvf.com/content_cvpr_2018/papers/Ding_Context_Contrasted_Feature_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578352", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00254", "http://doi.org/10.1109/CVPR.2018.00254"]}, {"id": "2770af2c74f9b82f2167cf5773ccc94d482ac8d4", "title": "Gossip training for deep learning", "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.09726.pdf"], "doi": []}, {"id": "ff5869f420d33511c22e60bbcff072c3cde3ebc4", "title": "Regional Interactive Image Segmentation Networks", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Liew_Regional_Interactive_Image_ICCV_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237559", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.297", "http://doi.org/10.1109/ICCV.2017.297"]}, {"id": "3aa66f2829ef440842c71a52cdaff30398a90ccb", "title": "Pointly-Supervised Action Localization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.11333.pdf"], "doi": []}, {"id": "15a148957469bc8b91bd7cc31aa1f0c6584a1571", "title": "DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575485"]}, {"id": "ccba451687f83c463deeefb69c1f4a781de2d638", "title": "Full-Network Embedding in a Multimodal Embedding Pipeline", "year": "2017", "pdf": [], "doi": []}, {"id": "0219ced7a3afcd8e7584b24809bac30304f9288e", "title": "L ] 3 1 M ay 2 01 7 Adversarial Ranking for Language Generation", "year": "2017", "pdf": [], "doi": []}, {"id": "59f4df3087c22e0e13574bb7d20e9d41e74cb9a5", "title": "Visual Re-ranking with Natural Language Understanding for Text Spotting", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12738.pdf"], "doi": []}, {"id": "3fb61e0d133d0971c853b8435fea99150e15cdbb", "title": "Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)", "year": "2018", "pdf": ["https://arxiv.org/pdf/1705.00366.pdf"], "doi": []}, {"id": "cb8f1f77a8b19d99dfe0c7b50dae3978cf646aa9", "title": "Adaptive attention fusion network for visual question answering", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8019540", "http://doi.ieeecomputersociety.org/10.1109/ICME.2017.8019540", "http://doi.org/10.1109/ICME.2017.8019540"]}, {"id": "4f6d8d4d460517297b419242a7e9ab3f9a307a72", "title": "Feature Extraction for Image Selection Using Machine Learning", "year": "2017", "pdf": [], "doi": []}, {"id": "0c36c988acc9ec239953ff1b3931799af388ef70", "title": "Face Detection Using Improved Faster RCNN", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02142.pdf"], "doi": []}, {"id": "1baa9fdfb27f561be67c52ef55b0e3587f306cff", "title": "Image Captioning with Attention", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/1baa/9fdfb27f561be67c52ef55b0e3587f306cff.pdf"], "doi": []}, {"id": "8b35c00edfa4edfd7a99d816e671023d2c000d55", "title": "AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578241"]}, {"id": "a0e03c5b647438299c79c71458e6b1776082a37b", "title": "Areas of Attention for Image Captioning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.01033.pdf"], "doi": []}, {"id": "9976b88d15f89b6c82b16564735d489a7524821d", "title": "Learning Visual N-Grams from Web Data", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.09161.pdf"], "doi": []}, {"id": "0b938c4a993e7e2fda81426924cb91c108a7830c", "title": "Which Emoji Talks Best for My Picture?", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8609639"]}, {"id": "4041cf003f797007fe53ac89fd57072f97257abd", "title": "End-to-end policy learning for active visual categorization.", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4041/cf003f797007fe53ac89fd57072f97257abd.pdf"], "doi": []}, {"id": "f741cba061655581f6fbb628613d0669c4bdecd5", "title": "Deep Cosine Metric Learning for Person Re-identification", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354191"]}, {"id": "c91e94e981084f5d9c3c1479fa90b8b091826d1d", "title": "Variational Bayesian Multiple Instance Learning with Gaussian Processes", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099576"]}, {"id": "03c820f35afdc38dd05e4c663d2877e2602bcde0", "title": "Semantically Guided Visual Question Answering", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354309", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00205", "http://doi.org/10.1109/WACV.2018.00205"]}, {"id": "23a0cfaceb35413bd6caad437e37d566fcfdcc64", "title": "MindCamera: Interactive Sketch-Based Image Retrieval and Synthesis", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8267031"]}, {"id": "9d5a5517650d5f9a7d9818bcc1eb59ba65d316e1", "title": "Conditional Generative Adversarial Network for Structured Domain Adaptation", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Hong_Conditional_Generative_Adversarial_CVPR_2018_paper.pdf", "https://weixianghong.github.io/publications/papers/CVPR_18.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578243", "http://doi.org/10.1109/cvpr.2018.00145"]}, {"id": "f87aa7d7b746e24e3b08fd3375331068ecd13311", "title": "Mask-SLAM: Robust Feature-Based Monocular SLAM by Masking Using Semantic Segmentation", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575524"]}, {"id": "3bb0ab7ebe1ffb83aa9775ffe2602407c9d6329d", "title": "Active Decision Boundary Annotation with Deep Generative Models", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237827"]}, {"id": "93adca9ce6f4a0fab9ea027c90b4df828cfa10d7", "title": "Learning Actionable Representations from Visual Observations", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593951"]}, {"id": "6962505b78d0cec04b992a059cc58870c361c971", "title": "Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1811.00218.pdf"], "doi": []}, {"id": "747e9b36c5a1b0b8a9572da0ab416ddd1e1d2d33", "title": "Augmentation for Visual Question Answering", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/747e/9b36c5a1b0b8a9572da0ab416ddd1e1d2d33.pdf"], "doi": []}, {"id": "85473d7bd0b73488f22d8443583165fdbd3d221d", "title": "Product Quantized Translation for Fast Nearest Neighbor Search", "year": "2018", "pdf": [], "doi": ["https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16953", "https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewFile/16953/16702"]}, {"id": "86d9f836c5fc542e987601a102c2b6cdbca1d64f", "title": "Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780602"]}, {"id": "c719a941d3ab00e45d1d74e7533ed59cc0740ae2", "title": "Does Optical Character Recognition and Caption Generation Improve Emotion Detection in Microblog Posts?", "year": "2017", "pdf": ["http://www.romanklinger.de/publications/klinger2017-nldb.pdf", "http://www.romanklinger.de/talks/nldb.pdf"], "doi": ["https://doi.org/10.1007/978-3-319-59569-6_39"]}, {"id": "4f618cbf19917ce5b8703adbc14e15b0bf0d35cc", "title": "Multi-View Dynamic Facial Action Unit Detection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.07863.pdf"], "doi": []}, {"id": "1f2b28dc48c8f2c0349dce728d7b6a0681f58aea", "title": "A Dataset for Lane Instance Segmentation in Urban Environments", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.01347.pdf"], "doi": []}, {"id": "7d6132a884d2b154059c461e107c7a8c41603ef7", "title": "Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00872.pdf"], "doi": []}, {"id": "8e06f628d0566e31366cf046b4a83ac4724ea7c3", "title": "Categorizing Concepts with Basic Level for Vision-to-Language", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Categorizing_Concepts_With_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578619", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00521", "http://doi.org/10.1109/CVPR.2018.00521"]}, {"id": "72048081cfe678f700c52e1c7a56713a8e0865b6", "title": "Unsupervised Adversarial Visual Level Domain Adaptation for Learning Video Object Detectors from Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02074.pdf"], "doi": []}, {"id": "974aa04b051bd2493bf4aaa5cd410dcb8f3b264d", "title": "Red Hen Lab: Dataset and Tools for Multimodal Human Communication Research", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1007/s13218-017-0505-9"]}, {"id": "13ad6164dba75845f0f397e9314ad596e74eb946", "title": "Learning to Estimate 3D Human Pose and Shape from a Single Color Image", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578153"]}, {"id": "91e89cedd4093bfe176532530ddb960f2767aca5", "title": "Cross-Domain Self-Supervised Multi-task Feature Learning Using Synthetic Imagery", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578184"]}, {"id": "f28e2bb46e49799589787e466c3ca966a0897bf7", "title": "Textually Customized Video Summaries", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.01528.pdf"], "doi": []}, {"id": "bcb35a8eb4cea46755c7430618e4ecfa4647b360", "title": "Deep Joint Semantic-Embedding Hashing", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bcb3/5a8eb4cea46755c7430618e4ecfa4647b360.pdf"], "doi": []}, {"id": "4b59e1fbcd68d616c9e5d02a62d332b0b2c268c5", "title": "Training Recurrent Neural Network through Moment Matching for NLP Applications", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4b59/e1fbcd68d616c9e5d02a62d332b0b2c268c5.pdf"], "doi": []}, {"id": "b8ccc5341a1b0214e9d155b019962023f344c2ee", "title": "Incremental Learning of Object Detectors without Catastrophic Forgetting", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06977.pdf"], "doi": []}, {"id": "45dd2a3cd7c27f2e9509b023d702408f5ac11c9d", "title": "Stacked Cross Attention for Image-Text Matching", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.08024.pdf"], "doi": []}, {"id": "02a4e2569b8033eff87099ad402f251d02213cfe", "title": "Learning-Based Cloth Material Recovery from Video", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237732"]}, {"id": "ff23167f18723faf41265cd36ee2cf1de45a3048", "title": "Straight to Shapes: Real-Time Detection of Encoded Shapes", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099931"]}, {"id": "47b4c33621bc0e636d6c268ad6acb319e12abbee", "title": "StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1710.10916.pdf"], "doi": []}, {"id": "26d27a6de0360ed690248a9dd08e4ec0818472b0", "title": "DehazeGAN: When Image Dehazing Meets Differential Programming", "year": "2018", "pdf": ["http://www.pengxi.me/wp-content/uploads/Papers/2018-IJCAI-DehazeGAN.pdf"], "doi": ["https://doi.org/10.24963/ijcai.2018%2F172", "https://doi.org/10.24963/ijcai.2018/172"]}, {"id": "2284ba28bd3b1afaf06afb8c2a94638e350b3ecb", "title": "Boosting Object Proposals: From Pascal to COCO", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01226.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410538", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.181", "http://doi.org/10.1109/ICCV.2015.181"]}, {"id": "21d7130230162af2a4cc1b9375bfe9b37dbbd499", "title": "Origami: A 803-GOp/s/W Convolutional Network Accelerator", "year": "2017", "pdf": ["https://arxiv.org/pdf/1512.04295.pdf"], "doi": []}, {"id": "efbac99adf8628aae7f070e5b4388a295956f9d2", "title": "CondenseNet: An Efficient DenseNet Using Learned Group Convolutions", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578389"]}, {"id": "015d25f66514ce0a966300944201d45968a104ba", "title": "SIMPLE IMAGE DESCRIPTION GENERATOR VIA A LINEAR PHRASE-BASED MODEL R\u00e9mi Lebret", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/015d/25f66514ce0a966300944201d45968a104ba.pdf"], "doi": []}, {"id": "47f8a217de3df8d70c3ac7fac73696a9104b1294", "title": "Weakly-supervised image captioning based on rich contextual information", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-017-5236-2"]}, {"id": "1fefc1d288a87fe218ba25024c4b2b6ef345738e", "title": "Self-ensembling for domain adaptation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/1fef/c1d288a87fe218ba25024c4b2b6ef345738e.pdf"], "doi": []}, {"id": "688cb9fd33769b152806c04ef6fc276629a9f300", "title": "LocNet: Improving Localization Accuracy for Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1511.07763.pdf"], "doi": []}, {"id": "c96f012f4915398259e7e223810c57898b5e1a76", "title": "Fast LIDAR-based Road Detection Using Convolutional Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c96f/012f4915398259e7e223810c57898b5e1a76.pdf"], "doi": []}, {"id": "c562e95b7906066be4210d00c4f6187475e6e13a", "title": "Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.10535.pdf"], "doi": []}, {"id": "a24a0126f76ba1423ac3548ef95aa24ac4e670dd", "title": "How Would You Say It ? Eliciting Lexically Diverse Data for Supervised Semantic Parsing", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3870/0128bc3ce57a04c46458c3898eaaa1166508.pdf"], "doi": []}, {"id": "99975f84728140154a35b0763753b35bc44e1d5a", "title": "Video Description: A Survey of Methods, Datasets and Evaluation Metrics", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.00186.pdf"], "doi": []}, {"id": "a6a6cfae45e8633c01793debf43592b7d515f65d", "title": "From ImageNet to Mining: Adapting Visual Object Detection with Minimal Supervision", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/a6a6/cfae45e8633c01793debf43592b7d515f65d.pdf"], "doi": []}, {"id": "acf13c52c86a3b38642ba0c6cbcd1b771778965c", "title": "NAACL HLT 2018 Generalization in the Age of Deep Learning Proceedings of the Workshop", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e255/eb6d8e46275387f71986a26d81fd746e0147.pdf"], "doi": []}, {"id": "fd716faea00fb6ec433a62c79aced17d51de8d23", "title": "Cascaded Contextual Region-based Convolutional Neural Network for Event Detection from Time Series Signals: A Seismic Application", "year": "2017", "pdf": [], "doi": []}, {"id": "64bff565c83c6ce3fac783d8d67191af99803701", "title": "Learning to Co-Generate Object Proposals with a Deep Structured Network", "year": "2016", "pdf": ["http://infoscience.epfl.ch/record/217984/files/HayderHeSalzmannCVPR16.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780650", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.281", "http://doi.org/10.1109/CVPR.2016.281"]}, {"id": "1779b6a17ee68afafb6801477b165f19901689b2", "title": "Object Contour Detection with a Fully Convolutional Encoder-Decoder Network", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780397"]}, {"id": "5ac18d505ed6d10e8692cbb7d33f6852e6782692", "title": "The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00982.pdf"], "doi": []}, {"id": "f2b95f135b95c3df4f6ebe6015098a2e1667711d", "title": "Weakly Supervised Object Localization Using Things and Stuff Transfer", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.08000.pdf"], "doi": []}, {"id": "e2c122bea06dfa067712cdb58ce474144f93af07", "title": "Phrase-based Image Captioning with Hierarchical LSTM Model", "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.05557.pdf"], "doi": []}, {"id": "acd26d5b85e979d73101ac790bfdedf17bfe8ed1", "title": "Learning from PhotoShop Operation Videos : the PSOV Dataset", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/acd2/6d5b85e979d73101ac790bfdedf17bfe8ed1.pdf"], "doi": []}, {"id": "0e0900b88c33b671be5dd2ded9885b6526d6b429", "title": "From captions to visual concepts and back", "year": "2015", "pdf": ["https://arxiv.org/pdf/1411.4952.pdf"], "doi": []}, {"id": "3e08a3912ebe494242f6bcd772929cc65307129c", "title": "Few-Shot Image Recognition by Predicting Parameters from Activations", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578853"]}, {"id": "47a2b1ba7e4275174a017a290f2e5de7de0acb00", "title": "Semantically Coherent Co-Segmentation and Reconstruction of Dynamic Scenes", "year": "2017", "pdf": ["http://epubs.surrey.ac.uk/813877/1/cvprFinalOpenAccess.pdf", "http://openaccess.thecvf.com/content_cvpr_2017/papers/Mustafa_Semantically_Coherent_Co-Segmentation_CVPR_2017_paper.pdf", "https://arminmustafa.github.io/docs/cvpr17/ArminCVPR2017.pdf", "https://arminmustafa.github.io/docs/cvpr17/ppt.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100075", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.592", "http://doi.org/10.1109/CVPR.2017.592"]}, {"id": "6c0c368fca391b4456e64d2943d0bcbe6d8e1ecc", "title": "A Pipeline for Creative Visual Storytelling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08077.pdf"], "doi": []}, {"id": "dc7a4d5ba20ca07d29c360b26e1e72afae9a77be", "title": "The ApolloScape Open Dataset for Autonomous Driving and its Application", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06184.pdf"], "doi": []}, {"id": "9120d59f2ca86954b45d254cae1409cb0806d9c7", "title": "DenseFuse: A Fusion Approach to Infrared and Visible Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.08361.pdf"], "doi": []}, {"id": "aa74e63360c341f47a921e0043c5d58d55807fe4", "title": "Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.05672.pdf"], "doi": []}, {"id": "ecbaa92c289f4f5ff9a57b19a2725036a92311f5", "title": "Focused Evaluation for Image Description with Binary Forced-Choice Tasks", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ecba/a92c289f4f5ff9a57b19a2725036a92311f5.pdf"], "doi": []}, {"id": "b3eb61c3542e0c6bafb4c1acd05cffc0970faa85", "title": "Region-Based Image Retrieval Revisited", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.09106.pdf"], "doi": []}, {"id": "904b322a61d9be9c0b1023946320f9245533085e", "title": "Multi-Residual Networks", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/95cd/6df1b921859103f2eea702e8d3622a862a08.pdf"], "doi": []}, {"id": "62a5f2a142fe636632f6467176ab18bb86e6398e", "title": "Pixelated Semantic Colorization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.10889.pdf"], "doi": []}, {"id": "a0e286f3c6a72c857ffd03bd8ab9a9f9b98c4432", "title": "AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04452.pdf"], "doi": []}, {"id": "333be4858994e6d9364341aeb520f7800a0f6a07", "title": "Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.05424.pdf"], "doi": []}, {"id": "23ef40af4fda9c7db8fd7596d34446303c378793", "title": "Towards a Generalized Approach for Deep Neural Network Based Event Processing for the Internet of Multimedia Things", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8331844", "http://doi.org/10.1109/ACCESS.2018.2823590"]}, {"id": "b0760764dc573b519f76d5a79531d49af333c67a", "title": "Neural Style Transfer: A Review", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.04058.pdf"], "doi": []}, {"id": "5fa587381a9e4308163b3a5395985f0375c3cf7d", "title": "Deep Extreme Cut: From Extreme Points to Object Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09081.pdf"], "doi": []}, {"id": "2f005b31b41face8a8b157e2ce7f97ece5b61391", "title": "L 1 Graph Based Sparse Model for Label Denoising", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/2f00/5b31b41face8a8b157e2ce7f97ece5b61391.pdf"], "doi": []}, {"id": "ede3af38e30ca332af0c1ce3bd5144070f7fb7f3", "title": "SGN: Sequential Grouping Networks for Instance Segmentation", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Liu_SGN_Sequential_Grouping_ICCV_2017_paper.pdf", "http://www.cs.toronto.edu/~fidler/papers/sgn_iccv17.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237640", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.378", "http://doi.org/10.1109/ICCV.2017.378"]}, {"id": "284af686292a6119129b410413831f8d2363fcc6", "title": "Learning Representation for Scene Understanding: Epitomes, CRFs, and CNNs", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/284a/f686292a6119129b410413831f8d2363fcc6.pdf"], "doi": []}, {"id": "73f1a3d88defbd5481214e27da7df501d0e31fb1", "title": "Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.01703.pdf"], "doi": []}, {"id": "2eef20a11324686099ee6f9b1a7613444b0d2112", "title": "Dual-Path Convolutional Image-Text Embedding with Instance Loss", "year": "2017", "pdf": ["https://arxiv.org/pdf/1711.05535.pdf"], "doi": []}, {"id": "f9255703f0a89c9ca2e9256595a0526829ff4402", "title": "On the Importance of Visual Context for Data Augmentation in Scene Understanding", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.02492.pdf"], "doi": []}, {"id": "e8e43abbc8bee64a53af64ceca90bfb687f7bb9d", "title": "Fast Object Class Labelling via Speech", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.09461.pdf"], "doi": []}, {"id": "3f775e3be9e1a00ebf4fd281e524932e88cec0ae", "title": "Deep Contextual Recurrent Residual Networks for Scene Labeling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.03594.pdf"], "doi": []}, {"id": "c5b9a96fcb07f538be3181922e5f1a24a7936783", "title": "Autonomous drone cinematographer: Using artistic principles to create smooth, safe, occlusion-free trajectories for aerial filming", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.09563.pdf"], "doi": []}, {"id": "d5673c53b3643372dd8d35136769ecd73a6dede3", "title": "A Deep Learning Framework for Smart Street Cleaning", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7944927", "http://doi.ieeecomputersociety.org/10.1109/BigDataService.2017.49", "http://doi.org/10.1109/BigDataService.2017.49"]}, {"id": "456983805a8781d6429bed1ed66dc9f3902767af", "title": "Seeing with Humans : Gaze-Assisted Neural Image", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/4569/83805a8781d6429bed1ed66dc9f3902767af.pdf"], "doi": []}, {"id": "a759570e6ef674cd93068020c2e6bd036961f7c6", "title": "SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.08435.pdf"], "doi": []}, {"id": "e7b92fc6e2f1a13a3076a48a78e03badacb0465b", "title": "Deep Cauchy Hashing for Hamming Space Retrieval", "year": "2018", "pdf": ["http://ise.thss.tsinghua.edu.cn/~mlong/doc/deep-cauchy-hashing-cvpr18.pdf", "http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_Deep_Cauchy_Hashing_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578232", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00134", "http://doi.org/10.1109/CVPR.2018.00134"]}, {"id": "7892606127c94d0be5c9bea5b6cb539f7fe3bf39", "title": "Combining Multiple Cues for Visual Madlibs Question Answering", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11263-018-1096-0"]}, {"id": "e42b2981f4e8de54213d624d1ef12bad4fe02f0a", "title": "Through-Wall Human Pose Estimation Using Radio Signals", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578866"]}, {"id": "c896502edcdec38466e7d66f38fb53a57c8e05db", "title": "Image Companding and Inverse Halftoning using Deep Convolutional Neural Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.00116.pdf"], "doi": []}, {"id": "30a68bea6a43c239d899d7f02bb8ef9f3c5a8f47", "title": "Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild", "year": "2018", "pdf": ["https://arxiv.org/pdf/1709.01305.pdf"], "doi": []}, {"id": "fdce9cbe5c726201575b3c8a8c1af0752f1af53f", "title": "MAttNet: Modular Attention Network for Referring Expression Comprehension", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578240"]}, {"id": "91bb3680cee8cd37b80e07644f66f9cccf1b1aff", "title": "PASCAL Boundaries: A Semantic Boundary Dataset with a Deep Semantic Boundary Detector", "year": "2017", "pdf": ["http://www.cs.jhu.edu/~alanlab/Pubs17/premachandran2017pascalboundaries.pdf", "https://www.computer.org/csdl/proceedings/wacv/2017/4822/00/07926599.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7926599", "http://doi.org/10.1109/WACV.2017.16"]}, {"id": "09b2e7af73689dbdba1547e19111a6ee06767906", "title": "PoseTrack: A Benchmark for Human Pose Estimation and Tracking", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578640"]}, {"id": "38e3c26829e38c6b56f7c541e0c4445820fab0fe", "title": "BOLD5000: A public fMRI dataset of 5000 images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.01281.pdf"], "doi": []}, {"id": "57bfbd06e94c5def35c1dde901bb4f1c839dbcdf", "title": "Deep patch learning for weakly supervised object classification and discovery", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02429.pdf"], "doi": []}, {"id": "165ef2b5f86b9b2c68b652391db5ece8c5a0bc7e", "title": "Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780717"]}, {"id": "944faf7f14f1bead911aeec30cc80c861442b610", "title": "Action Tubelet Detector for Spatio-Temporal Action Localization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01861.pdf"], "doi": []}, {"id": "729a30040132909cda0eab2c6c4ba60d6d1941b5", "title": "Image-based Plant Species Identification with Deep Convolutional Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/729a/30040132909cda0eab2c6c4ba60d6d1941b5.pdf"], "doi": []}, {"id": "28af8e1a3cb3a158f8a642c8493fcfb207743d0a", "title": "Better Image Segmentation by Exploiting Dense Semantic Predictions", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.01481.pdf"], "doi": []}, {"id": "139ab79a0aae5d4346f907b7b29288d09ef373fa", "title": "A Baseline for Multi-Label Image Classification Using Ensemble Deep CNN", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08412.pdf"], "doi": []}, {"id": "24aee34d1fb3cf5b1cddc2c6ef9259506be4e9c0", "title": "Visual Context Learning with Big Data Analytics", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7836722", "http://doi.org/10.1109/ICDMW.2016.0091"]}, {"id": "9b18cc5c938062161a4b6b0c71ee7a6c550a15f7", "title": "A Scalable Optimization Mechanism for Pairwise based Discrete Hashing.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10810.pdf"], "doi": []}, {"id": "ad9b3dc6c0e54070cec79df86458ed38566da1ff", "title": "Automated Image Captioning for Rapid Prototyping and Resource Constrained Environments", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.01393.pdf"], "doi": []}, {"id": "2a74b00daa80e64cde5256bc014d1b011926b97b", "title": "Shake-Shake regularization", "year": "2017", "pdf": [], "doi": []}, {"id": "40c1aec7e0830bf9dd8a689d671024567311ae72", "title": "Interact as You Intend: Intention-Driven Human-Object Interaction Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.09796.pdf"], "doi": []}, {"id": "4d1e28368e1121872bcd4ce75bc7ba5e43bd42d0", "title": "Attend to You: Personalized Image Captioning with Context Sequence Memory Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.06485.pdf"], "doi": []}, {"id": "b6f682648418422e992e3ef78a6965773550d36b", "title": "CBMM Memo No . 061 February 8 , 2017 Full interpretation of minimal images", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/b6f6/82648418422e992e3ef78a6965773550d36b.pdf"], "doi": []}, {"id": "2595319371a06449e3f8cef251303aecbb9e731e", "title": "A Review on Object Recognition for Blind People Based on Deep Learning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2595/319371a06449e3f8cef251303aecbb9e731e.pdf"], "doi": []}, {"id": "e7df750805d6c025d0a1a74a05a83bcf8cc63dd7", "title": "Assessment of crowdsourcing and gamification loss in user-assisted object segmentation", "year": "2015", "pdf": ["http://upcommons.upc.edu/bitstream/handle/2117/81293/asknseek.pdf;jsessionid=469B72384B7C56D4A331D68A53942294?sequence=1"], "doi": ["https://doi.org/10.1007/s11042-015-2897-6"]}, {"id": "abd4152773ebb97b90163b9a6bbdf2075e825481", "title": "Procedural Text Generation from an Execution Video", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/abd4/152773ebb97b90163b9a6bbdf2075e825481.pdf"], "doi": []}, {"id": "72f8df596eb9bb3a8c8206329083c42e70fcd9fd", "title": "Will People Like Your Image?", "year": "2016", "pdf": ["https://arxiv.org/pdf/1611.05203.pdf"], "doi": []}, {"id": "9684a54d9ff94855a40a2dc3eeb1ff16b44795fe", "title": "Human, Object and Scene Centric Image Retrieval Engine to Enhance Image Management", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8261019"]}, {"id": "b3b85d0a697c9b0309965151dcc396eb70adf46e", "title": "Shallowing Deep Networks: Layer-wise Pruning based on Feature Representations.", "year": "2018", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/30296213", "http://doi.org/10.1109/TPAMI.2018.2874634"]}, {"id": "5925a25dfe107c49c636eccb8f9fd1aeef7b438c", "title": "Temporal Shift Module for Efficient Video Understanding", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08383.pdf"], "doi": []}, {"id": "821ba3eba1e36a29cc482f5378f4a0d0f6893159", "title": "Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.07926.pdf"], "doi": []}, {"id": "1ca06a9c5e80bc0d4011f0d6f6ccc1a5ee746844", "title": "Automatic Image Cropping: A Computational Complexity Study", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Chen_Automatic_Image_Cropping_CVPR_2016_paper.pdf", "http://pages.cs.wisc.edu/~liangz/12_Chen_Automatic_Image_Cropping_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780430", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.61", "http://doi.org/10.1109/CVPR.2016.61"]}, {"id": "64a336f952ec67f85fe00092847d50dd29e4cddc", "title": "Fast Screening Algorithm for Template Matching FAST SCREENING ALGORITHM FOR TEMPLATE MATCHING", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/64a3/36f952ec67f85fe00092847d50dd29e4cddc.pdf"], "doi": []}, {"id": "cd8398e82e0c0cc4276a1694fd333214ede337ea", "title": "Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02563.pdf"], "doi": []}, {"id": "8e416d760feb5f23bc1a6dab98eb1f6e75ab8907", "title": "Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1701.08251.pdf"], "doi": []}, {"id": "f7186eb3d717694d4ab1730a8d0f662e90c44d6f", "title": "A Computational Study on Word Meanings and Their Distributed Representations via Polymodal Embedding", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f718/6eb3d717694d4ab1730a8d0f662e90c44d6f.pdf"], "doi": []}, {"id": "35c5b84fa47e5b6cee201f831507f62482ccebcc", "title": "CUNI System for the WMT 17 Multimodal Traslation Task", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/35c5/b84fa47e5b6cee201f831507f62482ccebcc.pdf"], "doi": []}, {"id": "b63041d05b78a66724fbcb2803508999bf885d6b", "title": "Deep Sets", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06114.pdf"], "doi": []}, {"id": "d318f3ca49f7f2159b9fc0face08eb284d5442dc", "title": "Scene Text Detection via Holistic, Multi-Channel Prediction", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.09002.pdf"], "doi": []}, {"id": "f81f5da2a1e4eb80b465b8dffca4c9e583a8a8a6", "title": "Rapid Object Detection Systems , Utilising Deep Learning and Unmanned Aerial Systems ( Uas ) for Civil Engineering Applications", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f81f/5da2a1e4eb80b465b8dffca4c9e583a8a8a6.pdf"], "doi": []}, {"id": "45e2aa7706fcedcbb2d93304a9824fe762b8b3b0", "title": "DAC-SDC Low Power Object Detection Challenge for UAV Applications", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.00110.pdf"], "doi": []}, {"id": "8f45907fba8fce5e9d958cf66cb68b406858fbb6", "title": "Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.05477.pdf"], "doi": []}, {"id": "f672bf42dbefb6b40921c00a05f60284934e9948", "title": "LDS-Inspired Residual Networks", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f672/bf42dbefb6b40921c00a05f60284934e9948.pdf"], "doi": []}, {"id": "c0343f9cc5f16166bda83815812c4c71ab3258e3", "title": "Hierarchical LSTMs with Adaptive Attention for Visual Captioning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.11004.pdf"], "doi": []}, {"id": "e075c5ef9d7d4ef77c92008ffaa7ac12e60383c1", "title": "Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.03905.pdf"], "doi": []}, {"id": "fb6bcf5763fe7ec7366f5991400090fa503613a7", "title": "Reduce Cognitive Burden on Drivers through Contextualising Environments", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8417781", "http://doi.org/10.1109/VTCSpring.2018.8417781"]}, {"id": "a133374b9630bbe6eb2b7de8c3204aa57e75c582", "title": "A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping.", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/a133/374b9630bbe6eb2b7de8c3204aa57e75c582.pdf"], "doi": []}, {"id": "ccbd7e417158e7ae0f9f61c3b6d1e5a3317cce34", "title": "Object Proposals in Computer Vision", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/7fb4/19f28652e4d1b1ddab1a19bdc5be1c7bbb62.pdf"], "doi": []}, {"id": "aa09ade36424fd83f067f234baffde294800e705", "title": "Is a Picture Worth Ten Thousand Words in a Review Dataset?", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.07496.pdf"], "doi": []}, {"id": "30ccfd2b4b6d5b30581356ccefcf96fd77c1766a", "title": "Overview of the ImageCLEF 2014 Scalable Concept Image Annotation Task", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/a346/060e3b71a0553eaa4bc28fbc0114b1798fec.pdf"], "doi": []}, {"id": "a25c32ea0292af5eacd6e9e0ed53b9ff7e65433f", "title": "Learning to Learn from Web Data Through Deep Semantic Embeddings", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.06368.pdf"], "doi": []}, {"id": "247b14570940601f5c7a2da1db532ecf1c302288", "title": "Dual Attention Networks for Multimodal Reasoning and Matching", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.00471.pdf"], "doi": []}, {"id": "bb021f58f8822d12f5747d583a46005ade4a0b10", "title": "Breaking Microsoft \u2019 s CAPTCHA", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/bb02/1f58f8822d12f5747d583a46005ade4a0b10.pdf"], "doi": []}, {"id": "a7066c13ba21817abcf8ff955740493adf95b02c", "title": "Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.09280.pdf"], "doi": []}, {"id": "c06447df3e50ec451240205cefa0708caee8ab8c", "title": "Picture it in your mind: generating high level visual representations from textual descriptions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.07287.pdf"], "doi": []}, {"id": "4ecaa651722a98c2847377f3ae1c70294b4791ce", "title": "Few-Example Object Detection with Model Communication.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.08249.pdf"], "doi": []}, {"id": "0b4d3e59a0107f0dad22e74054bab1cf1ad9c32e", "title": "Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.07332.pdf"], "doi": []}, {"id": "28b72ad9229f38ec61f950e1d794d6af070d1800", "title": "Zero-shot Object Prediction using Semantic Scene Knowledge", "year": "2017", "pdf": ["https://arxiv.org/pdf/1604.07952.pdf"], "doi": []}, {"id": "877c5a3ad915c2bbb5595252d08163f34ce58957", "title": "LCR-Net: Localization-Classification-Regression for Human Pose", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Rogez_LCR-Net_Localization-Classification-Regression_for_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099617", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.134", "http://doi.org/10.1109/CVPR.2017.134"]}, {"id": "e8e662e45e39249756d2b0090782434a5cf1f4aa", "title": "VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Hou_VegFru_A_Domain-Specific_ICCV_2017_paper.pdf", "http://openaccess.thecvf.com/content_ICCV_2017/supplemental/Hou_VegFru_A_Domain-Specific_ICCV_2017_supplemental.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237328", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.66", "http://doi.org/10.1109/ICCV.2017.66"]}, {"id": "1db6a35c42e86d5cd64ad2a4803fd683647fab96", "title": "Tiny Transform Net for Mobile Image Stylization", "year": "2017", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3079034"]}, {"id": "8efb48fdb8616da5133efb8659cd96c53529f76a", "title": "Active Vision Dataset Benchmark", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w40/Ammirato_Active_Vision_Dataset_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575447", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00277", "http://doi.org/10.1109/CVPRW.2018.00277"]}, {"id": "71afbb37a81a44299872bee9ae888f4129962e18", "title": "RECURRENT NEURAL FEEDBACK MODEL FOR AUTOMATED IMAGE ANNOTATION", "year": "2017", "pdf": [], "doi": []}, {"id": "9d8747468f0fed8e335656d7fe9737e4dc21c798", "title": "RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.03353.pdf"], "doi": []}, {"id": "9f545b9006970f7626b7b121c5c3c66204f1ba40", "title": "Improving Pairwise Ranking for Multi-label Image Classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.03135.pdf"], "doi": []}, {"id": "2ba540ca70c7dee81e13768792aa7571952987f6", "title": "Drivable Road Detection Based on Dilated FPN with Feature Aggregation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8372075", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2017.00172", "http://doi.org/10.1109/ICTAI.2017.00172"]}, {"id": "2e8b08c8df95d2ef8c0d03820094608e9cf456ab", "title": "License Plate Detection and Recognition in Unconstrained Scenarios", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2e8b/08c8df95d2ef8c0d03820094608e9cf456ab.pdf"], "doi": []}, {"id": "8331fb280f083767fe85ba476862e519e0275233", "title": "OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.02611.pdf"], "doi": []}, {"id": "54e0b4f63e6ed966d76b6ef83488249fd09d3a43", "title": "Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099857"]}, {"id": "f11f609facfb650ed8e659236a04bc0a664cb665", "title": "An Analysis of Scale Invariance in Object Detection - SNIP", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578475"]}, {"id": "a8773da25b133d258132d646024bf5ffd5694302", "title": "A Bottom-Up Approach Based on Semantics for the Interpretation of the Main Camera Stream in Soccer Games", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575392"]}, {"id": "666e08b6921a28fed75f35dd70d322f0edc06e41", "title": "Rain Removal in Traffic Surveillance: Does it Matter?", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12574.pdf"], "doi": []}, {"id": "1ac6a33f04f6c5a8084c15c85295f987cc8e3d72", "title": "FVQA: Fact-Based Visual Question Answering", "year": "2018", "pdf": ["https://arxiv.org/pdf/1606.05433.pdf"], "doi": []}, {"id": "3ab5d67310aa3592b68e9ef55df4603507d0d486", "title": "Learning Spatial Transforms for Refining Object Segment Proposals", "year": "2017", "pdf": ["https://www.computer.org/csdl/proceedings/wacv/2017/4822/00/07926595.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7926595", "http://doi.org/10.1109/WACV.2017.12"]}, {"id": "757b27a3ceb2293b8284fc24a7084a0c3fc2ae21", "title": "Data Distillation: Towards Omni-Supervised Learning", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578531"]}, {"id": "0d4dbd59e42e615ccf6cd4f71203be97afac48fb", "title": "End-to-End Joint Semantic Segmentation of Actors and Actions in Video", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0d4d/bd59e42e615ccf6cd4f71203be97afac48fb.pdf"], "doi": []}, {"id": "81d327ec41c67728b15438bca86d10b72de1d88f", "title": "Visual Affordance and Function Understanding: A Survey", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.06775.pdf"], "doi": []}, {"id": "df5094b2e8cf7e3bde3943ca7a56eb879b8e34ab", "title": "A Concatenated Residual Convolutional Network for Image Deblurring", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/df50/94b2e8cf7e3bde3943ca7a56eb879b8e34ab.pdf"], "doi": []}, {"id": "b8298cf0056af5afa3185181ddd5f6bb03181696", "title": "Training for Diversity in Image Paragraph Captioning", "year": "2018", "pdf": [], "doi": ["https://aclanthology.info/papers/D18-1084/d18-1084", "http://aclweb.org/anthology/D18-1084"]}, {"id": "7a9fe5781220cca6ca600833015f200a9c03d50e", "title": "Teaching Machines to Describe Images via Natural Language Feedback", "year": "2017", "pdf": ["https://arxiv.org/pdf/1706.00130.pdf"], "doi": []}, {"id": "08f46d6a91e513edd57a0ef15d5367b5d0545c1b", "title": "How do targets, nontargets, and scene context influence real-world object detection?", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/08f4/6d6a91e513edd57a0ef15d5367b5d0545c1b.pdf"], "doi": []}, {"id": "0612745dbd292fc0a548a16d39cd73e127faedde", "title": "Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models", "year": "2015", "pdf": ["https://arxiv.org/pdf/1505.04870.pdf"], "doi": []}, {"id": "4b4a174f46ce03caf1ffa4addd074aaa70539f35", "title": "BlazeIt: Fast Exploratory Video Queries using Neural Networks.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.01046.pdf"], "doi": []}, {"id": "aa6f094f17d78380f927555a348ad514a505cc3b", "title": "SlowFast Networks for Video Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.03982.pdf"], "doi": []}, {"id": "885d589101ab3c09bda20ee9578f2c6d2f6cddfa", "title": "Learning to Guide Decoding for Image Captioning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00887.pdf"], "doi": []}, {"id": "1553084dcbf2235428e7dbf57b57e567c5ea4d1f", "title": "AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.10583.pdf"], "doi": []}, {"id": "d7d2a1d42f0e3182d538cf8fb4d55f3e9d7ce779", "title": "Setting an attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.08711.pdf"], "doi": []}, {"id": "e56c99e8a94d3e585166fcd66f2ab6da60932f09", "title": "Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech", "year": "2018", "pdf": ["https://arxiv.org/pdf/1710.01949.pdf"], "doi": []}, {"id": "135c71101af5d030f8cf470c454e7b655d699920", "title": "Stacked Latent Attention for Multimodal Reasoning", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Fan_Stacked_Latent_Attention_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578216", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00118", "http://doi.org/10.1109/CVPR.2018.00118"]}, {"id": "9d17e897e8344d1cf42a322359b48d1ff50b4aef", "title": "Learning to Fuse Things and Stuff", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.01192.pdf"], "doi": []}, {"id": "185e7191dc5eca046d90205527da597b6ba9ae3c", "title": "Fast Self-Attentive Multimodal Retrieval", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354311", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00207", "http://doi.org/10.1109/WACV.2018.00207"]}, {"id": "6fdc0bc13f2517061eaa1364dcf853f36e1ea5ae", "title": "DAISEE: Dataset for Affective States in E-Learning Environments", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/6fdc/0bc13f2517061eaa1364dcf853f36e1ea5ae.pdf"], "doi": []}, {"id": "947c973846f2c5f8f42225c1108810bcdb4a7015", "title": "Grounded language understanding for manipulation instructions using GAN-based classification", "year": "2017", "pdf": ["https://arxiv.org/pdf/1801.05096.pdf"], "doi": []}, {"id": "d082f64b8a0a07d105207eb822be58ffb61b353a", "title": "EMOTIC: Emotions in Context Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w41/papers/Lapedriza_EMOTIC_Emotions_in_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8015019", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.285", "http://doi.org/10.1109/CVPRW.2017.285"]}, {"id": "1e55e9c647832c969e449da28a391205a9704c60", "title": "Actor and Action Video Segmentation from a Sentence", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578722"]}, {"id": "b705ca751a947e3b761e2305b41891051525d9df", "title": "Exploring Context with Deep Structured Models for Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1603.03183.pdf"], "doi": []}, {"id": "7c7af300c4780ad01e7db4d60fbf89771672585b", "title": "Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.02518.pdf"], "doi": []}, {"id": "f4c45108cb41051010d8a5175b8da23eb246c967", "title": "Improving Image Captioning by Leveraging Knowledge Graphs", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8658870"]}, {"id": "2c28c95066b1df918f956f3cc072e29fd452dcad", "title": "Generalized Multi-View Embedding for Visual Recognition and Cross-Modal Retrieval", "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.09696.pdf"], "doi": []}, {"id": "356ac139eb92753d710c1cd6bbb84403b8cd711b", "title": "A virtual reality platform for dynamic human-scene interaction", "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2992144"]}, {"id": "d3a545bb8008a717ef95aa981295f38e6cee0d9d", "title": "Art painting detection and identification based on deep learning and image local features", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-018-6387-5"]}, {"id": "3b1860cacfd59893bb0f7e131e982e9bbeb21e87", "title": "Defect Detection from UAV Images Based on Region-Based CNNs", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8637492"]}, {"id": "bd4b5fcdf801b13d51083f3f7809366751c81c09", "title": "c-RNN: A Fine-Grained Language Model for Image Captioning", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11063-018-9836-2"]}, {"id": "3f10b9d98a276fb9e21e5742ce88bc7f48629715", "title": "Imparare a Quantificare Guardando (Learning to Quantify by Watching)", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3f10/b9d98a276fb9e21e5742ce88bc7f48629715.pdf"], "doi": []}, {"id": "bb60196acdd4b0870cd0dd7f5a7c712aa042b1d1", "title": "A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.00799.pdf"], "doi": []}, {"id": "afc4cc092f990644ff7a11dc7ab60519920cbc9d", "title": "Learning Rich Features for Image Manipulation Detection", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578214"]}, {"id": "09222c50d8ffcc74bbb7462400bd021772850bba", "title": "Incorporating Network Built-in Priors in Weakly-Supervised Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.02189.pdf"], "doi": []}, {"id": "7d39d69b23424446f0400ef603b2e3e22d0309d6", "title": "YOLO9000: Better, Faster, Stronger", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.08242.pdf"], "doi": []}, {"id": "bc6a01ea112d45bdded0bb2d34a4782e4f6f16be", "title": "Real-world Multi-object, Multi-grasp Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.00520.pdf"], "doi": []}, {"id": "bbe3d39adcb41ad2824204c0b0d299d77c2d8363", "title": "SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579079"]}, {"id": "d7443ed614548498a390aa1b83c74069aa923074", "title": "Dataless Black-Box Model Comparison", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1134/S1054661818040272"]}, {"id": "b20dc4906fc021aaf8353df98f8828d99f951c3c", "title": "Good View Hunting: Learning Photo Composition from Dense View Pairs", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578668"]}, {"id": "f42099bcd6cd13146d96d1ed15353a4ebc1f4d9a", "title": "Single-Shot Refinement Neural Network for Object Detection", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578540"]}, {"id": "d05825a394f11a391c8815f6b0d394cdb4cfaa95", "title": "I2T2I: Learning text to image synthesis with textual data augmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.06676.pdf"], "doi": []}, {"id": "7985ac55e170273dd0ffa6bd756e588bab301d57", "title": "Mind's eye: A recurrent visual representation for image caption generation", "year": "2015", "pdf": ["http://www.cs.cmu.edu/~xinleic/docs/rvr/RVR-1.pdf", "http://www.cs.cmu.edu/~xinleic/papers/cvpr15_rnn.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2A_022.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2A_022_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/2A_022_ext.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Chen_Minds_Eye_A_2015_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7298856", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7298856", "http://doi.org/10.1109/CVPR.2015.7298856"]}, {"id": "5979acf247d8af73b41da0eab6d8a7eda1036c9a", "title": "A Fully-Convolutional Framework for Semantic Segmentation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8227388", "http://doi.org/10.1109/DICTA.2017.8227388"]}, {"id": "05357b8c05b5bc020e871fc330a88910c3177e4d", "title": "Multiple Instance Detection Network with Online Instance Classifier Refinement", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099809"]}, {"id": "2ce76250731cb19ccc5ffff43e4c6abec8f5af79", "title": "Learning to Segment Affordances", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w14/Luddecke_Learning_to_Segment_ICCV_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265305", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2017.96", "http://doi.org/10.1109/ICCVW.2017.96"]}, {"id": "3468740e4a9fc72a269f4f0ca8470ccd60925f92", "title": "Robustness Analysis of Visual QA Models by Basic Questions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.04625.pdf"], "doi": []}, {"id": "9c11b1552748c697bbfd33c157f7b7875686eb10", "title": "Application of deep learning in object detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7960069"]}, {"id": "bf2793fc09176f8bf23b3a2b3c6b32185e8a8329", "title": "Multi-level Fusion Based 3D Object Detection from Monocular Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578347"]}, {"id": "9a33c33190ce0c1bfffe2896ce162b3be05bc9e8", "title": "Using Explanations to Improve Ensembling of Visual Question Answering Systems", "year": "2017", "pdf": [], "doi": []}, {"id": "052373d7fd12145c41377f9a05513596d32e409c", "title": "Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780377"]}, {"id": "21ff1d20dd7b3e6b1ea02036c0176d200ec5626d", "title": "Loss Max-Pooling for Semantic Image Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.02966.pdf"], "doi": []}, {"id": "82451d0ae2e0154b5f9cd096af199c35319e911a", "title": "Image spam filtering using convolutional neural networks", "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s00779-018-1168-8"]}, {"id": "5fe7add7bb041eb52c9983fbdd792bfad1af9992", "title": "ELASTIC: Improving CNNs with Instance Specific Scaling Policies", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.05262.pdf"], "doi": []}, {"id": "c2021d9652bf3ec3921bf9c13a06e1ea51588d54", "title": "Multimodal Image Captioning for Marketing Analysis", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8396991"]}, {"id": "c88c233c50f49b4b85a8702d5ee384d96fca8c23", "title": "Object-Proposal Evaluation Protocol is \u2018Gameable\u2019", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780466"]}, {"id": "bd37ff771acd72ebdf4024043cb62fcacdd3a82b", "title": "Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval", "year": "2019", "pdf": ["https://arxiv.org/pdf/1804.11013.pdf"], "doi": []}, {"id": "a9b219bd6ad71394ad21929fb5c50387698f340d", "title": "Geometry-Aware Traffic Flow Analysis by Detection and Tracking", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575394"]}, {"id": "e8b2a98f87b7b2593b4a046464c1ec63bfd13b51", "title": "CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.05413.pdf"], "doi": []}, {"id": "79a05184a6689800fee40bbb95554ffeffafeee2", "title": "Deep Image Harmonization", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099782"]}, {"id": "4d86a4c74201c0d5df9a4b259a70f2221a5cb0cb", "title": "Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099901"]}, {"id": "8067d5d3fc80abb010b239bbe012b50bae8e6611", "title": "On the Robustness of Semantic Segmentation Models to Adversarial Attacks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.09856.pdf"], "doi": []}, {"id": "87fe38a79ee12531bb618d4006a476b3a5256f3e", "title": "Relative Saliency and Ranking: Models, Metrics, Data, and Benchmarks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02426.pdf"], "doi": []}, {"id": "04a5b47caca62d9351219726e92c08e60f74d652", "title": "A Novel Co-design Peta-scale Heterogeneous Cluster for Deep Learning Training.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.02326.pdf"], "doi": []}, {"id": "fc09e358a130e88dead33bf6bb2cbc0e94c88291", "title": "Single-Shot Object Detection with Enriched Semantics", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578707"]}, {"id": "ca673e6c11000459e3ac27dc4ab5f29177d04fea", "title": "A detection method for low-pixel ratio object", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-018-6653-6"]}, {"id": "e4a5ff03ac258f1bcc9c214c30497610b3d5faa2", "title": "DropBlock: A regularization method for convolutional networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.12890.pdf"], "doi": []}, {"id": "d7cb7ca97a665f23165b3c5420e848563cdf1f15", "title": "Pooling Pyramid Network for Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.03284.pdf"], "doi": []}, {"id": "38b2e523828a1f23ad5ad4306a0f9fedca167c90", "title": "Satellite Imagery Multiscale Rapid Detection with Windowed Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.09978.pdf"], "doi": []}, {"id": "1b7a7d291235e4b6e5f97722124070feb26f3cc1", "title": "Learning Two-Branch Neural Networks for Image-Text Matching Tasks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.03470.pdf"], "doi": []}, {"id": "c27c2fe9642fb82a3dfc314ce6003fe7a88eb1ec", "title": "Interpretable R-CNN", "year": "2017", "pdf": [], "doi": []}]}
\ No newline at end of file
diff --git a/site/datasets/unknown/flickr_faces.json b/site/datasets/unknown/flickr_faces.json
index 4fe5e2df..26c7131a 100644
--- a/site/datasets/unknown/flickr_faces.json
+++ b/site/datasets/unknown/flickr_faces.json
@@ -1 +1 @@
-{"id": "ceb2ebef0b41e31c1a21b28c2734123900c005e2", "citations": [{"id": "36b807372d084ccf433d9e3dc73ef4718fb5cb46", "title": "A Learned Representation for Scalable Vector Graphics", "year": "2019", "pdf": ["https://arxiv.org/pdf/1904.02632.pdf"], "doi": []}, {"id": "b9e5c79339f5be61d127b46c8e25cf4dd5d0c5b5", "title": "Multiple-Identity Image Attacks Against Face-based Identity Verification", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.08507.pdf"], "doi": []}, {"id": "db50c58ff1d377948b74ca1c8b4a78881dfb832c", "title": "Learning to see stuff", "year": "2019", "pdf": [], "doi": ["https://www.sciencedirect.com/science/article/pii/S2352154619300397?dgcid=api_sd_search-api-endpoint", "https://doi.org/10.1016/j.cobeha.2019.07.004"]}, {"id": "725c650ae8db8d9a57e4a7b15a555dbe69b67054", "title": "GANSynth: Adversarial Neural Audio Synthesis", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.08710.pdf"], "doi": []}, {"id": "c72cc4ac1bead4c6f2a9233d5e4f1a6763cdc791", "title": "SO(8) Supergravity and the Magic of Machine Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.00207.pdf"], "doi": []}, {"id": "a8f3dc53e321fbb2565f5925def4365b9f68d1af", "title": "Self-Attention Generative Adversarial Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08318.pdf"], "doi": []}, {"id": "37f675bf4329cd9e0811e232e81eef2b814c703d", "title": "Generative Adversarial Networks: A Survey and Taxonomy", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.01529.pdf"], "doi": []}, {"id": "3d25b82943a49dc7ecbe2e35551bd614886deb31", "title": "Output Standard ResNet Output Invertible ResNet InputInput", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/3d25/b82943a49dc7ecbe2e35551bd614886deb31.pdf"], "doi": []}, {"id": "57ac8ee66097274a5774ac33ef41e7855811cd57", "title": "Unsupervised Image Decomposition in Vector Layers.", "year": "2019", "pdf": ["https://arxiv.org/pdf/1812.05484.pdf"], "doi": []}, {"id": "62931b3e0dce8748364e19c87ef318e22ec59c7f", "title": "Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?", "year": "2019", "pdf": ["https://arxiv.org/pdf/1904.03189.pdf"], "doi": []}, {"id": "7c9c5e5e66302a9296444a233b63683c21778561", "title": "LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.07290.pdf"], "doi": []}, {"id": "33c7aef1f382f6167a950fd21e35b7c19a4ea14c", "title": "A Neuro-AI Interface: Learning DNNs from the Human Brain", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/33c7/aef1f382f6167a950fd21e35b7c19a4ea14c.pdf"], "doi": []}, {"id": "f34f14faa6f6144adb626fa8dee1286f0b734772", "title": "High-Fidelity Image Generation With Fewer Labels", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.02271.pdf"], "doi": []}, {"id": "8881f1b45ec6f0e1805627c828629cdd925bcfc6", "title": "Inspirational Adversarial Image Generation", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.11661.pdf"], "doi": []}, {"id": "bea263bafa31afadd9d6e150d9ac09251ffe56ee", "title": "Generating High-Resolution Fashion Model Images Wearing Custom Outfits", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.08847.pdf"], "doi": []}, {"id": "a7c531c4a38721516c6c4c155ee2234e0a3656a1", "title": "RAG: Facial Attribute Editing by Learning Residual Attributes", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8746217"]}, {"id": "41debc11e322ab83ca6ae2046781baad8b6361e8", "title": "A Large-Scale Study on Regularization and Normalization in GANs", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.04720.pdf"], "doi": []}, {"id": "4c94ee7df6bc2bfcac76703be4f059a79010f7e5", "title": "Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.06162.pdf"], "doi": []}, {"id": "ee1d22f56361547e0f357b9ecc02f6cb31416f72", "title": "Style Transfer Applied to Face Liveness Detection with User-Centered Models", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.07270.pdf"], "doi": []}, {"id": "7b35e14eb91fd99eda507552945975e6dbcf2952", "title": "Evaluating the distribution learning capabilities of GANs", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.02662.pdf"], "doi": []}, {"id": "b84e90c9d16a1cc1ba6153f351b08611d1077d30", "title": "Controlled Modification of Generated (Style)GAN Latent Vectors", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/6af8/6e7d68f18b61af4ed18deecaef9de2e0ff85.pdf"], "doi": []}, {"id": "a4d08b98dd22b87a2b3b6c4e44496f604d92950b", "title": "Measuring the Effectiveness of Voice Conversion on Speaker Identification and Automatic Speech Recognition Systems", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.12531.pdf"], "doi": []}, {"id": "21c07304466328bafe0b493f9583641f5f745c48", "title": "Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.09877.pdf"], "doi": []}, {"id": "e953ebb0d4637044c90436de5b973d64b3f45dcc", "title": "A Survey of Image Information Hiding Algorithms Based on Deep Learning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e953/ebb0d4637044c90436de5b973d64b3f45dcc.pdf"], "doi": []}, {"id": "eab5eaba0034a538394753edfa462a407102d1de", "title": "Texture Fields: Learning Texture Representations in Function Space", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.07259.pdf"], "doi": []}, {"id": "345e908980cf79f310fd3c7f21069bf64e1744af", "title": "Inspirational adversarial image generation Exploring the latent space of GANs", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/345e/908980cf79f310fd3c7f21069bf64e1744af.pdf"], "doi": []}, {"id": "36f7cfd15ec92239e0cdd3a034702c29010d972c", "title": "Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.10515.pdf"], "doi": []}, {"id": "ca42e4d7021d4e563bbeae7db35c1ce09fe38bfa", "title": "Classification Accuracy Score for Conditional Generative Models", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.10887.pdf"], "doi": []}, {"id": "24262bd12149b0b8322e0691fa30ec1a4c06b9a8", "title": "Efficient Video Generation on Complex Datasets", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.06571.pdf"], "doi": []}, {"id": "fd4e3d6cd3c9078c078178f885ae76db958340be", "title": "Synthetic Image Translation for Football Players Pose Estimation", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/58af/d93965e613bdc6e98136cccd81774af2a21c.pdf"], "doi": []}, {"id": "fe6b20332d37c50722aee0c6133df6c70826d27f", "title": "Spatially Controllable Image Synthesis with Internal Representation Collaging.", "year": "2019", "pdf": ["https://arxiv.org/pdf/1811.10153.pdf"], "doi": []}, {"id": "806bb0d6688ce0d93fbe34112922060506acbf6c", "title": "Invertible Residual Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00995.pdf"], "doi": []}, {"id": "79fe166e4f6f659dbb440d73e0f07ad11265f48d", "title": "Deep learning advancements: closing the gap", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8757133"]}, {"id": "39ce89817e1909d33a107a9dcd4af6cb3b884842", "title": "Class-Distinct and Class-Mutual Image Generation with GANs", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11163.pdf"], "doi": []}, {"id": "1e4ce741c9b5dd993826c34b492ffe9b250ea9fb", "title": "Attentive Normalization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.01259.pdf"], "doi": []}, {"id": "2bc5c29a3b7784113c63c91ed758c44a8c06ec0e", "title": "TileGAN: synthesis of large-scale non-homogeneous textures", "year": "2019", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3322993"]}, {"id": "fcdcde3f796fc2c7d6bdeeb4f6b2281ec18be614", "title": "Hierarchical Autoregressive Image Models with Auxiliary Decoders", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.04933.pdf"], "doi": []}, {"id": "74ee4fc4cbbd74553c80d8b378b0e809a372b184", "title": "A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.11478.pdf"], "doi": []}, {"id": "dbf513d27e20f41f095cacb6b8ef7bc136ce7cd1", "title": "A Neural Virtual Anchor Synthesizer based on Seq2Seq and GAN Models", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.07262.pdf"], "doi": []}, {"id": "27c6155fe17144cb28e727ca33ce57479e919db7", "title": "Chinese flower-bird character generation based on pencil drawings or brush drawings", "year": "2019", "pdf": [], "doi": ["https://doi.org/10.1117/1.JEI.28.3.033029"]}, {"id": "3ffbca69a2bdd21e2585f096902bdd79c8a2630f", "title": "Collaborative GAN Sampling", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.00813.pdf"], "doi": []}, {"id": "59f5e8fcf7ca84c8c9eb29e0f627e972e69bf061", "title": "Collaborative Sampling in Generative Adversarial Networks.", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.00813.pdf"], "doi": []}, {"id": "21371ba463bb1dcab7c92b1780b808ea440f1774", "title": "Adversarial Attack Type I: Cheat Classifiers by Significant Changes.", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/1648/0bf3544412ab893a750348acef19c5a76d66.pdf"], "doi": []}, {"id": "cde35c87aaabbc617d38f9cfaa2721a2e166d750", "title": "Large Scale Adversarial Representation Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.02544.pdf"], "doi": []}, {"id": "8d36b4b1a1c0f538b9d4f79671ecfc8a196c5bb0", "title": "Positional Normalization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.04312.pdf"], "doi": []}, {"id": "da66d5d96f7a9430249639c9391d80add15a8611", "title": "Conditional Neural Style Transfer with Peer-Regularized Feature Transform", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.02913.pdf"], "doi": []}, {"id": "7a56ab8785970885460cc3cc9092b5cd769d2a4f", "title": "Scaling up deep neural networks: a capacity allocation perspective", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.04455.pdf"], "doi": []}, {"id": "3f4a0bb3f031cbe7b0043243116e779c1e75d493", "title": "FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.04913.pdf"], "doi": []}, {"id": "deb956b70eb93bb08eaabc18fb11aed9bd20d08f", "title": "SRM : A Style-based Recalibration Module for Convolutional Neural Networks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.10829.pdf"], "doi": []}, {"id": "fc684c97d18d8dbb27b45a669209071f6dd36988", "title": "MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.03938.pdf"], "doi": []}, {"id": "bb0ba74be5248c3ec684e164b4c2cb92f04c1c0b", "title": "A Survey on Face Data Augmentation", "year": "2019", "pdf": ["https://arxiv.org/pdf/1904.11685.pdf"], "doi": []}, {"id": "7a8d6ffbbe2b0a5e7b98d8d5d22d1f74ff60f333", "title": "DualDis: Dual-Branch Disentangling with Adversarial Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.00804.pdf"], "doi": []}, {"id": "b735afafc3c71e4cdeb3a1cf4d9517c9cd319680", "title": "VQ VQ Encoder DecoderEncoder Decoder", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/b735/afafc3c71e4cdeb3a1cf4d9517c9cd319680.pdf"], "doi": []}, {"id": "dffba9e340c0255e88a7119d5b79fae8c6287984", "title": "Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.09288.pdf"], "doi": []}, {"id": "ba492f8000f9a156c79ebf284afa2127d3c284ca", "title": "Semi-supervised Image Attribute Editing using Generative Adversarial Networks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.01841.pdf"], "doi": []}, {"id": "bc06caa65e384c8fddcaf6aec668938b80ccf638", "title": "A Generative Adversarial Network for AI-Aided Chair Design", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8695313"]}, {"id": "203895ef650c7f5ea9d6ce9645c5c61e45be7981", "title": "Malware classification using fusion of neural networks", "year": "2019", "pdf": [], "doi": ["https://doi.org/10.1117/12.2533344"]}, {"id": "6c056c17e15539b093403d1d7b8c851efe361898", "title": "The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.03776.pdf"], "doi": []}]}
\ No newline at end of file
+{"id": "ceb2ebef0b41e31c1a21b28c2734123900c005e2", "citations": [{"id": "36b807372d084ccf433d9e3dc73ef4718fb5cb46", "title": "A Learned Representation for Scalable Vector Graphics", "year": "2019", "pdf": ["https://arxiv.org/pdf/1904.02632.pdf"], "doi": []}, {"id": "db50c58ff1d377948b74ca1c8b4a78881dfb832c", "title": "Learning to see stuff", "year": "2019", "pdf": [], "doi": ["https://www.sciencedirect.com/science/article/pii/S2352154619300397?dgcid=api_sd_search-api-endpoint", "https://doi.org/10.1016/j.cobeha.2019.07.004"]}, {"id": "725c650ae8db8d9a57e4a7b15a555dbe69b67054", "title": "GANSynth: Adversarial Neural Audio Synthesis", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.08710.pdf"], "doi": []}, {"id": "c72cc4ac1bead4c6f2a9233d5e4f1a6763cdc791", "title": "SO(8) Supergravity and the Magic of Machine Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.00207.pdf"], "doi": []}, {"id": "a8f3dc53e321fbb2565f5925def4365b9f68d1af", "title": "Self-Attention Generative Adversarial Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.08318.pdf"], "doi": []}, {"id": "37f675bf4329cd9e0811e232e81eef2b814c703d", "title": "Generative Adversarial Networks: A Survey and Taxonomy", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.01529.pdf"], "doi": []}, {"id": "3d25b82943a49dc7ecbe2e35551bd614886deb31", "title": "Output Standard ResNet Output Invertible ResNet InputInput", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/3d25/b82943a49dc7ecbe2e35551bd614886deb31.pdf"], "doi": []}, {"id": "57ac8ee66097274a5774ac33ef41e7855811cd57", "title": "Unsupervised Image Decomposition in Vector Layers.", "year": "2019", "pdf": ["https://arxiv.org/pdf/1812.05484.pdf"], "doi": []}, {"id": "62931b3e0dce8748364e19c87ef318e22ec59c7f", "title": "Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?", "year": "2019", "pdf": ["https://arxiv.org/pdf/1904.03189.pdf"], "doi": []}, {"id": "7c9c5e5e66302a9296444a233b63683c21778561", "title": "LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.07290.pdf"], "doi": []}, {"id": "33c7aef1f382f6167a950fd21e35b7c19a4ea14c", "title": "A Neuro-AI Interface: Learning DNNs from the Human Brain", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/33c7/aef1f382f6167a950fd21e35b7c19a4ea14c.pdf"], "doi": []}, {"id": "f34f14faa6f6144adb626fa8dee1286f0b734772", "title": "High-Fidelity Image Generation With Fewer Labels", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.02271.pdf"], "doi": []}, {"id": "8881f1b45ec6f0e1805627c828629cdd925bcfc6", "title": "Inspirational Adversarial Image Generation", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.11661.pdf"], "doi": []}, {"id": "bea263bafa31afadd9d6e150d9ac09251ffe56ee", "title": "Generating High-Resolution Fashion Model Images Wearing Custom Outfits", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.08847.pdf"], "doi": []}, {"id": "a7c531c4a38721516c6c4c155ee2234e0a3656a1", "title": "RAG: Facial Attribute Editing by Learning Residual Attributes", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8746217"]}, {"id": "41debc11e322ab83ca6ae2046781baad8b6361e8", "title": "A Large-Scale Study on Regularization and Normalization in GANs", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.04720.pdf"], "doi": []}, {"id": "4c94ee7df6bc2bfcac76703be4f059a79010f7e5", "title": "Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.06162.pdf"], "doi": []}, {"id": "ee1d22f56361547e0f357b9ecc02f6cb31416f72", "title": "Style Transfer Applied to Face Liveness Detection with User-Centered Models", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.07270.pdf"], "doi": []}, {"id": "7b35e14eb91fd99eda507552945975e6dbcf2952", "title": "Evaluating the distribution learning capabilities of GANs", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.02662.pdf"], "doi": []}, {"id": "b84e90c9d16a1cc1ba6153f351b08611d1077d30", "title": "Controlled Modification of Generated (Style)GAN Latent Vectors", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/6af8/6e7d68f18b61af4ed18deecaef9de2e0ff85.pdf"], "doi": []}, {"id": "a4d08b98dd22b87a2b3b6c4e44496f604d92950b", "title": "Measuring the Effectiveness of Voice Conversion on Speaker Identification and Automatic Speech Recognition Systems", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.12531.pdf"], "doi": []}, {"id": "21c07304466328bafe0b493f9583641f5f745c48", "title": "Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.09877.pdf"], "doi": []}, {"id": "e953ebb0d4637044c90436de5b973d64b3f45dcc", "title": "A Survey of Image Information Hiding Algorithms Based on Deep Learning", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/e953/ebb0d4637044c90436de5b973d64b3f45dcc.pdf"], "doi": []}, {"id": "eab5eaba0034a538394753edfa462a407102d1de", "title": "Texture Fields: Learning Texture Representations in Function Space", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.07259.pdf"], "doi": []}, {"id": "345e908980cf79f310fd3c7f21069bf64e1744af", "title": "Inspirational adversarial image generation Exploring the latent space of GANs", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/345e/908980cf79f310fd3c7f21069bf64e1744af.pdf"], "doi": []}, {"id": "36f7cfd15ec92239e0cdd3a034702c29010d972c", "title": "Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.10515.pdf"], "doi": []}, {"id": "ca42e4d7021d4e563bbeae7db35c1ce09fe38bfa", "title": "Classification Accuracy Score for Conditional Generative Models", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.10887.pdf"], "doi": []}, {"id": "24262bd12149b0b8322e0691fa30ec1a4c06b9a8", "title": "Efficient Video Generation on Complex Datasets", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.06571.pdf"], "doi": []}, {"id": "fd4e3d6cd3c9078c078178f885ae76db958340be", "title": "Synthetic Image Translation for Football Players Pose Estimation", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/58af/d93965e613bdc6e98136cccd81774af2a21c.pdf"], "doi": []}, {"id": "fe6b20332d37c50722aee0c6133df6c70826d27f", "title": "Spatially Controllable Image Synthesis with Internal Representation Collaging.", "year": "2019", "pdf": ["https://arxiv.org/pdf/1811.10153.pdf"], "doi": []}, {"id": "806bb0d6688ce0d93fbe34112922060506acbf6c", "title": "Invertible Residual Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00995.pdf"], "doi": []}, {"id": "79fe166e4f6f659dbb440d73e0f07ad11265f48d", "title": "Deep learning advancements: closing the gap", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8757133"]}, {"id": "39ce89817e1909d33a107a9dcd4af6cb3b884842", "title": "Class-Distinct and Class-Mutual Image Generation with GANs", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11163.pdf"], "doi": []}, {"id": "1e4ce741c9b5dd993826c34b492ffe9b250ea9fb", "title": "Attentive Normalization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.01259.pdf"], "doi": []}, {"id": "2bc5c29a3b7784113c63c91ed758c44a8c06ec0e", "title": "TileGAN: synthesis of large-scale non-homogeneous textures", "year": "2019", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3322993"]}, {"id": "fcdcde3f796fc2c7d6bdeeb4f6b2281ec18be614", "title": "Hierarchical Autoregressive Image Models with Auxiliary Decoders", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.04933.pdf"], "doi": []}, {"id": "74ee4fc4cbbd74553c80d8b378b0e809a372b184", "title": "A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.11478.pdf"], "doi": []}, {"id": "dbf513d27e20f41f095cacb6b8ef7bc136ce7cd1", "title": "A Neural Virtual Anchor Synthesizer based on Seq2Seq and GAN Models", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.07262.pdf"], "doi": []}, {"id": "27c6155fe17144cb28e727ca33ce57479e919db7", "title": "Chinese flower-bird character generation based on pencil drawings or brush drawings", "year": "2019", "pdf": [], "doi": ["https://doi.org/10.1117/1.JEI.28.3.033029"]}, {"id": "3ffbca69a2bdd21e2585f096902bdd79c8a2630f", "title": "Collaborative GAN Sampling", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.00813.pdf"], "doi": []}, {"id": "59f5e8fcf7ca84c8c9eb29e0f627e972e69bf061", "title": "Collaborative Sampling in Generative Adversarial Networks.", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.00813.pdf"], "doi": []}, {"id": "21371ba463bb1dcab7c92b1780b808ea440f1774", "title": "Adversarial Attack Type I: Cheat Classifiers by Significant Changes.", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/1648/0bf3544412ab893a750348acef19c5a76d66.pdf"], "doi": []}, {"id": "cde35c87aaabbc617d38f9cfaa2721a2e166d750", "title": "Large Scale Adversarial Representation Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.02544.pdf"], "doi": []}, {"id": "8d36b4b1a1c0f538b9d4f79671ecfc8a196c5bb0", "title": "Positional Normalization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.04312.pdf"], "doi": []}, {"id": "da66d5d96f7a9430249639c9391d80add15a8611", "title": "Conditional Neural Style Transfer with Peer-Regularized Feature Transform", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.02913.pdf"], "doi": []}, {"id": "7a56ab8785970885460cc3cc9092b5cd769d2a4f", "title": "Scaling up deep neural networks: a capacity allocation perspective", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.04455.pdf"], "doi": []}, {"id": "3f4a0bb3f031cbe7b0043243116e779c1e75d493", "title": "FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.04913.pdf"], "doi": []}, {"id": "deb956b70eb93bb08eaabc18fb11aed9bd20d08f", "title": "SRM : A Style-based Recalibration Module for Convolutional Neural Networks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.10829.pdf"], "doi": []}, {"id": "fc684c97d18d8dbb27b45a669209071f6dd36988", "title": "MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation", "year": "2019", "pdf": ["https://arxiv.org/pdf/1902.03938.pdf"], "doi": []}, {"id": "bb0ba74be5248c3ec684e164b4c2cb92f04c1c0b", "title": "A Survey on Face Data Augmentation", "year": "2019", "pdf": ["https://arxiv.org/pdf/1904.11685.pdf"], "doi": []}, {"id": "b735afafc3c71e4cdeb3a1cf4d9517c9cd319680", "title": "VQ VQ Encoder DecoderEncoder Decoder", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/b735/afafc3c71e4cdeb3a1cf4d9517c9cd319680.pdf"], "doi": []}, {"id": "dffba9e340c0255e88a7119d5b79fae8c6287984", "title": "Hiding Faces in Plain Sight: Disrupting AI Face Synthesis with Adversarial Perturbations", "year": "2019", "pdf": ["https://arxiv.org/pdf/1906.09288.pdf"], "doi": []}, {"id": "ba492f8000f9a156c79ebf284afa2127d3c284ca", "title": "Semi-supervised Image Attribute Editing using Generative Adversarial Networks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.01841.pdf"], "doi": []}, {"id": "bc06caa65e384c8fddcaf6aec668938b80ccf638", "title": "A Generative Adversarial Network for AI-Aided Chair Design", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8695313"]}, {"id": "203895ef650c7f5ea9d6ce9645c5c61e45be7981", "title": "Malware classification using fusion of neural networks", "year": "2019", "pdf": [], "doi": ["https://doi.org/10.1117/12.2533344"]}, {"id": "6c056c17e15539b093403d1d7b8c851efe361898", "title": "The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.03776.pdf"], "doi": []}]}
\ No newline at end of file
diff --git a/site/datasets/unknown/megaface.json b/site/datasets/unknown/megaface.json
index 434b4759..28eabf1b 100644
--- a/site/datasets/unknown/megaface.json
+++ b/site/datasets/unknown/megaface.json
@@ -1 +1 @@
-{"id": "15af83373274f4b4c5976c5f384ea0a5c124b287", "citations": [{"id": "34cd0ad0bdba5e74f06303bb58995bb54f7fcf3d", "title": "Continuously Reproducing Toolchains in Pattern Recognition and Machine Learning Experiments", "year": "2017", "pdf": [], "doi": []}, {"id": "576f4fd5f50c58c755eae73a983939bdccf8fac6", "title": "Deep Imbalanced Learning for Face Recognition and Attribute Prediction", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/576f/4fd5f50c58c755eae73a983939bdccf8fac6.pdf"], "doi": []}, {"id": "b3ce5d65848b40c8035d87c4b11236f34adfae8a", "title": "Distributed Mining of Outliers from Large Multi-Dimensional Databases", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b3ce/5d65848b40c8035d87c4b11236f34adfae8a.pdf"], "doi": []}, {"id": "da57bcc1a6c3b12eece51eded72035d21af10584", "title": "VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.05653.pdf"], "doi": []}, {"id": "d98476b475679db68431654be5eaadaa86aee9ff", "title": "IARPA Janus Benchmark - C: Face Dataset and Protocol", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8411217"]}, {"id": "d0df01d1a183d23be8fd638fdb2142280c737e80", "title": "Apprentissage automatique pour la d\u00e9tection d'anomalies dans les donn\u00e9es ouvertes : application \u00e0 la cartographie. (Satellite images analysis for anomaly detection in open geographical data)", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d0df/01d1a183d23be8fd638fdb2142280c737e80.pdf"], "doi": []}, {"id": "c4051f726e529543bd2f2b3039f61c1ba0889301", "title": "Eye In-painting with Exemplar Generative Adversarial Networks", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578922"]}, {"id": "8b79bfc93c7001dd7bb1eea7715af47d76202827", "title": "Decorrelated Adversarial Learning for Age-Invariant Face Recognition", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/8b79/bfc93c7001dd7bb1eea7715af47d76202827.pdf"], "doi": []}, {"id": "461ceb053b119b85022cc591132de6bcdc8bdc1f", "title": "Dictionary Representation of Deep Features for Occlusion-Robust Face Recognition", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8651449"]}, {"id": "9dc915697768dd1f7c7b97e2c25c90b02241958b", "title": "CosFace: Large Margin Cosine Loss for Deep Face Recognition", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578650"]}, {"id": "5d684c197c06139319bf575e2498fe040d9ea32f", "title": "Laplace Landmark Localization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.11633.pdf"], "doi": []}, {"id": "1ffe20eb32dbc4fa85ac7844178937bba97f4bf0", "title": "Face Clustering: Representation and Pairwise Constraints", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.05067.pdf"], "doi": []}, {"id": "8de1c724a42d204c0050fe4c4b4e81a675d7f57c", "title": "Deep Face Recognition: A Survey", "year": "2018", "pdf": ["https://talhassner.github.io/home/projects/DeepFaceSurvey/Masietal2018deepfacesurvey.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8614364", "http://doi.org/10.1109/SIBGRAPI.2018.00067"]}, {"id": "ad8e7b7349e15c4592aa2c18ce79f77671084781", "title": "Fast Face Image Synthesis With Minimal Training", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8658792"]}, {"id": "380dd0ddd5d69adc52defc095570d1c22952f5cc", "title": "Improving Smiling Detection with Race and Gender Diversity", "year": "2017", "pdf": [], "doi": []}, {"id": "65984ea40c3b17bb8965c215b61972cd660f61a7", "title": "Doppelganger Mining for Face Representation Learning", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Smirnov_Doppelganger_Mining_for_ICCV_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265436", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2017.226", "http://doi.org/10.1109/ICCVW.2017.226"]}, {"id": "4739b47af26137ec52bbfb582e6f37e9e9f5aba0", "title": "Hard Example Mining with Auxiliary Embeddings", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w1/Smirnov_Hard_Example_Mining_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575283", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00013", "http://doi.org/10.1109/CVPRW.2018.00013"]}, {"id": "9d14cdbf0af4af7a7bc0a62084fe9c0ab43d6502", "title": "Towards a Fast and Accurate Face Recognition System from Deep Representations", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/9d14/cdbf0af4af7a7bc0a62084fe9c0ab43d6502.pdf"], "doi": []}, {"id": "750486b2278ba542987655eede1b4da8c10f7f2e", "title": "Softmax Dissection: Towards Understanding Intra- and Inter-clas Objective for Embedding Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.01281.pdf"], "doi": []}, {"id": "5a564d108b43c6ff006a86d2fc981cd36c6c54dd", "title": "Deep Learning for Understanding Faces", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5a56/4d108b43c6ff006a86d2fc981cd36c6c54dd.pdf"], "doi": []}, {"id": "d45fd2b4583dd218091003ab65a4d77ccec6da47", "title": "Large-Scale Bisample Learning on ID Versus Spot Face Recognition", "year": "2018", "pdf": ["http://export.arxiv.org/pdf/1806.03018", "https://arxiv.org/pdf/1806.03018.pdf"], "doi": ["https://doi.org/10.1007/s11263-019-01162-8"]}, {"id": "39b615c73810e13998df3df9d5e73aebd3e67dab", "title": "A Compact Embedding for Facial Expression Similarity", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11283.pdf"], "doi": []}, {"id": "56f1202f88cefd4aad6f97914eeae61c1f5531b7", "title": "UHDB31: A Dataset for Better Understanding Face Recognition Across Pose and Illumination Variation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265511"]}, {"id": "8ed7d8a07ac21328d3c03ff3880e6f6f939257f6", "title": "Adversarial Learning for Age-Invariant Face Recognition", "year": "", "pdf": ["https://pdfs.semanticscholar.org/8ed7/d8a07ac21328d3c03ff3880e6f6f939257f6.pdf"], "doi": []}, {"id": "4e1a65f3c3d9cfeecab898affbe0b47a9b6c9157", "title": "DIY Human Action Dataset Generation", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575353"]}, {"id": "c607572fd2594ca83f732c9790fd590da9e69eb1", "title": "Comparative Evaluation of Deep Architectures for Face Recognition in Unconstrained Environment ( FRUE )", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c607/572fd2594ca83f732c9790fd590da9e69eb1.pdf"], "doi": []}, {"id": "18858cc936947fc96b5c06bbe3c6c2faa5614540", "title": "Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification", "year": "2018", "pdf": ["http://proceedings.mlr.press/v81/buolamwini18a/buolamwini18a-supp.pdf", "https://dam-prod.media.mit.edu/x/2018/02/06/Gender%20Shades%20Intersectional%20Accuracy%20Disparities.pdf"], "doi": ["http://proceedings.mlr.press/v81/buolamwini18a.html"]}, {"id": "4a6d7d222838c6bc59a32190c2f07d278f15539f", "title": "Towards optimal local binary patterns in texture and face description", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/4a6d/7d222838c6bc59a32190c2f07d278f15539f.pdf"], "doi": []}, {"id": "ddcf0cf00a50cff93c2cbdc6823aad7ab1d3634f", "title": "ID-Softmax: A Softmax-like Loss for ID Face Recognition", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/5244/4f9562ef17557de24d22716491b11bbd2802.pdf"], "doi": []}, {"id": "b612bbd751d94996a02b85829e0b2ac0511350ff", "title": "Learning Representations for Utility and Privacy : An Information-Theoretic Based Approach", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b612/bbd751d94996a02b85829e0b2ac0511350ff.pdf"], "doi": []}, {"id": "eb4be3c7711935c936cb6755e0873cb1492af71e", "title": "A Deep Face Identification Network Enhanced by Facial Attributes Prediction", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575246"]}, {"id": "3d789ce25828a9b55947927063aa87f643c2a41c", "title": "Face In Video Evaluation (FIVE) Face Recognition of Non-Cooperative Subjects", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3d78/9ce25828a9b55947927063aa87f643c2a41c.pdf"], "doi": []}, {"id": "b090bf0d5b4a780821b4f45fc216ac614493020d", "title": "A Generative Model of Worldwide Facial Appearance", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8658761"]}, {"id": "b8f22ef91a7fccbe7b04a0caf0d5d5f88e2cd230", "title": "The 2017 IARPA Face Recognition Prize Challenge (FRPC)", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/b8f2/2ef91a7fccbe7b04a0caf0d5d5f88e2cd230.pdf"], "doi": []}, {"id": "20a64c3d0d2108bc5fc7b0bbd11ad941734d5f2b", "title": "Heterogeneous Face Recognition Using Domain Specific Units", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8565895"]}, {"id": "934f69d038721540c96093cae634573b89d7d714", "title": "DeSTNet : Densely Fused Spatial Transformer Networks 1", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/934f/69d038721540c96093cae634573b89d7d714.pdf"], "doi": []}, {"id": "7d2165ee47828fac5128cd554b9be89c851463fb", "title": "Empirically Analyzing the Effect of Dataset Biases on Deep Face Recognition Systems", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575453"]}, {"id": "2e2534eb1f1af5c043a009391f0ef955aeed2044", "title": "Switchable Normalization for Learning-to-Normalize Deep Representation", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/2e25/34eb1f1af5c043a009391f0ef955aeed2044.pdf"], "doi": []}, {"id": "1e34b7505fef52b2881f4de6e78cfb90d51085a0", "title": "Trunk-Branch Ensemble Convolutional Neural Networks for Large Scale, Few-Shot Video-to-Still Face Recognition", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/1e34/b7505fef52b2881f4de6e78cfb90d51085a0.pdf"], "doi": []}, {"id": "8395cf3535a6628c3bdc9b8d0171568d551f5ff0", "title": "Entropy Non-increasing Games for the Improvement of Dataflow Programming", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.04389.pdf"], "doi": []}, {"id": "2c75658b080a9baaac20db39af86016ffa36f6f0", "title": "Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578977"]}, {"id": "97834ad2a0556fedbea0407a84ca8f520f0fc11f", "title": "Face-Specific Data Augmentation for Unconstrained Face Recognition", "year": "2019", "pdf": ["https://talhassner.github.io/home/projects/augmented_faces/Masietal_IJCV2019.pdf"], "doi": ["https://doi.org/10.1007/s11263-019-01178-0"]}, {"id": "a4433a97e766362c1f2ce6f013dff15a3fe9a3ac", "title": "Overcoming catastrophic forgetting with hard attention to the task", "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.01423.pdf"], "doi": []}, {"id": "64a68e1a3f7e5496ade9ee376f69d3bd15c43b70", "title": "Multi-camera object tracking via deep metric learning", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1117/12.2500776"]}, {"id": "35ddd4896d9396d5dcff3f32bd79ff7cf3e82777", "title": "ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1905.10620.pdf"], "doi": []}, {"id": "7789e2dcfa2bcd3ac55c63060509629ad77adb73", "title": "DHFML: deep heterogeneous feature metric learning for matching photograph and cartoon pairs", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s13735-018-0160-4"]}, {"id": "48499deeaa1e31ac22c901d115b8b9867f89f952", "title": "Interim Report of Final Year Project HKU-Face : A Large Scale Dataset for Deep Face Recognition", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4849/9deeaa1e31ac22c901d115b8b9867f89f952.pdf"], "doi": []}, {"id": "3c0fffd4cdbfef4ccd92d528d8b8a60ab0929827", "title": "An Empirical Study of Face Recognition under Variations", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8373845", "http://doi.ieeecomputersociety.org/10.1109/FG.2018.00052", "http://doi.org/10.1109/FG.2018.00052"]}, {"id": "568435e4a2d161c68808a35250be147202867ce4", "title": "Deep Learning For Face Recognition: A Critical Analysis", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.12739.pdf"], "doi": []}, {"id": "c6cdf39c70aabf973a56db1ea009ab275f3f6ee8", "title": "Image-set, Temporal and Spatiotemporal Representations of Videos for Recognizing, Localizing and Quantifying Actions", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c6cd/f39c70aabf973a56db1ea009ab275f3f6ee8.pdf"], "doi": []}, {"id": "3998f7d6022f67a1cf6050bccd3131911fec5a8a", "title": "Self Residual Attention Network for Deep Face Recognition", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8698884"]}, {"id": "fef0adf785aa6b91d23f0a61a32deece48a7f156", "title": "On the Capacity of Face Representation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.10433.pdf"], "doi": []}, {"id": "9ba4a5e0b7bf6e26563d294f1f3de44d95b7f682", "title": "To Frontalize or Not to Frontalize: Do We Really Need Elaborate Pre-processing to Improve Face Recognition?", "year": "2018", "pdf": ["http://docs.wixstatic.com/ugd/445e27_b7f15ceb15d34e45836f98d9eeba9a78.pdf", "https://arxiv.org/pdf/1610.04823v1.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354113", "http://arxiv.org/abs/1610.04823", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00009", "http://doi.org/10.1109/WACV.2018.00009"]}, {"id": "c924137ca87e8b4e1557465405744f8b639b16fc", "title": "Seeding Deep Learning using Wireless Localization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.10242.pdf"], "doi": []}, {"id": "4da4642ac4c1fcfbecd622dad485307b8d30ed2b", "title": "Deep representation for partially occluded face verification", "year": "2018", "pdf": ["https://jivp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13640-018-0379-2"], "doi": ["https://doi.org/10.1186/s13640-018-0379-2"]}, {"id": "fb67b0625e2374d2c32e447fb682c22784c5a8b5", "title": "Wearable Technologies for Law Enforcement: Multifunctional Vest System Options", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/fb67/b0625e2374d2c32e447fb682c22784c5a8b5.pdf"], "doi": []}, {"id": "4e6ac0f8dfa5592458e100bc0bb5bac69f7912c1", "title": "Robust RGB-D Face Recognition Using Attribute-Aware Loss", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/de47/c456f5e8d0d663c204afca443c6412740fee.pdf"], "doi": []}, {"id": "e3d76f1920c5bf4a60129516abb4a2d8683e48ae", "title": "I Know That Person: Generative Full Body and Face De-identification of People in Images", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w16/papers/Kalafatic_I_Know_That_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8014907", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.173", "http://doi.org/10.1109/CVPRW.2017.173"]}, {"id": "0ab7cff2ccda7269b73ff6efd9d37e1318f7db25", "title": "Facial Coding Scheme Reference 1 Craniofacial Distances", "year": "2019", "pdf": [], "doi": []}, {"id": "15af83373274f4b4c5976c5f384ea0a5c124b287", "title": "Level Playing Field for Million Scale Face Recognition", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099846"]}, {"id": "c9c56f8bb89948d15a9564b146e7bdff7b17a1c2", "title": "Modeling Grasp Motor Imagery", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/c9c5/6f8bb89948d15a9564b146e7bdff7b17a1c2.pdf"], "doi": []}, {"id": "cfb8bc66502fb5f941ecdb22aec1fdbfdb73adce", "title": "Git Loss for Deep Face Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08512.pdf"], "doi": []}, {"id": "3417d1521552330aee30e0d9a6aec481ba904b17", "title": "An Investigation of High-Throughput Biometric Systems: Results of the 2018 Department of Homeland Security Biometric Technology Rally", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8698547"]}, {"id": "559b12257d56725fbef5790e2dfdec8751919ef1", "title": "Synthesizing Normalized Faces from Facial Identity Features", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099844"]}, {"id": "4d3fbeb69ee1207d47b182dd88bdd82791f1c17d", "title": "Performance Comparison of Face Detection and Recognition Algorithms", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/4d3f/beb69ee1207d47b182dd88bdd82791f1c17d.pdf"], "doi": []}, {"id": "3f4a0bb3f031cbe7b0043243116e779c1e75d493", "title": "FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.04913.pdf"], "doi": []}, {"id": "db0880947452943a038e8d4c348107ef631d26a9", "title": "Learning from Longitudinal Face Demonstration\u2014Where Tractable Deep Modeling Meets Inverse Reinforcement Learning", "year": "2017", "pdf": ["http://arxiv.org/pdf/1711.10520", "https://arxiv.org/pdf/1711.10520.pdf", "https://export.arxiv.org/pdf/1711.10520"], "doi": ["https://doi.org/10.1007/s11263-019-01165-5"]}, {"id": "722b8cdb7d786283c6d6512729622561e3072d68", "title": "Temporal Non-volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237665"]}, {"id": "d31328b12eef33e7722b8e5505d0f9d9abe2ffd9", "title": "Deep Unsupervised Domain Adaptation for Face Recognition", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8373866", "http://doi.ieeecomputersociety.org/10.1109/FG.2018.00073", "http://doi.org/10.1109/FG.2018.00073"]}, {"id": "1d4f087217b816691254ef0d4377094ce16eea95", "title": "Adversarially Learned Representations for Information Obfuscation and Inference", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/7778/6c525fce29a84bf4cfcd5e7f901ddc04847a.pdf"], "doi": []}, {"id": "bcd883ef8faa9a81f5c14da97669df1dd2e8f1b8", "title": "Local directional relation pattern for unconstrained and robust face retrieval", "year": "2017", "pdf": ["http://arxiv.org/pdf/1709.09518", "http://arxiv-export-lb.library.cornell.edu/pdf/1709.09518", "https://arxiv.org/pdf/1709.09518.pdf"], "doi": ["https://doi.org/10.1007/s11042-019-07908-3"]}, {"id": "d2eb1079552fb736e3ba5e494543e67620832c52", "title": "DeSTNet: Densely Fused Spatial Transformer Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.04050.pdf"], "doi": []}, {"id": "04922595cee2ce50030674a7179ecd871e5df1d2", "title": "Effective indexing for face recognition", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1117/12.2238096"]}, {"id": "173657da03e3249f4e47457d360ab83b3cefbe63", "title": "HKU-Face : A Large Scale Dataset for Deep Face Recognition Final Report", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1736/57da03e3249f4e47457d360ab83b3cefbe63.pdf"], "doi": []}, {"id": "8a9ca15aebadad4b7cfa18c5af91c431d6045b86", "title": "cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06436.pdf"], "doi": []}, {"id": "a2344004f0e1409c0c9473d071a5cfd74bff0a5d", "title": "Learnable PINs: Cross-modal Embeddings for Person Identity", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.00833.pdf"], "doi": []}, {"id": "829770e9eff6ae7f9a2412b63e438e19767c564c", "title": "Computer Vision", "year": "2014", "pdf": ["http://www.cl.cam.ac.uk/teaching/0809/CompVision/CompVisNotes.pdf", "http://www.cl.cam.ac.uk/teaching/1617/CompVision/ConsolidatedSlides.pdf", "http://www.cl.cam.ac.uk/teaching/2004/CompVision/notes.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part01-intro.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part02-linear_regression.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part07-approximate_inference.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part15-latent_factor_models.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part16-beta_processes-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part17-beta_processes2-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part18-support_vector_machines.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part20-structured-output-learning-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part21-structured-output-learning2.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part01-intro.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part03-image-processing2-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part03-image-processing2.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part05-segmentation1-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part12-local-features3.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part13-categorization2-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part14-reconstruction1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-13-14/lectures/cv13-part05-structure-extraction.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-13-14/lectures/cv13-part15-local-features4.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part03-image-processing2-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part14-local-features3.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part17-reconstruction1-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part17-reconstruction1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part22-repetition.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision_2/lectures/cv2_14-part08-kalman-filter-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision_2/lectures/cv2_14-part12-multiobject-tracking3-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/summer-2012/lectures/ml12-part15-graphical_models5.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/summer-2015/lectures-1/ml15-part13-graphical_models1-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/summer-2015/lectures-1/ml15-part15-graphical_models3.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/summer-2015/lectures-1/ml15-part18-repetition.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part02-pde1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part09-nonlinear_svms.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part13-model_selection.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part20-graphical_models5.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2014/computer-vision-2/cv2_14-part08-kalman-filter-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2014/computer-vision-2/cv2_14-part12-multiobject-tracking3-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2015/machine-learning/ml15-part13-graphical_models1-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2015/machine-learning/ml15-part15-graphical_models3.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2015/machine-learning/ml15-part18-repetition.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part02-pde1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part05-linear_discriminants-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part12-randomized_trees-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part15-graphical_models1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part18-graphical_models4.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2019/computer-vision/cv19-part02-image-processing.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part01-intro.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part02-linear_regression.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part07-approximate_inference.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part15-latent_factor_models.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part18-support_vector_machines.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part21-structured-output-learning2.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part03-image-processing2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part14-local-features3.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part17-reconstruction1-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part22-repetition.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/advanced-machine-learning/ml2_15-part01-intro.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/advanced-machine-learning/ml2_15-part02-linear_regression.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/advanced-machine-learning/ml2_15-part12-neural-networks-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/advanced-machine-learning/ml2_15-part16-cnns2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/computer-vision/cv15-part10-categorization2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/computer-vision/cv15-part22-repetition-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/advanced-machine-learning/ml2_16-part08-linear-discriminants-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/advanced-machine-learning/ml2_16-part12-optimization2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/advanced-machine-learning/ml2_16-part16-word-embeddings.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/advanced-machine-learning/ml2_16-part21-repetition.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/computer-vision/cv16-part03-image-processing2.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/computer-vision/cv16-part07-segmentation2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/computer-vision/cv16-part09-categorization2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/computer-vision/cv16-part21-reconstruction4-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2017/machine-learning/ml17-part17-cnns3-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2018/machine-learning/ml18-part06-linear_discriminants2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2018/machine-learning/ml18-part07-linear_svms.pdf", "https://www.cl.cam.ac.uk/teaching/1516/CompVision/slides2016.pdf", "https://www.cl.cam.ac.uk/teaching/1819/CompVision/CompVisLectureNotes2019.pdf", "https://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part17-reconstruction1.pdf", "https://www.vision.rwth-aachen.de/media/course/WS/2017/machine-learning/ml17-part06-linear_discriminants2-6on1.pdf", "https://www.vision.rwth-aachen.de/media/course/WS/2017/machine-learning/ml17-part08-nonlinear_svms-6on1.pdf", "https://www.vision.rwth-aachen.de/media/course/WS/2017/machine-learning/ml17-part10-adaboost.pdf"], "doi": ["https://doi.org/10.1007/978-0-387-31439-6_100073", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part12-randomized_trees-6on1.ppt"]}, {"id": "e4a7e92be7865cebe78ad3ebb46c80789c92d473", "title": "Not-So-CLEVR: learning same-different relations strains feedforward neural networks.", "year": "2018", "pdf": ["https://royalsocietypublishing.org/doi/pdf/10.1098/rsfs.2018.0011", "http://serre-lab.clps.brown.edu/wp-content/uploads/2018/06/not_so_clevr_RoyalSoc.pdf", "http://serre-lab.clps.brown.edu/wp-content/uploads/2019/07/RSFS20180011.pdf"], "doi": ["https://doi.org/10.1098/rsfs.2018.0011", "https://www.ncbi.nlm.nih.gov/pubmed/29951191"]}, {"id": "b882e95f0bbf0f253d1e22afa3090ea3f82456e5", "title": "Face and Body Biometrics in the Wild: Advances in the Visible Spectrum and Beyond", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/b882/e95f0bbf0f253d1e22afa3090ea3f82456e5.pdf"], "doi": []}, {"id": "2c03df8b48bf3fa39054345bafabfeff15bfd11d", "title": "Deep Residual Learning for Image Recognition", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780459"]}, {"id": "1a6a5a33aa27e44b80b51d0bbc26734a7fc2cccf", "title": "Overview of research on facial ageing using the FG-NET ageing database", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1049/iet-bmt.2014.0053"]}]}
\ No newline at end of file
+{"id": "15af83373274f4b4c5976c5f384ea0a5c124b287", "citations": [{"id": "34cd0ad0bdba5e74f06303bb58995bb54f7fcf3d", "title": "Continuously Reproducing Toolchains in Pattern Recognition and Machine Learning Experiments", "year": "2017", "pdf": [], "doi": []}, {"id": "576f4fd5f50c58c755eae73a983939bdccf8fac6", "title": "Deep Imbalanced Learning for Face Recognition and Attribute Prediction", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/576f/4fd5f50c58c755eae73a983939bdccf8fac6.pdf"], "doi": []}, {"id": "b3ce5d65848b40c8035d87c4b11236f34adfae8a", "title": "Distributed Mining of Outliers from Large Multi-Dimensional Databases", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b3ce/5d65848b40c8035d87c4b11236f34adfae8a.pdf"], "doi": []}, {"id": "d98476b475679db68431654be5eaadaa86aee9ff", "title": "IARPA Janus Benchmark - C: Face Dataset and Protocol", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8411217"]}, {"id": "d0df01d1a183d23be8fd638fdb2142280c737e80", "title": "Apprentissage automatique pour la d\u00e9tection d'anomalies dans les donn\u00e9es ouvertes : application \u00e0 la cartographie. (Satellite images analysis for anomaly detection in open geographical data)", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d0df/01d1a183d23be8fd638fdb2142280c737e80.pdf"], "doi": []}, {"id": "c4051f726e529543bd2f2b3039f61c1ba0889301", "title": "Eye In-painting with Exemplar Generative Adversarial Networks", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578922"]}, {"id": "8b79bfc93c7001dd7bb1eea7715af47d76202827", "title": "Decorrelated Adversarial Learning for Age-Invariant Face Recognition", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/8b79/bfc93c7001dd7bb1eea7715af47d76202827.pdf"], "doi": []}, {"id": "461ceb053b119b85022cc591132de6bcdc8bdc1f", "title": "Dictionary Representation of Deep Features for Occlusion-Robust Face Recognition", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8651449"]}, {"id": "9dc915697768dd1f7c7b97e2c25c90b02241958b", "title": "CosFace: Large Margin Cosine Loss for Deep Face Recognition", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578650"]}, {"id": "5d684c197c06139319bf575e2498fe040d9ea32f", "title": "Laplace Landmark Localization", "year": "2019", "pdf": ["https://arxiv.org/pdf/1903.11633.pdf"], "doi": []}, {"id": "1ffe20eb32dbc4fa85ac7844178937bba97f4bf0", "title": "Face Clustering: Representation and Pairwise Constraints", "year": "2018", "pdf": ["https://arxiv.org/pdf/1706.05067.pdf"], "doi": []}, {"id": "8de1c724a42d204c0050fe4c4b4e81a675d7f57c", "title": "Deep Face Recognition: A Survey", "year": "2018", "pdf": ["https://talhassner.github.io/home/projects/DeepFaceSurvey/Masietal2018deepfacesurvey.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8614364", "http://doi.org/10.1109/SIBGRAPI.2018.00067"]}, {"id": "ad8e7b7349e15c4592aa2c18ce79f77671084781", "title": "Fast Face Image Synthesis With Minimal Training", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8658792"]}, {"id": "380dd0ddd5d69adc52defc095570d1c22952f5cc", "title": "Improving Smiling Detection with Race and Gender Diversity", "year": "2017", "pdf": [], "doi": []}, {"id": "65984ea40c3b17bb8965c215b61972cd660f61a7", "title": "Doppelganger Mining for Face Representation Learning", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w27/Smirnov_Doppelganger_Mining_for_ICCV_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265436", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2017.226", "http://doi.org/10.1109/ICCVW.2017.226"]}, {"id": "4739b47af26137ec52bbfb582e6f37e9e9f5aba0", "title": "Hard Example Mining with Auxiliary Embeddings", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w1/Smirnov_Hard_Example_Mining_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575283", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00013", "http://doi.org/10.1109/CVPRW.2018.00013"]}, {"id": "9d14cdbf0af4af7a7bc0a62084fe9c0ab43d6502", "title": "Towards a Fast and Accurate Face Recognition System from Deep Representations", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/9d14/cdbf0af4af7a7bc0a62084fe9c0ab43d6502.pdf"], "doi": []}, {"id": "750486b2278ba542987655eede1b4da8c10f7f2e", "title": "Softmax Dissection: Towards Understanding Intra- and Inter-clas Objective for Embedding Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.01281.pdf"], "doi": []}, {"id": "5a564d108b43c6ff006a86d2fc981cd36c6c54dd", "title": "Deep Learning for Understanding Faces", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/5a56/4d108b43c6ff006a86d2fc981cd36c6c54dd.pdf"], "doi": []}, {"id": "d45fd2b4583dd218091003ab65a4d77ccec6da47", "title": "Large-Scale Bisample Learning on ID Versus Spot Face Recognition", "year": "2018", "pdf": ["http://export.arxiv.org/pdf/1806.03018", "https://arxiv.org/pdf/1806.03018.pdf"], "doi": ["https://doi.org/10.1007/s11263-019-01162-8"]}, {"id": "39b615c73810e13998df3df9d5e73aebd3e67dab", "title": "A Compact Embedding for Facial Expression Similarity", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.11283.pdf"], "doi": []}, {"id": "56f1202f88cefd4aad6f97914eeae61c1f5531b7", "title": "UHDB31: A Dataset for Better Understanding Face Recognition Across Pose and Illumination Variation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265511"]}, {"id": "8ed7d8a07ac21328d3c03ff3880e6f6f939257f6", "title": "Adversarial Learning for Age-Invariant Face Recognition", "year": "", "pdf": ["https://pdfs.semanticscholar.org/8ed7/d8a07ac21328d3c03ff3880e6f6f939257f6.pdf"], "doi": []}, {"id": "4e1a65f3c3d9cfeecab898affbe0b47a9b6c9157", "title": "DIY Human Action Dataset Generation", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575353"]}, {"id": "c607572fd2594ca83f732c9790fd590da9e69eb1", "title": "Comparative Evaluation of Deep Architectures for Face Recognition in Unconstrained Environment ( FRUE )", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c607/572fd2594ca83f732c9790fd590da9e69eb1.pdf"], "doi": []}, {"id": "18858cc936947fc96b5c06bbe3c6c2faa5614540", "title": "Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification", "year": "2018", "pdf": ["http://proceedings.mlr.press/v81/buolamwini18a/buolamwini18a-supp.pdf", "https://dam-prod.media.mit.edu/x/2018/02/06/Gender%20Shades%20Intersectional%20Accuracy%20Disparities.pdf"], "doi": ["http://proceedings.mlr.press/v81/buolamwini18a.html"]}, {"id": "4a6d7d222838c6bc59a32190c2f07d278f15539f", "title": "Towards optimal local binary patterns in texture and face description", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/4a6d/7d222838c6bc59a32190c2f07d278f15539f.pdf"], "doi": []}, {"id": "ddcf0cf00a50cff93c2cbdc6823aad7ab1d3634f", "title": "ID-Softmax: A Softmax-like Loss for ID Face Recognition", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/5244/4f9562ef17557de24d22716491b11bbd2802.pdf"], "doi": []}, {"id": "b612bbd751d94996a02b85829e0b2ac0511350ff", "title": "Learning Representations for Utility and Privacy : An Information-Theoretic Based Approach", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b612/bbd751d94996a02b85829e0b2ac0511350ff.pdf"], "doi": []}, {"id": "eb4be3c7711935c936cb6755e0873cb1492af71e", "title": "A Deep Face Identification Network Enhanced by Facial Attributes Prediction", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575246"]}, {"id": "3d789ce25828a9b55947927063aa87f643c2a41c", "title": "Face In Video Evaluation (FIVE) Face Recognition of Non-Cooperative Subjects", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3d78/9ce25828a9b55947927063aa87f643c2a41c.pdf"], "doi": []}, {"id": "b090bf0d5b4a780821b4f45fc216ac614493020d", "title": "A Generative Model of Worldwide Facial Appearance", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8658761"]}, {"id": "b8f22ef91a7fccbe7b04a0caf0d5d5f88e2cd230", "title": "The 2017 IARPA Face Recognition Prize Challenge (FRPC)", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/b8f2/2ef91a7fccbe7b04a0caf0d5d5f88e2cd230.pdf"], "doi": []}, {"id": "20a64c3d0d2108bc5fc7b0bbd11ad941734d5f2b", "title": "Heterogeneous Face Recognition Using Domain Specific Units", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8565895"]}, {"id": "934f69d038721540c96093cae634573b89d7d714", "title": "DeSTNet : Densely Fused Spatial Transformer Networks 1", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/934f/69d038721540c96093cae634573b89d7d714.pdf"], "doi": []}, {"id": "7d2165ee47828fac5128cd554b9be89c851463fb", "title": "Empirically Analyzing the Effect of Dataset Biases on Deep Face Recognition Systems", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575453"]}, {"id": "2e2534eb1f1af5c043a009391f0ef955aeed2044", "title": "Switchable Normalization for Learning-to-Normalize Deep Representation", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/2e25/34eb1f1af5c043a009391f0ef955aeed2044.pdf"], "doi": []}, {"id": "1e34b7505fef52b2881f4de6e78cfb90d51085a0", "title": "Trunk-Branch Ensemble Convolutional Neural Networks for Large Scale, Few-Shot Video-to-Still Face Recognition", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/1e34/b7505fef52b2881f4de6e78cfb90d51085a0.pdf"], "doi": []}, {"id": "8395cf3535a6628c3bdc9b8d0171568d551f5ff0", "title": "Entropy Non-increasing Games for the Improvement of Dataflow Programming", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.04389.pdf"], "doi": []}, {"id": "2c75658b080a9baaac20db39af86016ffa36f6f0", "title": "Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578977"]}, {"id": "97834ad2a0556fedbea0407a84ca8f520f0fc11f", "title": "Face-Specific Data Augmentation for Unconstrained Face Recognition", "year": "2019", "pdf": ["https://talhassner.github.io/home/projects/augmented_faces/Masietal_IJCV2019.pdf"], "doi": ["https://doi.org/10.1007/s11263-019-01178-0"]}, {"id": "a4433a97e766362c1f2ce6f013dff15a3fe9a3ac", "title": "Overcoming catastrophic forgetting with hard attention to the task", "year": "2018", "pdf": ["https://arxiv.org/pdf/1801.01423.pdf"], "doi": []}, {"id": "64a68e1a3f7e5496ade9ee376f69d3bd15c43b70", "title": "Multi-camera object tracking via deep metric learning", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1117/12.2500776"]}, {"id": "7789e2dcfa2bcd3ac55c63060509629ad77adb73", "title": "DHFML: deep heterogeneous feature metric learning for matching photograph and cartoon pairs", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s13735-018-0160-4"]}, {"id": "48499deeaa1e31ac22c901d115b8b9867f89f952", "title": "Interim Report of Final Year Project HKU-Face : A Large Scale Dataset for Deep Face Recognition", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/4849/9deeaa1e31ac22c901d115b8b9867f89f952.pdf"], "doi": []}, {"id": "3c0fffd4cdbfef4ccd92d528d8b8a60ab0929827", "title": "An Empirical Study of Face Recognition under Variations", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8373845", "http://doi.ieeecomputersociety.org/10.1109/FG.2018.00052", "http://doi.org/10.1109/FG.2018.00052"]}, {"id": "568435e4a2d161c68808a35250be147202867ce4", "title": "Deep Learning For Face Recognition: A Critical Analysis", "year": "2019", "pdf": ["https://arxiv.org/pdf/1907.12739.pdf"], "doi": []}, {"id": "c6cdf39c70aabf973a56db1ea009ab275f3f6ee8", "title": "Image-set, Temporal and Spatiotemporal Representations of Videos for Recognizing, Localizing and Quantifying Actions", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c6cd/f39c70aabf973a56db1ea009ab275f3f6ee8.pdf"], "doi": []}, {"id": "3998f7d6022f67a1cf6050bccd3131911fec5a8a", "title": "Self Residual Attention Network for Deep Face Recognition", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8698884"]}, {"id": "fef0adf785aa6b91d23f0a61a32deece48a7f156", "title": "On the Capacity of Face Representation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.10433.pdf"], "doi": []}, {"id": "9ba4a5e0b7bf6e26563d294f1f3de44d95b7f682", "title": "To Frontalize or Not to Frontalize: Do We Really Need Elaborate Pre-processing to Improve Face Recognition?", "year": "2018", "pdf": ["http://docs.wixstatic.com/ugd/445e27_b7f15ceb15d34e45836f98d9eeba9a78.pdf", "https://arxiv.org/pdf/1610.04823v1.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354113", "http://arxiv.org/abs/1610.04823", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00009", "http://doi.org/10.1109/WACV.2018.00009"]}, {"id": "c924137ca87e8b4e1557465405744f8b639b16fc", "title": "Seeding Deep Learning using Wireless Localization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.10242.pdf"], "doi": []}, {"id": "4da4642ac4c1fcfbecd622dad485307b8d30ed2b", "title": "Deep representation for partially occluded face verification", "year": "2018", "pdf": ["https://jivp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13640-018-0379-2"], "doi": ["https://doi.org/10.1186/s13640-018-0379-2"]}, {"id": "fb67b0625e2374d2c32e447fb682c22784c5a8b5", "title": "Wearable Technologies for Law Enforcement: Multifunctional Vest System Options", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/fb67/b0625e2374d2c32e447fb682c22784c5a8b5.pdf"], "doi": []}, {"id": "4e6ac0f8dfa5592458e100bc0bb5bac69f7912c1", "title": "Robust RGB-D Face Recognition Using Attribute-Aware Loss", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/de47/c456f5e8d0d663c204afca443c6412740fee.pdf"], "doi": []}, {"id": "e3d76f1920c5bf4a60129516abb4a2d8683e48ae", "title": "I Know That Person: Generative Full Body and Face De-identification of People in Images", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w16/papers/Kalafatic_I_Know_That_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8014907", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.173", "http://doi.org/10.1109/CVPRW.2017.173"]}, {"id": "0ab7cff2ccda7269b73ff6efd9d37e1318f7db25", "title": "Facial Coding Scheme Reference 1 Craniofacial Distances", "year": "2019", "pdf": [], "doi": []}, {"id": "15af83373274f4b4c5976c5f384ea0a5c124b287", "title": "Level Playing Field for Million Scale Face Recognition", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099846"]}, {"id": "c9c56f8bb89948d15a9564b146e7bdff7b17a1c2", "title": "Modeling Grasp Motor Imagery", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/c9c5/6f8bb89948d15a9564b146e7bdff7b17a1c2.pdf"], "doi": []}, {"id": "cfb8bc66502fb5f941ecdb22aec1fdbfdb73adce", "title": "Git Loss for Deep Face Recognition", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.08512.pdf"], "doi": []}, {"id": "3417d1521552330aee30e0d9a6aec481ba904b17", "title": "An Investigation of High-Throughput Biometric Systems: Results of the 2018 Department of Homeland Security Biometric Technology Rally", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8698547"]}, {"id": "559b12257d56725fbef5790e2dfdec8751919ef1", "title": "Synthesizing Normalized Faces from Facial Identity Features", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099844"]}, {"id": "4d3fbeb69ee1207d47b182dd88bdd82791f1c17d", "title": "Performance Comparison of Face Detection and Recognition Algorithms", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/4d3f/beb69ee1207d47b182dd88bdd82791f1c17d.pdf"], "doi": []}, {"id": "3f4a0bb3f031cbe7b0043243116e779c1e75d493", "title": "FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age", "year": "2019", "pdf": ["https://arxiv.org/pdf/1908.04913.pdf"], "doi": []}, {"id": "722b8cdb7d786283c6d6512729622561e3072d68", "title": "Temporal Non-volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237665"]}, {"id": "d31328b12eef33e7722b8e5505d0f9d9abe2ffd9", "title": "Deep Unsupervised Domain Adaptation for Face Recognition", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8373866", "http://doi.ieeecomputersociety.org/10.1109/FG.2018.00073", "http://doi.org/10.1109/FG.2018.00073"]}, {"id": "1d4f087217b816691254ef0d4377094ce16eea95", "title": "Adversarially Learned Representations for Information Obfuscation and Inference", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/7778/6c525fce29a84bf4cfcd5e7f901ddc04847a.pdf"], "doi": []}, {"id": "bcd883ef8faa9a81f5c14da97669df1dd2e8f1b8", "title": "Local directional relation pattern for unconstrained and robust face retrieval", "year": "2017", "pdf": ["http://arxiv.org/pdf/1709.09518", "http://arxiv-export-lb.library.cornell.edu/pdf/1709.09518", "https://arxiv.org/pdf/1709.09518.pdf"], "doi": ["https://doi.org/10.1007/s11042-019-07908-3"]}, {"id": "d2eb1079552fb736e3ba5e494543e67620832c52", "title": "DeSTNet: Densely Fused Spatial Transformer Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.04050.pdf"], "doi": []}, {"id": "04922595cee2ce50030674a7179ecd871e5df1d2", "title": "Effective indexing for face recognition", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1117/12.2238096"]}, {"id": "173657da03e3249f4e47457d360ab83b3cefbe63", "title": "HKU-Face : A Large Scale Dataset for Deep Face Recognition Final Report", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1736/57da03e3249f4e47457d360ab83b3cefbe63.pdf"], "doi": []}, {"id": "8a9ca15aebadad4b7cfa18c5af91c431d6045b86", "title": "cvpaper.challenge in 2016: Futuristic Computer Vision through 1, 600 Papers Survey", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06436.pdf"], "doi": []}, {"id": "a2344004f0e1409c0c9473d071a5cfd74bff0a5d", "title": "Learnable PINs: Cross-modal Embeddings for Person Identity", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.00833.pdf"], "doi": []}, {"id": "829770e9eff6ae7f9a2412b63e438e19767c564c", "title": "Computer Vision", "year": "2014", "pdf": ["http://www.cl.cam.ac.uk/teaching/0809/CompVision/CompVisNotes.pdf", "http://www.cl.cam.ac.uk/teaching/1617/CompVision/ConsolidatedSlides.pdf", "http://www.cl.cam.ac.uk/teaching/2004/CompVision/notes.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part01-intro.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part02-linear_regression.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part07-approximate_inference.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part15-latent_factor_models.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part16-beta_processes-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part17-beta_processes2-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part18-support_vector_machines.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part20-structured-output-learning-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/advanced-machine-learning/winter-12-13/lectures/ml2_12-part21-structured-output-learning2.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part01-intro.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part03-image-processing2-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part03-image-processing2.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part05-segmentation1-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part12-local-features3.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part13-categorization2-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-12-13/lectures/cv12-part14-reconstruction1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-13-14/lectures/cv13-part05-structure-extraction.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-13-14/lectures/cv13-part15-local-features4.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part03-image-processing2-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part14-local-features3.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part17-reconstruction1-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part17-reconstruction1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision/winter-14-15/lectures/cv14-part22-repetition.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision_2/lectures/cv2_14-part08-kalman-filter-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_computer_vision_2/lectures/cv2_14-part12-multiobject-tracking3-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/summer-2012/lectures/ml12-part15-graphical_models5.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/summer-2015/lectures-1/ml15-part13-graphical_models1-6on1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/summer-2015/lectures-1/ml15-part15-graphical_models3.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/summer-2015/lectures-1/ml15-part18-repetition.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part02-pde1.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part09-nonlinear_svms.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part13-model_selection.pdf", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part20-graphical_models5.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2014/computer-vision-2/cv2_14-part08-kalman-filter-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2014/computer-vision-2/cv2_14-part12-multiobject-tracking3-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2015/machine-learning/ml15-part13-graphical_models1-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2015/machine-learning/ml15-part15-graphical_models3.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2015/machine-learning/ml15-part18-repetition.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part02-pde1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part05-linear_discriminants-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part12-randomized_trees-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part15-graphical_models1.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2016/machine-learning/ml16-part18-graphical_models4.pdf", "http://www.vision.rwth-aachen.de/media/course/SS/2019/computer-vision/cv19-part02-image-processing.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part01-intro.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part02-linear_regression.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part07-approximate_inference.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part15-latent_factor_models.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part18-support_vector_machines.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2012/advanced-machine-learning/ml2_12-part21-structured-output-learning2.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part03-image-processing2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part14-local-features3.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part17-reconstruction1-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part22-repetition.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/advanced-machine-learning/ml2_15-part01-intro.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/advanced-machine-learning/ml2_15-part02-linear_regression.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/advanced-machine-learning/ml2_15-part12-neural-networks-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/advanced-machine-learning/ml2_15-part16-cnns2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/computer-vision/cv15-part10-categorization2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2015/computer-vision/cv15-part22-repetition-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/advanced-machine-learning/ml2_16-part08-linear-discriminants-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/advanced-machine-learning/ml2_16-part12-optimization2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/advanced-machine-learning/ml2_16-part16-word-embeddings.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/advanced-machine-learning/ml2_16-part21-repetition.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/computer-vision/cv16-part03-image-processing2.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/computer-vision/cv16-part07-segmentation2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/computer-vision/cv16-part09-categorization2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2016/computer-vision/cv16-part21-reconstruction4-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2017/machine-learning/ml17-part17-cnns3-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2018/machine-learning/ml18-part06-linear_discriminants2-6on1.pdf", "http://www.vision.rwth-aachen.de/media/course/WS/2018/machine-learning/ml18-part07-linear_svms.pdf", "https://www.cl.cam.ac.uk/teaching/1516/CompVision/slides2016.pdf", "https://www.cl.cam.ac.uk/teaching/1819/CompVision/CompVisLectureNotes2019.pdf", "https://www.vision.rwth-aachen.de/media/course/WS/2014/computer-vision/cv14-part17-reconstruction1.pdf", "https://www.vision.rwth-aachen.de/media/course/WS/2017/machine-learning/ml17-part06-linear_discriminants2-6on1.pdf", "https://www.vision.rwth-aachen.de/media/course/WS/2017/machine-learning/ml17-part08-nonlinear_svms-6on1.pdf", "https://www.vision.rwth-aachen.de/media/course/WS/2017/machine-learning/ml17-part10-adaboost.pdf"], "doi": ["https://doi.org/10.1007/978-0-387-31439-6_100073", "http://www.mmp.rwth-aachen.de/teaching/lecture_machine_learning/winter-13-14/lectures/ml13-part12-randomized_trees-6on1.ppt"]}, {"id": "e4a7e92be7865cebe78ad3ebb46c80789c92d473", "title": "Not-So-CLEVR: learning same-different relations strains feedforward neural networks.", "year": "2018", "pdf": ["https://royalsocietypublishing.org/doi/pdf/10.1098/rsfs.2018.0011", "http://serre-lab.clps.brown.edu/wp-content/uploads/2018/06/not_so_clevr_RoyalSoc.pdf", "http://serre-lab.clps.brown.edu/wp-content/uploads/2019/07/RSFS20180011.pdf"], "doi": ["https://doi.org/10.1098/rsfs.2018.0011", "https://www.ncbi.nlm.nih.gov/pubmed/29951191"]}, {"id": "b882e95f0bbf0f253d1e22afa3090ea3f82456e5", "title": "Face and Body Biometrics in the Wild: Advances in the Visible Spectrum and Beyond", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/b882/e95f0bbf0f253d1e22afa3090ea3f82456e5.pdf"], "doi": []}, {"id": "2c03df8b48bf3fa39054345bafabfeff15bfd11d", "title": "Deep Residual Learning for Image Recognition", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780459"]}, {"id": "1a6a5a33aa27e44b80b51d0bbc26734a7fc2cccf", "title": "Overview of research on facial ageing using the FG-NET ageing database", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1049/iet-bmt.2014.0053"]}]}
\ No newline at end of file
diff --git a/site/datasets/unknown/voc.json b/site/datasets/unknown/voc.json
index a2197382..771f810c 100644
--- a/site/datasets/unknown/voc.json
+++ b/site/datasets/unknown/voc.json
@@ -1 +1 @@
-{"id": "0ee1916a0cb2dc7d3add086b5f1092c3d4beb38a", "citations": [{"id": "c399c0089fb134d1476fadf5f0426e0e8b70eebd", "title": "The Lov\u00e1sz Hinge: A Novel Convex Surrogate for Submodular Losses.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1512.07797.pdf"], "doi": []}, {"id": "6b6fcf1220ea100aa80004018c78b137289d3c50", "title": "CAD: Scale Invariant Framework for Real-Time Object Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265304"]}, {"id": "656f05741c402ba43bb1b9a58bcc5f7ce2403d9a", "title": "Supervised Learning Approaches for Automatic Structuring of Videos. (M\u00e9thodes d'apprentissage supervis\u00e9 pour la structuration automatique de vid\u00e9os)", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/656f/05741c402ba43bb1b9a58bcc5f7ce2403d9a.pdf"], "doi": []}, {"id": "aa3398e15395a2a380c7c6b3f274c8c60fb0b48c", "title": "Chained Cascade Network for Object Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237476"]}, {"id": "e58434a01c45505995b000f5e631843a2f2ea582", "title": "Scale coding bag of deep features for human attribute and action recognition", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.04884.pdf"], "doi": []}, {"id": "eaf65c7cf4e9f7868c61f48656cb608fae0adcee", "title": "Visual dictionaries as intermediate features in the human brain", "year": "2014", "pdf": ["http://journal-cdn.frontiersin.org/article/104962/files/pubmed-zip/versions/1/pdf", "http://journal.frontiersin.org/article/10.3389/fncom.2014.00168/pdf", "https://pure.uva.nl/ws/files/2455021/162945_fncom_08_00168.pdf"], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/25642183", "http://doi.org/10.3389/fncom.2014.00168", "https://www.wikidata.org/entity/Q34969835"]}, {"id": "4c5d723dd83250c6b289c94318717de2d373a6ed", "title": "Learning Image Classification and Retrieval Models", "year": "2012", "pdf": [], "doi": []}, {"id": "841a5de1d71a0b51957d9be9d9bebed33fb5d9fa", "title": "PCANet: A Simple Deep Learning Baseline for Image Classification?", "year": "2015", "pdf": ["https://arxiv.org/pdf/1404.3606.pdf"], "doi": []}, {"id": "095ccb4e2e0f3934dc1aa51c685b2f54c8a6e588", "title": "Derivate-based Component-Trees for Multi-Channel Image Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01906.pdf"], "doi": []}, {"id": "a221588fd2d062462254481cfd9563fec2f7c387", "title": "Deep neural network ensemble architecture for eye movements classification", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8345537"]}, {"id": "67126ad0af544740c455311d08cb180aec830a6c", "title": "Generating Descriptions of Spatial Relations between Objects in Images", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/6712/6ad0af544740c455311d08cb180aec830a6c.pdf"], "doi": []}, {"id": "823db813f036365cf9b22b2081ec167a2b582532", "title": "Segmentation and Shape Extraction from Convolutional Neural Networks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354273", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00169", "http://doi.org/10.1109/WACV.2018.00169", "http://www.grk1564.uni-siegen.de/publicationPDFbyID?ID=926"]}, {"id": "f3ccdf54a3384e601fa36969e7b3f657e2516a3b", "title": "Paying More A ention to Saliency : Image Captioning with Saliency and Context A ention 1 : 3", "year": "2017", "pdf": [], "doi": []}, {"id": "2c9c597ab660815e07980e9655c3c5989402205b", "title": "Vision-Based Reacquisition for Task-Level Control", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/2c9c/597ab660815e07980e9655c3c5989402205b.pdf"], "doi": []}, {"id": "aae1bf434983545c8a99a5dbfc2ce37435c76e03", "title": "SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00248.pdf"], "doi": []}, {"id": "ff18125a8f549135e6320fed91d0002bd2dae635", "title": "Colour Terms: a Categorisation Model Inspired by Visual Cortex Neurons", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.06300.pdf"], "doi": []}, {"id": "3e50e351687779c05390daf117f0394d1556cd3c", "title": "Die Detektion interessanter Objekte unter Verwendung eines objektbasierten Aufmerksamkeitsmodells", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3e50/e351687779c05390daf117f0394d1556cd3c.pdf"], "doi": []}, {"id": "065f05c9cb2a6080191851dd82cd9b439a77499a", "title": "Comparing Boosted Cascades to Deep Learning Architectures for Fast and Robust Coconut Tree Detection in Aerial Images", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/065f/05c9cb2a6080191851dd82cd9b439a77499a.pdf"], "doi": []}, {"id": "4ba503d8f173880d8e8402808f54b78b653e5d20", "title": "Accelerating Stochastic Gradient Descent via Online Learning to Sample", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/4ba5/03d8f173880d8e8402808f54b78b653e5d20.pdf"], "doi": []}, {"id": "03a2235fea70317461222fac05e38ee35ead9711", "title": "Implementation of a Computer Vision Algorithm for Onboard Detection of Unmanned Aircraft submitted by Luk\u00e1\u0161 Bauer", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/03a2/235fea70317461222fac05e38ee35ead9711.pdf"], "doi": []}, {"id": "d07dabdea9e2e4546b09d07a019723ceb6c61b84", "title": "Deep learning for text spotting", "year": "2015", "pdf": [], "doi": []}, {"id": "7f66ff8dd0313fc9c7d67be7ea5aecdda956657c", "title": "Tracking-by-Segmentation with Online Gradient Boosting Decision Tree", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Son_Tracking-by-Segmentation_With_Online_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Son_Tracking-by-Segmentation_With_Online_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410707", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.350", "http://doi.org/10.1109/ICCV.2015.350"]}, {"id": "4896c9f6958137c88db29a3a707aafae3c29d106", "title": "Discriminative Re-ranking of Diverse Segmentations", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619095"]}, {"id": "858555b6f4663fe083d6c81a2671c9cd8130bbf3", "title": "Object Discovery via Cohesion Measurement", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.08944.pdf"], "doi": []}, {"id": "f81f5da2a1e4eb80b465b8dffca4c9e583a8a8a6", "title": "Rapid Object Detection Systems , Utilising Deep Learning and Unmanned Aerial Systems ( Uas ) for Civil Engineering Applications", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f81f/5da2a1e4eb80b465b8dffca4c9e583a8a8a6.pdf"], "doi": []}, {"id": "369bd35ab8bad4c7bc5e376cc776a5366d97b12e", "title": "An Object Detector Trained on Line Drawings", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/369b/d35ab8bad4c7bc5e376cc776a5366d97b12e.pdf"], "doi": []}, {"id": "46971fb6caa61c606b046da855be4e196a830ccf", "title": "Identification of Scene Text by Character Descriptor in Smart Mobile Devices", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/4697/1fb6caa61c606b046da855be4e196a830ccf.pdf"], "doi": []}, {"id": "afad16c9fee11d8f78785af6b1856beb86b5ccf4", "title": "Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08011.pdf"], "doi": []}, {"id": "9089280062cf40870a322d687c2850d45c02ebae", "title": "Single Image Action Recognition by Predicting Space-Time Saliency", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.04641.pdf"], "doi": []}, {"id": "cf384eda31030a45238ebd8356ace7600da5076b", "title": "Cross-Domain CNN for Hyperspectral Image Classification", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.00093.pdf"], "doi": []}, {"id": "44c5e66e58dd8212b753662e08cc0a7c8327ec50", "title": "Scene Parsing with Object Instance Inference Using Regions and Per-exemplar Detectors", "year": "2014", "pdf": ["http://slazebni.cs.illinois.edu/publications/jtighe-ijcv14.pdf", "http://wwwx.cs.unc.edu/~mn/sites/default/files/jtighe-ijcv14.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0778-5"]}, {"id": "83acbf0bee402b0472ff101cee5942f4137d91c3", "title": "Semi-automatic Annotation on Image Segmentation Hierarchies", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/83ac/bf0bee402b0472ff101cee5942f4137d91c3.pdf"], "doi": []}, {"id": "e9af96d478b487fec9a06dde9e43b2ed3355ea7b", "title": "Automatic thresholding of SIFT descriptors", "year": "2016", "pdf": ["https://arxiv.org/pdf/1811.03173.pdf"], "doi": []}, {"id": "b1369e4785dd0b23f89ca76f45468049c8667863", "title": "1 DARTS : Deceiving Autonomous Cars with Toxic Signs", "year": "2018", "pdf": [], "doi": []}, {"id": "1a5151b4205ab27b1c76f98964debbfc11b124d5", "title": "Self Paced Deep Learning for Weakly Supervised Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.07651.pdf"], "doi": []}, {"id": "f1d8c377093ecf64afd7f17383738e81666fe5ae", "title": "Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.10805.pdf"], "doi": []}, {"id": "12ff1c48f5776fda9d156c7b324af3f2674420a9", "title": "Are Large Scale Training Images or Discriminative Features Important for Codebook Construction?", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/12ff/1c48f5776fda9d156c7b324af3f2674420a9.pdf"], "doi": []}, {"id": "e4dc24e4926df4de3e8d7ca7cd1f4115e91f03e1", "title": "Instance-level video segmentation from object tracks Anonymous CVPR submission", "year": "", "pdf": ["https://pdfs.semanticscholar.org/e4dc/24e4926df4de3e8d7ca7cd1f4115e91f03e1.pdf"], "doi": []}, {"id": "194af94f1ea9357bebb0aab5ab98aa0daa21ddbd", "title": "Snapshot Distillation: Teacher-Student Optimization in One Generation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00123.pdf"], "doi": []}, {"id": "9d67f5adf4497ba99201d318cfbbed07e926c05b", "title": "Unseen Object Segmentation in Videos via Transferable Representations", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.02444.pdf"], "doi": []}, {"id": "0caef87116f62fcc86735401a9aa9d4e170ffbef", "title": "On Performance Evaluation of Driver Hand Detection Algorithms: Challenges, Dataset, and Metrics", "year": "2015", "pdf": ["http://cvrr.ucsd.edu/eshed/papers/Das_ITSC2015.pdf", "http://cvrr.ucsd.edu/publications/2015/DasOhnbarTrivedi_ITSC2015.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7313566", "http://doi.org/10.1109/ITSC.2015.473"]}, {"id": "806aea24148fc2ef851803c216a0a25894d78bf4", "title": "Correlation filter based visual trackers for person pursuit using a low-cost Quadrotor", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7294481", "http://doi.org/10.1109/I4CS.2015.7294481"]}, {"id": "63ed42249d7cbb21a4b0d42419d42b014ff114eb", "title": "Comprehensive Parameter Sweep for Learning-Based Detector on Traffic Lights", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/4817/826f1af10e0c31dee067f8d9255d6387d486.pdf"], "doi": []}, {"id": "1b1323b4677c640ae8835a9ccab611ca1e9652e3", "title": "Robust object tracking with a hierarchical ensemble framework", "year": "2016", "pdf": ["https://arxiv.org/pdf/1509.06925.pdf"], "doi": []}, {"id": "557e5e38a4c5b95e2bc86f491b03e5c8c7add857", "title": "Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Kwak_Thin-Slicing_for_Pose_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Kwak_Thin-Slicing_for_Pose_CVPR_2016_paper.pdf", "http://www.di.ens.fr/willow/pdfscurrent/kwak2016.pdf", "https://vlg.dgist.ac.kr/research/pose_emb/data/CVPR2016_pose.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780903", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.534", "http://doi.org/10.1109/CVPR.2016.534"]}, {"id": "6bcc2b50e32bdbb0c668f75000badf21e6cd0839", "title": "Knowledge Projection for Deep Neural Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.09505.pdf"], "doi": []}, {"id": "071680ca97de050a372ea79f2b99f102bb3ca6ef", "title": "Inferring Unseen Views of People", "year": "2014", "pdf": ["http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/inferring-unseen-views-of-people-paper.pdf", "http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/inferring-unseen-views-of-people-poster.pdf", "http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/supp.pdf", "http://www.cs.utexas.edu/~chaoyeh/cvpr_2014_Inferring_Unseen_Views_of_People%20(2).pdf", "http://www.cs.utexas.edu/~grauman/papers/chen-pose-cvpr2014.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Chen_Inferring_Unseen_Views_2014_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909655", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.258", "http://doi.org/10.1109/CVPR.2014.258"]}, {"id": "415c0eecce9fde7d1ba9c70bd0bfa5471760c117", "title": "Oriented Object Proposals", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/He_Oriented_Object_Proposals_ICCV_2015_paper.pdf", "http://www.cs.cityu.edu.hk/~rynson/papers/iccv15.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/He_Oriented_Object_Proposals_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410397", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.40", "http://doi.org/10.1109/ICCV.2015.40"]}, {"id": "f865248065b8d6bcbce4a4053b73e4de2080ba23", "title": "Efficient object detection for high resolution images", "year": "2015", "pdf": ["https://arxiv.org/pdf/1510.01257.pdf"], "doi": []}, {"id": "e0e19769ad446c2a74c0616fcfb551059c899ce6", "title": "Part level transfer regularization for enhancing exemplar SVMs", "year": "2015", "pdf": ["http://people.csail.mit.edu/yusuf/publications/2015/Aytar15/aytar15.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2015.04.004"]}, {"id": "009fba8df6bbca155d9e070a9bd8d0959bc693c2", "title": "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909475"]}, {"id": "a0703bef11c978cc8faf05eb229e29a889f8a0b1", "title": "Superpixel Hierarchy", "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.06325.pdf"], "doi": []}, {"id": "472de7b3c674e8f06702385569779d11b71bc8f2", "title": "Superpixel Coherency and Uncertainty Models for Semantic Segmentation", "year": "2013", "pdf": ["http://cvlab.postech.ac.kr/~tgx.lim/paper/iccv2013_semantic.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_workshops_2013/W08/papers/Baek_Superpixel_Coherency_and_2013_ICCV_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6755909"]}, {"id": "73818ae13a89c2377c30cdb029fdb7e490fe5367", "title": "Joint cost minimization for multi-object tracking", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8078481", "http://doi.ieeecomputersociety.org/10.1109/AVSS.2017.8078481", "http://doi.org/10.1109/AVSS.2017.8078481"]}, {"id": "ba51ce1ec7b18fa808985b919f4a201fe5e4bafb", "title": "Semantic parsing for priming object detection in indoors RGB-D scenes", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ba51/ce1ec7b18fa808985b919f4a201fe5e4bafb.pdf"], "doi": []}, {"id": "23e707600c3e9a240e24eaa4ed4b0e4ec6a436c1", "title": "Automatic foreground extraction via joint CRF and online learning", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/7f3b/115dd38a933f3a88e3b20b58862216297d63.pdf"], "doi": []}, {"id": "c5632e2117d268159225d5c307b7efbb6428ccba", "title": "Understanding image concepts using ISTOP model", "year": "2016", "pdf": ["http://www.cs.uu.nl/groups/MG/multimedia/publications/art/PR2016b.pdf"], "doi": ["http://doi.org/10.1016/j.patcog.2015.11.010"]}, {"id": "773fd71d3d24c268c99e1c53ae87a28da3bbe0f6", "title": "Conditional Entropies as Over-Segmentation and Under-Segmentation Metrics for Multi-Part Image Segmentation", "year": "2011", "pdf": [], "doi": []}, {"id": "0435a34e93b8dda459de49b499dd71dbb478dc18", "title": "VEGAC: Visual Saliency-based Age, Gender, and Facial Expression Classification Using Convolutional Neural Networks", "year": "2018", "pdf": [], "doi": []}, {"id": "02567fd428a675ca91a0c6786f47f3e35881bcbd", "title": "Deep Label Distribution Learning With Label Ambiguity", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.01731.pdf"], "doi": []}, {"id": "9ea7205ef136f207123cd6b54e15075835ae0049", "title": "Self-supervised language grounding by active sensing combined with Internet acquired images and text", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9ea7/205ef136f207123cd6b54e15075835ae0049.pdf"], "doi": []}, {"id": "6452d294af27b1f9408c9522bfb98bf00e1e4732", "title": "A novel infrared video surveillance system using deep learning based techniques", "year": "2018", "pdf": ["https://ore.exeter.ac.uk/repository/bitstream/handle/10871/32083/MTA-manuscript-revision-R2-accepted.pdf?isAllowed=y&sequence=1", "https://repository.edgehill.ac.uk/10281/6/MTA-manuscript-revision-R2.pdf"], "doi": ["https://doi.org/10.1007/s11042-018-5883-y"]}, {"id": "191beb87f84326d2cc9c427efe2a5abee8f67574", "title": "Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05462.pdf"], "doi": []}, {"id": "5020a75c45416073d0b07b1deb7382bc80de1779", "title": "Human Detection Using Learned Part Alphabet and Pose Dictionary", "year": "2014", "pdf": ["http://cis-linux1.temple.edu/~latecki/Papers/HumanDetectionECCV2014.pdf", "http://mc.eistar.net/UpLoadFiles/Papers/%5B38%5D%202014%20ECCV%20Yaocong.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/ECCV_2014/papers/8693/86930251.pdf", "https://cis.temple.edu/~latecki/Papers/HumanDetectionECCV2014.pdf"], "doi": ["http://doi.org/10.1007/978-3-319-10602-1_17"]}, {"id": "6e7248f33be3f6b44d6089b7039a5c2d84acaed0", "title": "Object cosegmentation using deep Siamese network", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02555.pdf"], "doi": []}, {"id": "b8ccc5341a1b0214e9d155b019962023f344c2ee", "title": "Incremental Learning of Object Detectors without Catastrophic Forgetting", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06977.pdf"], "doi": []}, {"id": "37668092cf8b7695d4a85eb7a25e9a2ef0fd0739", "title": "Robust object detection under partial occlusion", "year": "2016", "pdf": [], "doi": []}, {"id": "49f276e1b8fd162ac3cd996becc63cab2b2535b7", "title": "Trained 3D Models for CNN based Object Recognition", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/49f2/76e1b8fd162ac3cd996becc63cab2b2535b7.pdf"], "doi": []}, {"id": "1426045c4188f09fec46d0d2f246357a230a1748", "title": "Structured Labels in Random Forests for Semantic Labelling and Object Detection", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6784137", "http://doi.org/10.1109/TPAMI.2014.2315814", "https://www.ncbi.nlm.nih.gov/pubmed/26352638", "https://www.wikidata.org/entity/Q38404154"]}, {"id": "efe133717899b41cd4c0b0c999da312d3af60a6e", "title": "Depth-Based Hand Pose Estimation: Methods, Data, and Challenges", "year": "2018", "pdf": ["https://arxiv.org/pdf/1504.06378.pdf"], "doi": []}, {"id": "9caa7605c16da42761c8a27327f5f037dbf901fa", "title": "q-Gaussian mixture models for image and video semantic indexing", "year": "2013", "pdf": [], "doi": ["http://doi.org/10.1016/j.jvcir.2013.10.005", "http://t2r2.star.titech.ac.jp/rrws/file/CTT100664441/ATD100000413/"]}, {"id": "4bb84c9b24456fb0bb920ca83280bd9c48ad4b66", "title": "Instance-Level Video Segmentation from Object Tracks", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Seguin_Instance-Level_Video_Segmentation_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Seguin_Instance-Level_Video_Segmentation_CVPR_2016_paper.pdf", "http://www.di.ens.fr/willow/pdfscurrent/seguin2016.pdf", "http://www.di.ens.fr/willow/research/instancelevel/seguin16instancelevel.pdf", "http://www.di.ens.fr/~bojanowski/papers/seguin16instance.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780769", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.400", "http://doi.org/10.1109/CVPR.2016.400"]}, {"id": "ce0dbe6b1abecb54dcc98dbe652aa63d190dbc94", "title": "Part-Based Models for Finding People and Estimating Their Pose", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/ce0d/be6b1abecb54dcc98dbe652aa63d190dbc94.pdf"], "doi": []}, {"id": "a5683661e80668e05170bf17bcbd754d1b07af74", "title": "Comparison of Data Set Bias in Object Recognition Benchmarks", "year": "2015", "pdf": ["http://vfacstaff.ltu.edu/lshamir/publications/object_recognition_dataset_bias.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7299607", "http://doi.org/10.1109/ACCESS.2015.2491921"]}, {"id": "646a669f1dc38ae961fe41fbd3c83cab64ce9d53", "title": "Real-Time Seamless Single Shot 6D Object Pose Prediction", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578136"]}, {"id": "575a0e97702edcb0621a47b574949bac50e34200", "title": "Unsupervised Learning by Predicting Noise", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.05310.pdf"], "doi": []}, {"id": "b9128ff3b0b96815ff41a7d5fb2b4bef69f635ca", "title": "Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.04984.pdf"], "doi": []}, {"id": "7c03a0ad5202a6a31ad3b78b11f6b45ecd840616", "title": "Scale-Invariant Feature Learning using Deconvolutional Neural Networks for Weakly-Supervised Semantic Segmentation", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/7c03/a0ad5202a6a31ad3b78b11f6b45ecd840616.pdf"], "doi": []}, {"id": "17342b1c4caccfc499d9ae55a68d7b93285c5d6b", "title": "Action recognition in still images using a combination of human pose and context information", "year": "2012", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6466977", "http://doi.org/10.1109/ICIP.2012.6466977"]}, {"id": "571d2b173c2db8ac751dabdfcf5a18c06f365e05", "title": "Improved Part Segmentation Performance by Optimising Realism of Synthetic Images using Cycle Generative Adversarial Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06301.pdf"], "doi": []}, {"id": "90e36f66c25a4c73a252102c6c6c329c36d82676", "title": "Probably Unknown: Deep Inverse Sensor Modelling In Radar", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08151.pdf"], "doi": []}, {"id": "fb710e9d897b7c1fd5275a0bcfa22711c5768990", "title": "A Graphical Model for Rapid Obstacle Image-Map Estimation from Unmanned Surface Vehicles", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/fb71/0e9d897b7c1fd5275a0bcfa22711c5768990.pdf"], "doi": []}, {"id": "821ba3eba1e36a29cc482f5378f4a0d0f6893159", "title": "Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.07926.pdf"], "doi": []}, {"id": "b50156e76ae03a1c0b04cd2076a99b7f2b441506", "title": "An image classification method that considers privacy-preservation", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1016/j.neucom.2016.04.056"]}, {"id": "3481a544e28cfc14108b0785eef7c12747e622ee", "title": "Online Multi-object Tracking via Structural Constraint Event Aggregation", "year": "2016", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/cvpr16_mot.pdf", "http://vc.cs.nthu.edu.tw/home/paper/codfiles/melu/201703210652/Online%20Multi-Object%20Tracking%20via%20Structural%20Constraint%20Event%20Aggregation.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Yoon_Online_Multi-Object_Tracking_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780524", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.155", "http://doi.org/10.1109/CVPR.2016.155"]}, {"id": "7fd5d2b0a034da43a747f6b8be3e51d775a05625", "title": "A Method to Detect Boats in Images of the Amazonian Rivers", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8247064", "http://doi.ieeecomputersociety.org/10.1109/BRACIS.2017.73", "http://doi.org/10.1109/BRACIS.2017.73"]}, {"id": "13105c611a059b4825bc92ff9778f532b6a849b2", "title": "Compressing Sparse Feature Vectors Using Random Ortho-Projections", "year": "2010", "pdf": ["http://www.ee.oulu.fi/mvg/files/pdf/PID1267977.pdf", "http://www.ee.oulu.fi/research/mvmp/mvg/files/pdf/PID1267977.pdf", "http://www.rni.helsinki.fi/~msa/pub/ICPR2010.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5597593", "http://doi.ieeecomputersociety.org/10.1109/ICPR.2010.345", "http://doi.org/10.1109/ICPR.2010.345"]}, {"id": "0967341790643f680f3fc9dc87bfe311723be4e4", "title": "A Perception-Driven Transcale Display Scheme for Space Image Sequences", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0967/341790643f680f3fc9dc87bfe311723be4e4.pdf"], "doi": []}, {"id": "a8bf49021017e19df051a3efb7337d93ea263e37", "title": "Deep Multiple Instance Hashing for Object-based Image Retrieval", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a8bf/49021017e19df051a3efb7337d93ea263e37.pdf"], "doi": []}, {"id": "347ce37f15cea5bb8d0a676562664f80e3609b78", "title": "Pixel Objectness: Learning to Segment Generic Objects Automatically in Images and Videos", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.04702.pdf"], "doi": []}, {"id": "0755ee472e2bc2968b16f851a16c39b3f3e2d0d0", "title": "From Weakly Supervised Object Localization to Semantic Segmentation by Probabilistic Image Modeling", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8227436", "http://doi.org/10.1109/DICTA.2017.8227436"]}, {"id": "659fc2a483a97dafb8fb110d08369652bbb759f9", "title": "Improving the Fisher Kernel for Large-Scale Image Classification", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/659f/c2a483a97dafb8fb110d08369652bbb759f9.pdf"], "doi": []}, {"id": "1e02dfeb93e8fd8753d2e69baf705baf8996cb81", "title": "Online Object Tracking, Learning and Parsing with And-Or Graphs", "year": "2014", "pdf": ["https://arxiv.org/pdf/1509.08067.pdf"], "doi": []}, {"id": "bdfb5f11d497b44b17d0315c3b6892f835723832", "title": "Object Captioning and Retrieval with Natural Language", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06152.pdf"], "doi": []}, {"id": "43fe9006b90137d6ce85a539685ce66c13f0e38e", "title": "A review of image-based automatic facial landmark identification techniques", "year": "", "pdf": ["https://pdfs.semanticscholar.org/43fe/9006b90137d6ce85a539685ce66c13f0e38e.pdf"], "doi": []}, {"id": "642772c38ff690d17a3ce84a1d8646aefc802139", "title": "VIDEO OBJECT TRACKING BASED ON AUTOMATIC BACKGROUND SEGMENTATION : A SURVEY", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/6427/72c38ff690d17a3ce84a1d8646aefc802139.pdf"], "doi": []}, {"id": "303c08071500421c3aca758e6c7cd6a9fcbda1a8", "title": "Scene understanding with complete scenes and structured representations", "year": "2014", "pdf": [], "doi": []}, {"id": "86f0f71bff42e4bdc60014e4f94ec76d52c8eccf", "title": "Felzenszwalb-Baum-Welch: Event Detection by Changing Appearance", "year": "2013", "pdf": ["https://arxiv.org/pdf/1306.4746.pdf"], "doi": []}, {"id": "d9cc8bc5c4a4b29ab40f75b721bd9e5140d2baf6", "title": "Object Detection for Crime Scene Evidence Analysis Using Deep Learning", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6926/4f28158f9245a06f7a2c1ae666241261cc0e.pdf"], "doi": []}, {"id": "d3f6b3ce8f7b67c1e112a79b3fe9764242c655f5", "title": "Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354202"]}, {"id": "9b6538d09e914c41345812b3086feff1dc1ae218", "title": "Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08937.pdf"], "doi": []}, {"id": "bf417e1c265b31720b4fb980afb83cc3a573fa6f", "title": "Representations and Similarities of Images for Visual Classification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bf41/7e1c265b31720b4fb980afb83cc3a573fa6f.pdf"], "doi": []}, {"id": "4dc57432fa8fea1614a39c324bf11ae0620cb26f", "title": "Aalborg Universitet Detection of U . S . Traffic", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/6e53/63af2bfb7d1b2bd13feb41c2688bd0cf12b3.pdf"], "doi": []}, {"id": "878169be6e2c87df2d8a1266e9e37de63b524ae7", "title": "Image interpretation above and below the object level.", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/8781/69be6e2c87df2d8a1266e9e37de63b524ae7.pdf"], "doi": []}, {"id": "3daafe6389d877fe15d8823cdf5ac15fd919676f", "title": "Human Action Localization with Sparse Spatial Supervision", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05197.pdf"], "doi": []}, {"id": "04f9b591cdfa1e3667230ae1224b1dfdac0a8ef1", "title": "Discriminative Segment Annotation in Weakly Labeled Video", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619165"]}, {"id": "4e4f2c4d2ea47636ca2ab795770d6b3214640f37", "title": "Efficient Maximum Appearance Search for Large-Scale Object Detection", "year": "2013", "pdf": ["http://researcher.watson.ibm.com/researcher/files/us-liangliang.cao/qiangcvpr2013_final.pdf", "http://rogerioferis.com/publications/ChenCVPR2013.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d190.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Chen_Efficient_Maximum_Appearance_2013_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619254", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.410", "http://doi.org/10.1109/CVPR.2013.410"]}, {"id": "9434524669777d281a8a7358f20181c9e157942e", "title": "VSEM: An open library for visual semantics representation", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/9434/524669777d281a8a7358f20181c9e157942e.pdf"], "doi": []}, {"id": "0e0900b88c33b671be5dd2ded9885b6526d6b429", "title": "From captions to visual concepts and back", "year": "2015", "pdf": ["https://arxiv.org/pdf/1411.4952.pdf"], "doi": []}, {"id": "4d910c5ab0b70ddbef6be944077ed63821608135", "title": "On Dimensionality Reduction for Indexing and Retrieval of Large-Scale Solar Image Data", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/4d91/0c5ab0b70ddbef6be944077ed63821608135.pdf"], "doi": []}, {"id": "9076183dcdb28ebb3e547f7ffd3f9d5d0faec531", "title": "Describing Video Contents in Natural Language", "year": "2012", "pdf": [], "doi": []}, {"id": "07764e1607d9e3d8094455adb658077996eb38c4", "title": "End-to-End Trained CNN Encoder-Decoder Networks for Image Steganography", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.07201.pdf"], "doi": []}, {"id": "46f135110c5fc5f158bc3ffce21b9ae946c7ff68", "title": "Adaptive NormalHedge for robust visual tracking", "year": "2015", "pdf": ["https://core.ac.uk/download/pdf/33581176.pdf", "https://pure.qub.ac.uk/portal/files/13941301/main_huiyu.pdf"], "doi": ["https://doi.org/10.1016/j.sigpro.2014.08.027"]}, {"id": "b961009dedea99f948650df7291a28f18bbfc1dc", "title": "Towards Automated Visual Monitoring of Individual Gorillas in the Wild", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265544"]}, {"id": "7dbc61e2dc497e9dcff98e7df832780cc8a2b60c", "title": "A Flexible Object-of-Interest Annotation Framework for Online Video Portals", "year": "2012", "pdf": ["http://www.mdpi.com/1999-5903/4/1/179/pdf"], "doi": ["https://doi.org/10.3390/fi4010179"]}, {"id": "d4f454b24a7901dea14858808bbe277c7bee8ffb", "title": "Edge-based Component-Trees for Multi-Channel Image Segmentation", "year": "2017", "pdf": [], "doi": []}, {"id": "6768b558cc58e113096540c123ef3b2c2d2469a1", "title": "Maximum Margin Linear Classifiers in Unions of Subspaces", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/1a06/e518bf15015153b4973bb2e9e06e51485a4c.pdf"], "doi": []}, {"id": "ba6c19771926564e89be4ace7c33dc3da580249e", "title": "Utilisation du contexte pour l'indexation s\u00e9mantique des images et vid\u00e9os. (Using context for semantic indexing of images and videos)", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/ba6c/19771926564e89be4ace7c33dc3da580249e.pdf"], "doi": []}, {"id": "447b28c347172c6da0fb4d764a534fdee557b7f8", "title": "Studying Relationships between Human Gaze, Description, and Computer Vision", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6618945"]}, {"id": "782b21e803d149955c627c063ae60efeae04a9b1", "title": "Analysis of Multilayer Neural Networks for Object Recognition", "year": "2014", "pdf": [], "doi": []}, {"id": "3e01f2fefe219bfeb112f1d82e76ebba4c0e2aac", "title": "Transfer learning via attributes for improved on-the-fly classification", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6836097", "http://doi.ieeecomputersociety.org/10.1109/WACV.2014.6836097", "http://doi.org/10.1109/WACV.2014.6836097"]}, {"id": "ba156b81fe8fca1fd1bfb1c822e39205c4ff355b", "title": "Unsupervised Multi-class Joint Image Segmentation", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909798"]}, {"id": "72048081cfe678f700c52e1c7a56713a8e0865b6", "title": "Unsupervised Adversarial Visual Level Domain Adaptation for Learning Video Object Detectors from Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02074.pdf"], "doi": []}, {"id": "9cd8a2d07f07d888fcf50aa0735d0831edcf5e46", "title": "Bag of contour fragments for robust shape classification", "year": "2014", "pdf": ["http://cis-linux1.temple.edu/~latecki/Papers/XinggangPR2014.pdf", "http://mc.eistar.net/~xwang/pubs/BagOfShape.pdf", "http://mclab.eic.hust.edu.cn/~xwang/pubs/BagOfShape.pdf", "https://cis.temple.edu/~latecki/Papers/XinggangPR2014.pdf"], "doi": ["http://doi.org/10.1016/j.patcog.2013.12.008"]}, {"id": "8c21cd8d5e98c77d727fc900450c6223f9e1fa24", "title": "DARE: Dynamic Adaptive Mobile Augmented Reality with Edge Computing", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8526799"]}, {"id": "7fe203374ba3ddc8462a7c775b276e53f09dd036", "title": "NavigationNet: A Large-scale Interactive Indoor Navigation Dataset", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.08374.pdf"], "doi": []}, {"id": "8f8599012002dd3bbb6526b3be92d7a7355ad22a", "title": "Construction et \u00e9valuation d'un corpus pour la recherche d'instances d'images mus\u00e9ales", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8f85/99012002dd3bbb6526b3be92d7a7355ad22a.pdf"], "doi": []}, {"id": "ebf35073e122782f685a0d6c231622412f28a53b", "title": "A High-Quality Denoising Dataset for Smartphone Cameras", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578280"]}, {"id": "9463f71b2d8e291d5fc5a7db6b95b3d01e759b29", "title": "Describing Spatial Relationships between Objects in Images in English and French", "year": "2015", "pdf": ["http://www.emnlp2015.org/proceedings/VL/pdf/VL16.pdf"], "doi": ["https://doi.org/10.18653/v1%2FW15-2816", "http://aclweb.org/anthology/W15-2816", "https://doi.org/10.18653/v1/W15-2816"]}, {"id": "aaa6fe8045e1a071e1762cffe4f59e0bd508daf9", "title": "Single-Pedestrian Detection Aided by Two-Pedestrian Detection", "year": "2015", "pdf": ["http://www.ee.cuhk.edu.hk/~wlouyang/Papers/tpami15-ouyang_xgWang_xyZeng.pdf", "http://www.ee.cuhk.edu.hk/~xgwang/papers/ouyangZWtpami15.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6994306", "http://doi.ieeecomputersociety.org/10.1109/TPAMI.2014.2377734", "http://doi.org/10.1109/TPAMI.2014.2377734", "https://www.ncbi.nlm.nih.gov/pubmed/26353133"]}, {"id": "2a7007555f71e559c6aa33efbd3bd8b401638d82", "title": "Full interpretation of minimal images", "year": "2018", "pdf": ["https://perso.telecom-paristech.fr/bloch/AIC/articles/BenYosef2017.pdf"], "doi": ["https://www.sciencedirect.com/science/article/pii/S001002771730269X?dgcid=api_sd_search-api-endpoint", "http://doi.org/10.1016/j.cognition.2017.10.006", "https://www.ncbi.nlm.nih.gov/pubmed/29107889"]}, {"id": "08c71fe89af5f168b373e92b44a7cf9d1755fb8c", "title": "The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition", "year": "2013", "pdf": ["http://infoscience.epfl.ch/record/182860/files/2013_ChavarriagaPRLETTERS_preprint.pdf?version=1", "https://www.researchgate.net/profile/Ricardo_Chavarriaga/publication/258031577_The_Opportunity_challenge_A_benchmark_database_for_on-body_sensor-based_activity_recognition/links/02e7e528146aa12213000000.pdf"], "doi": ["https://doi.org/10.1016/j.patrec.2012.12.014"]}, {"id": "8d73906f0a232e8b94200017e512446c1af4dd9d", "title": "Detection of U.S. Traffic Signs", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7116530"]}, {"id": "497857bce6ea1ed4889fb949a2f176072e2509c7", "title": "A Comparison of L_1 Norm and L_2 Norm Multiple Kernel SVMs in Image and Video Classification", "year": "2009", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5137808"]}, {"id": "1d5f704a98d82c34de96ceb80fa06552082effd3", "title": "Dynamic Zoom-in Network for Fast Object Detection in Large Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578822"]}, {"id": "3de71ddc07619c0dd6bbaa3f7b412a9262a0e761", "title": "Discriminatively Trained And-Or Tree Models for Object Detection", "year": "2013", "pdf": ["http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d278.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Song_Discriminatively_Trained_And-Or_2013_CVPR_paper.pdf", "http://www.stat.ucla.edu/~sczhu/papers/Conf_2013/DiscriminativeAOG_cvpr2013.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619265", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.421", "http://doi.org/10.1109/CVPR.2013.421"]}, {"id": "18b4a20ed465972d9d8f3f8d8982d321acf45907", "title": "Mod\u00e9lisation de contextes pour l'annotation s\u00e9mantique de vid\u00e9os. (Context based modeling for video semantic annotation)", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/18b4/a20ed465972d9d8f3f8d8982d321acf45907.pdf"], "doi": []}, {"id": "992a614aa601c52b20729538ea25b62471ffe8bc", "title": "Towards Automatic Construction of Diverse, High-quality Image Dataset", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06495.pdf"], "doi": []}, {"id": "53822d61e829ef02a95a6c89fea082114fd3e16b", "title": "A General Framework for Tracking Multiple People from a Moving Camera", "year": "2013", "pdf": ["http://www.willowgarage.com/sites/default/files/pami_preprint.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6361406", "http://doi.org/10.1109/TPAMI.2012.248", "https://www.ncbi.nlm.nih.gov/pubmed/23681988", "https://www.wikidata.org/entity/Q48723090"]}, {"id": "323eb410e0d0978901a8baa670f905f280ab19ff", "title": "Inner-Scene Similarities as a Contextual Cue for Object Detection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.04406.pdf"], "doi": []}, {"id": "7532996c27b199ed89b412a9f0df7483df83ea72", "title": "Committees of deep feedforward networks trained with few data", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.5947.pdf"], "doi": []}, {"id": "bf7238df8b3a7fc0ebf0e8028a417c7e99fca8d8", "title": "An ontology-based framework for the automated analysis and interpretation of comic books' images", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1016/j.ins.2016.10.032", "https://hal.archives-ouvertes.fr/hal-01387033/document"]}, {"id": "c6e042f9db094d3a01c13a9d3120fc6898f40cb8", "title": "Multi-label Classification for Image Annotation via Sparse Similarity Voting", "year": "2010", "pdf": ["http://naosite.lb.nagasaki-u.ac.jp/dspace/bitstream/10069/27087/1/LNCS6469_344.pdf", "https://page-one.springer.com/pdf/preview/10.1007/978-3-642-22819-3_35"], "doi": ["https://doi.org/10.1007/978-3-642-22819-3_35"]}, {"id": "2dd6749ddffa620d2ac40275a436ecd89aa51a45", "title": "Learning Dual Multi-Scale Manifold Ranking for Semantic Segmentation of High-Resolution Images", "year": "2017", "pdf": ["http://www.mdpi.com/2072-4292/9/5/500/pdf"], "doi": ["https://doi.org/10.3390/rs9050500", "https://www.preprints.org/manuscript/201704.0061/v1/download"]}, {"id": "478261574ddc6cf297611000735aa9808f8f0030", "title": "ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.04405.pdf"], "doi": []}, {"id": "c5fcc36768428185c0ec0f04c82c9204c9ba962c", "title": "Deep Material-Aware Cross-Spectral Stereo Matching", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578303"]}, {"id": "e4fc560a78e48bd927c2f6253f5fc489927bb15f", "title": "Detecting objects in internet videos AIMS Project Report", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/e4fc/560a78e48bd927c2f6253f5fc489927bb15f.pdf"], "doi": []}, {"id": "2049db406168f63c46e5efd2d5ceb5941e3fdc7c", "title": "Region detection and matching for object recognition", "year": "2013", "pdf": [], "doi": []}, {"id": "e42b89b6ed1c6d79286a62ded1e4c090f474eb40", "title": "Using image analytics to monitor retail store shelves", "year": "2015", "pdf": [], "doi": ["https://doi.org/10.1147/JRD.2015.2394513"]}, {"id": "64fb6a04a3ec96b2ad266c381c75f4dc16ce3460", "title": "Hole-based traffic sign detection method for traffic signs with red rim", "year": "2013", "pdf": [], "doi": ["https://doi.org/10.1007/s00371-013-0879-0"]}, {"id": "24c20c28871fa923c3f45b745b9b9f2d3d280e81", "title": "Harmony potentials for joint classification and segmentation", "year": "2010", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5540048"]}, {"id": "06f1c079303937f6022e6157e6341c7921fe9428", "title": "Efficient Dense Rigid-Body Motion Segmentation and Estimation in RGB-D Video", "year": "2014", "pdf": ["http://ais.uni-bonn.de/papers/IJCV_2015_Stueckler_Motion_Segmentation.pdf", "http://www.ais.uni-bonn.de/papers/IJCV_2015_Stueckler_Motion_Segmentation.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0796-3"]}, {"id": "333b877ea761c5c1d4ffa39654fc19bd015e245d", "title": "Ontology-Based Semantic Image Segmentation Using Mixture Models and Multiple CRFs", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7450190"]}, {"id": "0ecaabbf846bbc78c91bf7ff71b998b61c0082d8", "title": "Automated Visual Fin Identification of Individual Great White Sharks", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.06323.pdf"], "doi": []}, {"id": "28863c0f3a1aa186bf1c281c73784cf36e2bf361", "title": "Efficient Non-iterative Domain Adaptation of Pedestrian Detectors to Video Scenes", "year": "2014", "pdf": ["http://eprints.whiterose.ac.uk/84865/1/ICPR14.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6976833", "http://doi.org/10.1109/ICPR.2014.123"]}, {"id": "054738ce39920975b8dcc97e01b3b6cc0d0bdf32", "title": "Towards the design of an end-to-end automated system for image and video-based recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.07883.pdf"], "doi": []}, {"id": "4446924885545b255164b32e42b8375bac699f23", "title": "Object semantic categorization based on ensemble SVM classifiers", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7867229"]}, {"id": "fc2c39b6439623c00b10e8d9826b1c82e8487805", "title": "Generalized Semantic Preserving Hashing for N-Label Cross-Modal Retrieval", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Mandal_Generalized_Semantic_Preserving_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099765", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.282", "http://doi.org/10.1109/CVPR.2017.282"]}, {"id": "92cd808bba43c3702d8cbddde65ee42bf01676d4", "title": "A MultiPath Network for Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.02135.pdf"], "doi": []}, {"id": "3bccc5621b14f2e6b07a5936acecdf957724c6ff", "title": "Convolutional Fisher Kernels for RGB-D Object Recognition", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7335478", "http://doi.ieeecomputersociety.org/10.1109/3DV.2015.23", "http://doi.org/10.1109/3DV.2015.23"]}, {"id": "0b67879b1d5db9da12490b41b4f52d12626e87bc", "title": "The KIT object models database: An object model database for object recognition, localization and manipulation in service robotics", "year": "2012", "pdf": ["http://ijr.sagepub.com/content/31/8/927.full.pdf"], "doi": ["https://doi.org/10.1177/0278364912445831"]}, {"id": "98b4bf8cf8890f50b12e4fabe78bafd687a598c2", "title": "Semantic Labeling Based Vehicle Detection in Aerial Imagery", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354178"]}, {"id": "e03a2299caf2febcc7b87ee4e61e78ad8cb24e45", "title": "Combined Holistic and Local Patches for Recovering 6D Object Pose", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265469"]}, {"id": "26eadb307d62ab28713931beb8be9ff0f04c6ea0", "title": "Synthetic Viewpoint Prediction", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7801548", "http://doi.ieeecomputersociety.org/10.1109/CRV.2016.58", "http://doi.org/10.1109/CRV.2016.58"]}, {"id": "55d01b7314d78fe3bc5ae03b6e414ecba14188f8", "title": "Cognitive Inspired WOR Framework to Reveal Image Semantics, for Efficient Content Based Image Retrieval", "year": "2015", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2709034"]}, {"id": "05e9e85b5137016c93d042170e82f77bb551a108", "title": "A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation", "year": "2016", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Perazzi_A_Benchmark_Dataset_CVPR_2016_paper.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_poster_cvpr_2016.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_supplementary.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780454", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.85", "http://doi.org/10.1109/CVPR.2016.85"]}, {"id": "64bff565c83c6ce3fac783d8d67191af99803701", "title": "Learning to Co-Generate Object Proposals with a Deep Structured Network", "year": "2016", "pdf": ["http://infoscience.epfl.ch/record/217984/files/HayderHeSalzmannCVPR16.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780650", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.281", "http://doi.org/10.1109/CVPR.2016.281"]}, {"id": "66dcc6771e35068a1ea2f6e6f4cdb9a40a4df450", "title": "A Linear Approximation to the chi^2 Kernel with Geometric Convergence", "year": "2012", "pdf": ["https://arxiv.org/pdf/1206.4074.pdf"], "doi": []}, {"id": "dbf2d57def648d1dae7717c92a32ff02157e5cb5", "title": "RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.01054.pdf"], "doi": []}, {"id": "2284ba28bd3b1afaf06afb8c2a94638e350b3ecb", "title": "Boosting Object Proposals: From Pascal to COCO", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01226.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410538", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.181", "http://doi.org/10.1109/ICCV.2015.181"]}, {"id": "174b6d661b96840e27cd9435c2dbb8e538b2c8a6", "title": "Progressive Representation Adaptation for Weakly Supervised Object Localization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.04647.pdf"], "doi": []}, {"id": "b95cdaaa0d6c191bcc8169ce555219ad545258fb", "title": "Online streaming feature selection: a minimum redundancy, maximum significance approach", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s10044-018-0690-7"]}, {"id": "0f780a8cb09627bec41000345c2771df2853224a", "title": "Automatic inspection of aeronautic components", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1007/s00138-017-0839-1"]}, {"id": "c1206330ba57a27fd0acc29dd39825bbf2d91060", "title": "A Shape Reconstructability Measure of Object Part Importance with Applications to Object Detection and Localization", "year": "2014", "pdf": ["http://www.stat.ucla.edu/~yuille/Pubs10_12/PartImportance_IJCV2014_online.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0705-9"]}, {"id": "4c500c84e16e5ebb50b33f9bcff36854e5131c16", "title": "All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification", "year": "2016", "pdf": ["https://arxiv.org/pdf/1711.04450.pdf"], "doi": []}, {"id": "02f86370fd467f0d03948a94a346034d8a111ffd", "title": "Semantic Video Retrieval Using High Level Context", "year": "2008", "pdf": ["https://pdfs.semanticscholar.org/02f8/6370fd467f0d03948a94a346034d8a111ffd.pdf"], "doi": []}, {"id": "d111faa1990f80e3351ea1eef0e5fc177d4e44b4", "title": "Iteratively Training Look-Up Tables for Network Quantization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.05355.pdf"], "doi": []}, {"id": "165c27a4bfb56562c807279bef9d15f1bced5ca0", "title": "Scene parsing using inference Embedded Deep Networks", "year": "2016", "pdf": ["http://www.adv-ci.com/publications/2016_PR_Bu.pdf"], "doi": ["http://doi.org/10.1016/j.patcog.2016.01.027"]}, {"id": "f348d23a88fd81e05585897629f2f230fcfe77c7", "title": "Transfer Learning of Deep Neural Networks for Visual Collaborative Maritime Asset Identification", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8537839"]}, {"id": "87fe38a79ee12531bb618d4006a476b3a5256f3e", "title": "Relative Saliency and Ranking: Models, Metrics, Data, and Benchmarks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02426.pdf"], "doi": []}, {"id": "d8b8e165279ca2091d5af1440ed974db4792250f", "title": "Mean Response-Time Minimization of a Soft-Cascade Detector", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ad73/ff39869e223dba6e0ee94481b6c32766df86.pdf"], "doi": []}, {"id": "0f6a2ea69c325bcbfca85fb05cb5f542873b1bf8", "title": "Food Recognition and Detection with Minimum Supervision", "year": "2016", "pdf": [], "doi": []}, {"id": "df8aee8aef6f0c71f968979318dafcd53da04bdc", "title": "Bending the Curve: Improving the ROC Curve Through Error Redistribution", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.06652.pdf"], "doi": []}, {"id": "70918453e9f147747b7a37d9159c8c1515a55ae4", "title": "Visual object tracking via the local soft cosine similarity", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1016/j.patrec.2018.03.026"]}, {"id": "1876095a9387a84e594d81675c9c2c17cb10f7cf", "title": "Accurate segmentation of complex document image using digital shearlet transform with neutrosophic set as uncertainty handling tool", "year": "2017", "pdf": ["http://fs.gallup.unm.edu/neut/AccurateSegmentationOfComplex.pdf"], "doi": ["http://doi.org/10.1016/j.asoc.2017.08.005"]}, {"id": "ad52d047a44f20416f9dd6655cef54169d481454", "title": "Perceptual modeling in the problem of active object recognition in visual scenes", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1016/j.patcog.2016.03.007"]}, {"id": "e096b11b3988441c0995c13742ad188a80f2b461", "title": "DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers", "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.04702.pdf"], "doi": []}, {"id": "56e95fa26fb417776824e5adf6d6d511e5b30110", "title": "Object and Action Classification with Latent Window Parameters", "year": "2013", "pdf": ["http://homepages.inf.ed.ac.uk/hbilen/assets/pdf/Bilen14.pdf", "http://www.cse.iitk.ac.in/users/cs365/2014/_papers/bilen-namboodri-vanGool-13_object-action-classify-latent-windows.pdf", "http://www.cse.iitk.ac.in/users/vinaypn/papers/bilen2013ijcv.pdf"], "doi": ["http://doi.org/10.1007/s11263-013-0646-8"]}, {"id": "e7df750805d6c025d0a1a74a05a83bcf8cc63dd7", "title": "Assessment of crowdsourcing and gamification loss in user-assisted object segmentation", "year": "2015", "pdf": ["http://upcommons.upc.edu/bitstream/handle/2117/81293/asknseek.pdf;jsessionid=469B72384B7C56D4A331D68A53942294?sequence=1"], "doi": ["https://doi.org/10.1007/s11042-015-2897-6"]}, {"id": "85eedee59aca5f2a591265a2173cf3a2799cdc94", "title": "Action and Event Recognition with Fisher Vectors on a Compact Feature Set", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751336"]}, {"id": "3463aeda3a8d33bc88d8383cc4ad451a6775c75a", "title": "Understanding Indoor Scenes Using 3D Geometric Phrases", "year": "2013", "pdf": ["http://courses.cs.washington.edu/courses/cse590v/13au/choi_cvpr13.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989a033.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Choi_Understanding_Indoor_Scenes_2013_CVPR_paper.pdf", "https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/41340.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6618856", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.12", "http://doi.org/10.1109/CVPR.2013.12"]}, {"id": "70b420850e16ec2afe42d5c0006742d9045b3e7f", "title": "If You Can't Beat Them, Join Them: Learning with Noisy Data", "year": "2015", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2806231"]}, {"id": "985b6a10c1bb9c8908d6d299c7ab0bba76df2259", "title": "Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Bilinski_Dense_Decoder_Shortcut_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578788", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00690", "http://doi.org/10.1109/CVPR.2018.00690"]}, {"id": "82451d0ae2e0154b5f9cd096af199c35319e911a", "title": "Image spam filtering using convolutional neural networks", "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s00779-018-1168-8"]}, {"id": "8ff6294535acf46abf523b879f20685de0692a8c", "title": "Bayes Risk for Large Scale Hierarchical Top-K Image Classification", "year": "2013", "pdf": ["https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/153936/eth-6877-01.pdf?isAllowed=y&sequence=1"], "doi": ["https://doi.org/10.3929/ethz-a-009767867"]}, {"id": "d97224063697392f073e467005e89973d2be7d65", "title": "Recherche de motifs fr\u00e9quents dans une base de cartes combinatoires. (Frequent pattern discovery in combinatorial maps databases)", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/02d1/8e600804a1a6ff354856d8dcb80ceb4c8a43.pdf"], "doi": []}, {"id": "74a1336f1fbc8b7bb3b6e159711af1a91336ce22", "title": "An overview of traffic sign detection methods", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/74a1/336f1fbc8b7bb3b6e159711af1a91336ce22.pdf"], "doi": []}, {"id": "e33bc0cd79d92d6868989a29c3ab06b75f808590", "title": "Deep Nets: What have they ever done for Vision?", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04025.pdf"], "doi": []}, {"id": "0b4d3e59a0107f0dad22e74054bab1cf1ad9c32e", "title": "Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.07332.pdf"], "doi": []}, {"id": "14d1a458f49e251cbbab34349e379469300a2bae", "title": "Scene Parsing with Object Instances and Occlusion Ordering", "year": "2014", "pdf": ["http://slazebni.cs.illinois.edu/publications/jtighe-cvpr14.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Tighe_Scene_Parsing_with_2014_CVPR_paper.pdf", "http://wwwx.cs.unc.edu/~mn/sites/default/files/jtighe-cvpr14.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909874", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.479", "http://doi.org/10.1109/CVPR.2014.479"]}, {"id": "a6cd743c29667ab5baef9d66d6558247b1cd00b0", "title": "New in-situ training image and one-shot detection model without adaptation GENETIM detection model for synset bottle", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/a6cd/743c29667ab5baef9d66d6558247b1cd00b0.pdf"], "doi": []}, {"id": "9b8746e9480c3bdcaa6efca33096369422c624aa", "title": "Algae Detection Using Computer Vision and Deep Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10847.pdf"], "doi": []}, {"id": "3325860c0c82a93b2eac654f5324dd6a776f609e", "title": "2D Human Pose Estimation: New Benchmark and State of the Art Analysis", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909866"]}, {"id": "896e2776174dcb86d311789ab83a266151d0595b", "title": "A Novel Performance Evaluation Methodology for Single-Target Trackers", "year": "2016", "pdf": ["https://arxiv.org/pdf/1503.01313.pdf"], "doi": []}, {"id": "bf26ccc92bca086195c5f250aef2e409a1c7cd85", "title": "Local Bayes Risk Minimization Based Stopping Strategy for Hierarchical Classification", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8215524", "http://doi.ieeecomputersociety.org/10.1109/ICDM.2017.61", "http://doi.org/10.1109/ICDM.2017.61"]}, {"id": "ff3a9545e73adea5275a1c7c71c5e3fe2e35a9a1", "title": "An Enhanced Feature Extraction Technique for Diagnosis of Pathological Problems in Mango Crop", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ff3a/9545e73adea5275a1c7c71c5e3fe2e35a9a1.pdf"], "doi": []}, {"id": "21d1225296aad388406824eb113715c4b90ed3da", "title": "Dirichlet-Based Concentric Circle Feature Transform for Breast Mass Classification", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7372146", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2015.50", "http://doi.org/10.1109/ICTAI.2015.50"]}, {"id": "3f0b0ffe315ee111fc028561ec4ecf2c93f94a05", "title": "Pose Normalization Network for Object Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3f0b/0ffe315ee111fc028561ec4ecf2c93f94a05.pdf"], "doi": []}, {"id": "75b987f86af2bc7f68edc45be240dd30e1ef2699", "title": "Sampling Algorithms to Handle Nuisances in Large-Scale Recognition", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/75b9/87f86af2bc7f68edc45be240dd30e1ef2699.pdf"], "doi": []}, {"id": "6a405e7284ff7e2127a241d60646b4abd3da92f2", "title": "Generate To Adapt : Unsupervised Domain Adaptation using Generative Adversarial Networks", "year": "2017", "pdf": [], "doi": []}, {"id": "c0e551acb063c9cd73dea28ab8963f850b6f1148", "title": "A Comparison of Techniques based on Image Classification and Object Detection to Count Cars and Non-empty Stalls in Parking Spaces", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c0e5/51acb063c9cd73dea28ab8963f850b6f1148.pdf"], "doi": []}, {"id": "8b45a87f3dfc8eccd745161effbf2457a9097e6a", "title": "WEAKLY SUPERVISED SEMANTIC SEGMENTATION 3 priors can give good pixel labelling results", "year": "2017", "pdf": [], "doi": []}, {"id": "25d75339720787e7003f2f103cf38cee8175972a", "title": "Optimistic and Pessimistic Neural Networks for Scene and Object Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.07982.pdf"], "doi": []}, {"id": "12d9a4233a16ea08fbb1de853b6a97b4f4952c23", "title": "Tractable Structured Prediction using the Permutohedral Lattice", "year": "2017", "pdf": ["https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-01.pdf?isAllowed=y&sequence=1", "https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-02.pdf?isAllowed=y&sequence=2"], "doi": ["https://doi.org/10.3929/ethz-a-010882665"]}, {"id": "33d101fe276fd5e6220c9b40c33e1a1d1389e5bb", "title": "DOC: DEEP OCCLUSION ESTIMATION FROM A SIN-", "year": "2016", "pdf": [], "doi": []}, {"id": "c6c691b772822881c5c52b779100928f0d54fdd7", "title": "Using Visual Saliency to Improve Human Detection with Convolutional Networks", "year": "2018", "pdf": [], "doi": []}, {"id": "11a3084768f035c824662a85a348f02466693d2a", "title": "Lifting Object Detection Datasets into 3D", "year": "2016", "pdf": ["https://arxiv.org/pdf/1503.06465.pdf"], "doi": []}, {"id": "4be10db13a9210e078d78a4a072c569d9bbd9939", "title": "Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.06098.pdf"], "doi": []}, {"id": "18a849b1f336e3c3b7c0ee311c9ccde582d7214f", "title": "Efficiently Scaling Up Crowdsourced Video Annotation A Set of Best Practices for High Quality , Economical Video Labeling", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/18a8/49b1f336e3c3b7c0ee311c9ccde582d7214f.pdf"], "doi": []}, {"id": "13e424d502bf539108ad6f5cc877cfb1255dbee0", "title": "Improving Vision-Based Self-Positioning in Intelligent Transportation Systems via Integrated Lane and Vehicle Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7045914"]}, {"id": "1dbd7653ede6af15d539f64cb2128752ca029e44", "title": "Hollywood 3D: Recognizing Actions in 3D Natural Scenes", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619280"]}, {"id": "f4c45108cb41051010d8a5175b8da23eb246c967", "title": "Improving Image Captioning by Leveraging Knowledge Graphs", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8658870"]}, {"id": "1b3ee5455956a40c6e9e09ccda0f4fb162838629", "title": "The Recognition of License Plate Restrictions Based on Faster R-CNN", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1b3e/e5455956a40c6e9e09ccda0f4fb162838629.pdf"], "doi": []}, {"id": "5c45a1abc51fe059987bcfba19b1d5076a8d9afb", "title": "Autonomous Object Category Learning for Service Robots Using Internet Resources", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5c45/a1abc51fe059987bcfba19b1d5076a8d9afb.pdf"], "doi": []}, {"id": "4a31b3fcc346bf3235efe1c0fb310833570cef27", "title": "Learning Intelligent Dialogs for Bounding Box Annotation", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579054"]}, {"id": "ed62a56b81511d7fcf6d247014987163d9668982", "title": "\"What happens if...\" Learning to Predict the Effect of Forces in Images", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.05600.pdf"], "doi": []}, {"id": "29aa3dc15450e6eb46c34f30f0e224e5ea16615e", "title": "Sketch Me That Shoe", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Yu_Sketch_Me_That_CVPR_2016_paper.pdf", "http://vision.cs.utexas.edu/381V-fall2016/slides/hsiao_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Yu_Sketch_Me_That_CVPR_2016_paper.pdf", "https://www.eecs.qmul.ac.uk/~qian/SketchMeThatShoe.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780462", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.93", "http://doi.org/10.1109/CVPR.2016.93"]}, {"id": "1999d5e0700bf8fa50bb1bab5b981bda1d111a4f", "title": "Monocular Road Terrain Detection by Combining Visual and Spatial Information", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/73b1/10df4809d0a015f90fa6e7a7dce351bcc52e.pdf", "https://www.researchgate.net/profile/Jannik_Fritsch/publication/261073577_Monocular_Road_Terrain_Detection_by_Combining_Visual_and_Spatial_Information/links/5475ef240cf29afed612e5a8.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6766705", "http://doi.org/10.1109/TITS.2014.2303899"]}, {"id": "34072c31c2c778df471c9f0c43ba6198dfd0db32", "title": "Arbitrary Category Classification of Websites Based on Image Content", "year": "2015", "pdf": ["http://users.ics.aalto.fi/juha/papers/ELM2014.pdf", "http://www.engineering.uiowa.edu/sites/default/files/files/newpaper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7083681", "http://doi.org/10.1109/MCI.2015.2405317"]}, {"id": "d23ac99cdab20a9a3eca2784a5b262649c717988", "title": "Rotation Invariant Angular Descriptor Via A Bandlimited Gaussian-like Kernel", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.02753.pdf"], "doi": []}, {"id": "22cf367d14e646914cc959bbcd402df0c20cd0dc", "title": "Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.04024.pdf"], "doi": []}, {"id": "c9d73438bf5e66bd0c4f512c5a4e53c3e33e721e", "title": "Adding spatial distribution clue to aggregated vector in image retrieval", "year": "2018", "pdf": ["https://jivp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13640-018-0247-0?site=jivp-eurasipjournals.springeropen.com"], "doi": ["http://doi.org/10.1186/s13640-018-0247-0"]}, {"id": "a74b045f28670e8f85173e0e483581520d667f02", "title": "Object tracking using Langevin Monte Carlo particle filter and locality sensitive histogram based likelihood model", "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1016/j.cag.2017.07.023"]}, {"id": "c56da136b8d62125009a131f6dc21fcd0dd6a559", "title": "ICDAR2017 Robust Reading Challenge on Text Extraction from Biomedical Literature Figures (DeTEXT)", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8270166", "http://doi.ieeecomputersociety.org/10.1109/ICDAR.2017.235", "http://doi.org/10.1109/ICDAR.2017.235"]}, {"id": "02e5372e439c09f8a8ce8c4784b044ce116ca11c", "title": "DeepCorrect: Correcting DNN models against Image Distortions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02406.pdf"], "doi": []}, {"id": "e8b2a98f87b7b2593b4a046464c1ec63bfd13b51", "title": "CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.05413.pdf"], "doi": []}, {"id": "5fdbebf417da2427744d2c60f413b5375e68993e", "title": "Discriminative Sub-categorization", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619062"]}, {"id": "32bebe84ffbd4fd81f0e5bb30dbc90774aa3b14b", "title": "Segmentation Results Stimuli Final Saliency Map Ground Truth Constructed Graph CCA", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/32be/be84ffbd4fd81f0e5bb30dbc90774aa3b14b.pdf"], "doi": []}, {"id": "a02e5d8e2a10176dc5e2566e1b492823a0cb6ee2", "title": "A learning framework for higher-order consistency models in multi-class pixel labeling problems", "year": "2014", "pdf": [], "doi": []}, {"id": "383d64b27fb3cdf2beff43f3beb8caac8c21a886", "title": "Detecting activities of daily living in first-person camera views", "year": "2012", "pdf": ["http://people.csail.mit.edu/hpirsiav/papers/adl_cvpr12.pdf", "http://people.csail.mit.edu/hpirsiav/papers/adl_cvpr12_poster.pdf", "http://people.csail.mit.edu/hpirsiav/papers/adl_cvpr12_slides.pdf", "http://vision.ics.uci.edu/papers/PirsiavashR_CVPR_2012_1/PirsiavashR_CVPR_2012_1.pdf", "http://web.cs.hacettepe.edu.tr/~erkut/bil722.f12/w06-cagdas.pdf", "http://www.cs.utexas.edu/~cv-fall2012/slides/dinesh-expt.pdf", "http://www.ics.uci.edu/~dramanan/papers/ADL_2012.pdf", "https://www.cs.cmu.edu/~deva/papers/ADL_2012.pdf", "https://www.csee.umbc.edu/~hpirsiav/papers/adl_cvpr12.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6248010", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2012.6248010", "http://doi.org/10.1109/CVPR.2012.6248010"]}, {"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"], "doi": []}, {"id": "64c1158a4061882d610f1cffd5ddb1e8fc9a74b4", "title": "Gated Feedback Refinement Network for Dense Image Labeling", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Islam_Gated_Feedback_Refinement_CVPR_2017_paper.pdf", "http://www.cs.umanitoba.ca/~ywang/papers/cvpr17.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100001", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.518", "http://doi.org/10.1109/CVPR.2017.518"]}, {"id": "284be8be0c6bedc36dfe43229bc84345ab0aedc2", "title": "Faster Training of Mask R-CNN by Focusing on Instance Boundaries", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07069.pdf"], "doi": []}, {"id": "be2d326fa588b4ffd1d8d3d4408ae680e1a26277", "title": "JOURNA A Survey on Modern Era \u2019 s Online Object Tracking Algorithms", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/be2d/326fa588b4ffd1d8d3d4408ae680e1a26277.pdf"], "doi": []}, {"id": "2a2232f2972191a0606d588aa4f13c9f27d1972d", "title": "InstanceCut: From Edges to Instances with MultiCut", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.08272.pdf"], "doi": []}, {"id": "029cabb6f3f6a824590e735feb1d8557646db8a6", "title": "One-Bit Object Detection: On learning to localize objects with minimal supervision", "year": "2014", "pdf": ["https://arxiv.org/pdf/1403.1024.pdf"], "doi": []}, {"id": "fd23dda0abe2d6a3ae0c8253c89110364cdecbc9", "title": "Deep Learning for People Detection on Beach Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575616", "http://doi.ieeecomputersociety.org/10.1109/BRACIS.2018.00045", "http://doi.org/10.1109/BRACIS.2018.00045"]}, {"id": "c3c4f0caf1b42b6466306360c4ebe16f66489df0", "title": "Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.11266.pdf"], "doi": []}, {"id": "03fd6774f57aaed9320060e4527121c59e9eca2b", "title": "Intrinsic spatial pyramid matching for deformable 3D shape retrieval", "year": "2013", "pdf": [], "doi": ["https://doi.org/10.1007/s13735-013-0041-9"]}, {"id": "304aa9bfd6bc32d3d87abce6a229d973270bbd73", "title": "Fast Neural Cell Detection Using Light-Weight SSD Neural Network", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w8/papers/Yi_Fast_Neural_Cell_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8014853", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.119", "http://doi.org/10.1109/CVPRW.2017.119"]}, {"id": "c8ba499e8d8daa32637885f03137f41d61023bf9", "title": "Weak supervision for detecting object classes from activities", "year": "2017", "pdf": ["https://ps.is.tue.mpg.de/uploads_file/attachment/attachment/296/weak_supervision_object_detection.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2016.09.006"]}, {"id": "cd1a636c1261208084cb8395c877c7ca22c76df1", "title": "Fast Deep Vehicle Detection in Aerial Images", "year": "2017", "pdf": ["https://www.computer.org/csdl/proceedings/wacv/2017/4822/00/07926624.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7926624", "http://doi.org/10.1109/WACV.2017.41"]}, {"id": "101c7305f141145c4d168dfa40284e0ad86a0d9b", "title": "Active Object Localization with Deep Reinforcement Learning", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410643"]}, {"id": "48922520e6de0954a83f26977b2b50b7fbfdcf61", "title": "A survey of sketch-based image retrieval", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s00138-018-0953-8"]}, {"id": "c37fe13f94dfc2f3494a35a63336689ce4392135", "title": "MPNET: An End-to-End Deep Neural Network for Object Detection in Surveillance Video", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8365094", "http://doi.org/10.1109/ACCESS.2018.2836921"]}, {"id": "0f8f9253c81fd90fe44d474cc185d4ae2487e5b4", "title": "NYC3DCars: A Dataset of 3D Vehicles in Geographic Context", "year": "2013", "pdf": ["http://nyc3d.cs.cornell.edu/static/paper.pdf", "http://www.cs.cornell.edu/~snavely/publications/papers/nyc3dcars_iccv13.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Matzen_NYC3DCars_A_Dataset_2013_ICCV_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751204", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.99", "http://doi.org/10.1109/ICCV.2013.99"]}, {"id": "e8ffef3d4d74720e766e506e175e533bdc8ee705", "title": "Object Detection Networks on Convolutional Feature Maps", "year": "2017", "pdf": ["https://arxiv.org/pdf/1504.06066.pdf"], "doi": []}, {"id": "1daf971c087f5e21dbae831231377cbe9bb2f188", "title": "Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619272"]}, {"id": "8d74fbd46f9d5d615e350c4593cbc5b5ca63fa8b", "title": "Data driven visual tracking via representation learning and online multi-class LPBoost learning", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1049/iet-cvi.2014.0388"]}, {"id": "7af667b6c1b4b32f513dd70fe3ef36fcf344a741", "title": "A transfer learning based approach for automated grading of Gliomas using deep Residual Networks", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/7af6/67b6c1b4b32f513dd70fe3ef36fcf344a741.pdf"], "doi": []}, {"id": "d9dafc343727db2b6060c868d748f97eff6bac7d", "title": "Improved pedestrian detection using motion segmentation and silhouette orientation", "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-017-4933-1"]}, {"id": "3b304585d5af0afe98a85d6e0559315fbf3a7807", "title": "An Improved Labelling for the INRIA Person Data Set for Pedestrian Detection", "year": "2013", "pdf": ["http://welcome.isr.ist.utl.pt/img/pdfs/2999_2013_IbPRIA_Taiana_Nascimento_Bernardino.pdf", "http://welcome.isr.tecnico.ulisboa.pt/wp-content/uploads/2015/05/2999_2013_IbPRIA_Taiana_Nascimento_Bernardino.pdf"], "doi": ["http://doi.org/10.1007/978-3-642-38628-2_34"]}, {"id": "99df9e95b3f3d187636918a65277baf7c98cbfc5", "title": "An efficient subsequence search for video anomaly detection and localization", "year": "2015", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-015-2453-4", "https://www.wikidata.org/entity/Q56907428"]}, {"id": "832246357de85108cb910e773c203997448c570a", "title": "Recurrently Target-Attending Tracking", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780530"]}, {"id": "74031f12dde0be772a742b96bf5f4c8d9fa41ec7", "title": "Joint Object-Material Category Segmentation from Audio-Visual Cues", "year": "2015", "pdf": ["https://arxiv.org/pdf/1601.02220.pdf"], "doi": []}, {"id": "9452d029f5d140aece06619b6fd8e47b070cacd1", "title": "Urban classification by pixel and object-based approaches for very high resolution imagery", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9452/d029f5d140aece06619b6fd8e47b070cacd1.pdf"], "doi": []}, {"id": "7268747251a61d1ce3285baade15c372d4c566d6", "title": "Person Attribute Recognition with a Jointly-Trained Holistic CNN Model", "year": "2015", "pdf": ["http://web-info8.informatik.rwth-aachen.de/media/papers/sudowe_spitzer_leibe_ICCV_LaP_2015.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w11/papers/Sudowe_Person_Attribute_Recognition_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7406400", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2015.51", "http://doi.org/10.1109/ICCVW.2015.51"]}, {"id": "81763bb718dc6630be210c056a250b1c2ed57fd7", "title": "3D Semantic Parsing of Large-Scale Indoor Spaces", "year": "2016", "pdf": ["http://buildingparser.stanford.edu/images/CVPR_2016_poster.pdf", "http://buildingparser.stanford.edu/images/supp_mat.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/papers/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780539", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.170", "http://doi.org/10.1109/CVPR.2016.170"]}, {"id": "9d5db7427b44d83bf036ff4cff382c23c6c7b6d8", "title": "Video redaction: a survey and comparison of enabling technologies", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f78d/6d092deaafee550fb58d6ea6e8b559325876.pdf"], "doi": []}, {"id": "a228ba020bd321d29ab24485cb2988a62707fd64", "title": "Using objective ground-truth labels created by multiple annotators for improved video classification: A comparative study", "year": "2013", "pdf": ["https://engineering.purdue.edu/RVL/Publications/Srivastava2013.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2013.06.009"]}, {"id": "037f2e9d2d2aa15c3d476f4aa358da96707b4b44", "title": "Square Localization for Efficient and Accurate Object Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410651"]}, {"id": "bf3aae7293f664d512c0904916d804327af22f52", "title": "STDnet: A ConvNet for Small Target Detection", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bf3a/ae7293f664d512c0904916d804327af22f52.pdf"], "doi": []}, {"id": "d6b514a68abff3ab14af9fc0152cd5b28bd0192c", "title": "Instance Segmentation by Deep Coloring", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.10007.pdf"], "doi": []}, {"id": "0de46e6768acaa71745406d646573644b975dc62", "title": "Scene-Domain Active Part Models for Object Representation", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410644"]}, {"id": "e24792ec2a6cb8971b2f6befb4b97b9fe2d79952", "title": "Bottom-up Object Detection by Grouping Extreme and Center Points", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08043.pdf"], "doi": []}, {"id": "1d7029a974f950de61f3980704956b43f1a06e7b", "title": "Efficient Optimization for Rank-Based Loss Functions", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578487"]}, {"id": "22a8b7ca2e6449cad31ae4f71bb3587751087e77", "title": "DeepBox: Learning Objectness with Convolutional Networks", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410642"]}, {"id": "9c4365a56fb3cf41b15712657b15f7422ca0dab2", "title": "A Hybrid Supervised-Unsupervised Vocabulary Generation Algorithm for Visual Concept Recognition", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/9c43/65a56fb3cf41b15712657b15f7422ca0dab2.pdf"], "doi": []}, {"id": "37b9ea1bf5b6ce8ecb656628af3933c64c632c2b", "title": "Transfer Learning for 3 D LiDAR-based Human Classification with a Mobile Robot", "year": "2018", "pdf": [], "doi": []}, {"id": "f79c4bf83371627ba139b61eb427463b93cd687b", "title": "Learning from Few Examples for Visual Recognition Problems", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/f79c/4bf83371627ba139b61eb427463b93cd687b.pdf"], "doi": []}, {"id": "084bd219dd239dc4c9a02621a5333d3bc1446566", "title": "DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking", "year": "2015", "pdf": ["https://arxiv.org/pdf/1503.00072.pdf"], "doi": []}, {"id": "1c9da6cef6b1be9c116b26dd52c341c0adcf7db2", "title": "Interactive Perception: Leveraging Action in Perception and Perception in Action", "year": "2017", "pdf": ["https://arxiv.org/pdf/1604.03670.pdf"], "doi": []}, {"id": "549c719c4429812dff4d02753d2db11dd490b2ae", "title": "YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00824.pdf"], "doi": []}, {"id": "e430d1ae3a28ec342f767cdfb19aeb76c20a3f21", "title": "Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8592805"]}, {"id": "3b4ad6b789837a6a878f33c0b7ddb1b1fc7daaf8", "title": "Fine-grained recognition of plants from images", "year": "2017", "pdf": ["https://plantmethods.biomedcentral.com/track/pdf/10.1186/s13007-017-0265-4?site=plantmethods.biomedcentral.com"], "doi": ["https://doi.org/10.1186/s13007-017-0265-4", "https://www.ncbi.nlm.nih.gov/pubmed/29299049"]}, {"id": "f92ceb6875f614bbccb25e4b11ca55353773890f", "title": "Saliency Detection via Boundary Prior and Center Prior", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f92c/eb6875f614bbccb25e4b11ca55353773890f.pdf"], "doi": []}, {"id": "828b73e8a4d539eeae82601b5f5a4392818c6430", "title": "Long-Term Tracking by Decision Making", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/828b/73e8a4d539eeae82601b5f5a4392818c6430.pdf"], "doi": []}, {"id": "2114b25727a21275e88e30dad0423752f6047dae", "title": "Generic Visual Recognition on Non-Uniform Distributions Based on AdaBoost Codebooks", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/cac0/c534e02784a3a873690d213dd8c92b81992f.pdf"], "doi": []}, {"id": "7cb4d30b3bfb0d4b02499c15c7c7a9dfddda8049", "title": "Object Tracking using L 1 / L 2 Sparse Coding and Multi Scale Max Pooling", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/7cb4/d30b3bfb0d4b02499c15c7c7a9dfddda8049.pdf"], "doi": []}, {"id": "b7efecec654acd8831d045e728b54356c697c9c8", "title": "Learning Semantic Segmentation with Diverse Supervision", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354268"]}, {"id": "eacb95e81156c48f4ff7470567ba205225170fa7", "title": "Learning Aerial Image Segmentation From Online Maps", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06879.pdf"], "doi": []}, {"id": "14b311b848b51b7b5345573a289b1cedcbb4d581", "title": "Instance Similarity Deep Hashing for Multi-Label Image Retrieval", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02987.pdf"], "doi": []}, {"id": "24ff832171cb774087a614152c21f54589bf7523", "title": "Beat-Event Detection in Action Movie Franchises", "year": "2015", "pdf": ["https://arxiv.org/pdf/1508.03755.pdf"], "doi": []}, {"id": "ffd73d1956163a4160ec2c96b3ab256f79fc92e8", "title": "Attributes as Semantic Units between Natural Language and Visual Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03249.pdf"], "doi": []}, {"id": "99c37dba394b100ba8f3d895c0ee0e57d5852347", "title": "Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects", "year": "2014", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2014/papers/Zia_Are_Cars_Just_2014_CVPR_paper.pdf", "http://resources.mpi-inf.mpg.de/publications/D2/2014/zia14cvpr.pdf", "http://www.igp.ethz.ch/photogrammetry/publications/pdf_folder/cvpr2014zz.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909865", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.470", "http://doi.org/10.1109/CVPR.2014.470"]}, {"id": "f6b649023e49a341f042f9a17b2f923db58ccf35", "title": "Feature representation of RGB-D images using joint spatial-depth feature pooling", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1016/j.patrec.2016.04.001"]}, {"id": "f9f86d087e84eaf0e6a09575982aa7b41fa62451", "title": "Image Synthesis for Self-Supervised Visual Representation Learning", "year": "2018", "pdf": [], "doi": ["https://www.base-search.net/Record/6ecfef13a126fd20b941bbb80477b94bd643db70d224a43b1d0b0cb61aa181b1"]}, {"id": "b85c198ce09ffc4037582a544c7ffb6ebaeff198", "title": "Efficient Multiple Instance Metric Learning Using Weakly Supervised Data", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Law_Efficient_Multiple_Instance_CVPR_2017_paper.pdf", "http://www.cs.toronto.edu/~law/publications/CVPR/2017/mimlca_cvpr_2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100113", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.630", "http://doi.org/10.1109/CVPR.2017.630"]}, {"id": "c77c094faf7b1a4e293609a0909c7c50b468675a", "title": "Satyam: Democratizing Groundtruth for Machine Vision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.03621.pdf"], "doi": []}, {"id": "2a5667702b0f1ff77dde8fb3e2e10d4e05e8de9d", "title": "Scene Parsing through ADE20K Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhou_Scene_Parsing_Through_CVPR_2017_paper.pdf", "http://people.csail.mit.edu/bzhou/publication/scene-parse-camera-ready.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100027", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.544", "http://doi.org/10.1109/CVPR.2017.544"]}, {"id": "a422c2bd9030c8a2c89b6db79be2743c4a4609fb", "title": "Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02886.pdf"], "doi": []}, {"id": "46a1172c784c3741e79781ef2353209b08dbea67", "title": "YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shot Recognition", "year": "2013", "pdf": ["http://www.cs.utexas.edu/users/ml/papers/guadarrama.iccv13.pdf", "http://www.cs.utexas.edu/users/ml/posters/guadarrama.iccv13.pdf", "http://www.eecs.berkeley.edu/~sguada/pdfs/2013-ICCV-YouTube2Text-final.pdf", "https://www.cs.utexas.edu/~vsub/pdf/YouTube2Text_Recognizing_and_2013_ICCV_paper.pdf", "https://www.icsi.berkeley.edu/pubs/vision/youtube2text13.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751448", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.337", "http://doi.org/10.1109/ICCV.2013.337"]}, {"id": "670b10569c5f978ee70d99cf8c14ad9cabb9d454", "title": "Masked face detection via a modified LeNet", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1016/j.neucom.2016.08.056"]}, {"id": "4acf31294e940d85a4eea56c244205e3a66d8b8e", "title": "Improving Product Classification Using Images", "year": "2011", "pdf": ["http://talukdar.net/papers/ImageText-ICDM2011.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6137235", "http://doi.ieeecomputersociety.org/10.1109/ICDM.2011.79", "http://doi.org/10.1109/ICDM.2011.79"]}, {"id": "057f5ffda59a3412f1e62159e96f84faa352628e", "title": "Tracking with scattering descriptor", "year": "2014", "pdf": [], "doi": ["http://doi.org/10.1049/iet-cvi.2013.0124"]}, {"id": "4404a99e2f6db3e703609168a3595e0fbdeabc38", "title": "Online Video SEEDS for Temporal Window Objectness", "year": "2013", "pdf": ["http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Van_Den_Bergh_Online_Video_SEEDS_2013_ICCV_paper.pdf", "http://www.mvdblive.org/research/videoseeds.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01056.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751156", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.54", "http://doi.org/10.1109/ICCV.2013.54"]}, {"id": "59ee0f67bcf2d8ea0bbbfcbc71159725fc3a7059", "title": "Object Detection with Appearance-based Mixture Models Anonymous CVPR submission", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/59ee/0f67bcf2d8ea0bbbfcbc71159725fc3a7059.pdf"], "doi": []}, {"id": "e478c322de923337627487d8a688f5922b45b2ff", "title": "Automatic Garage Door Opening Using License Plate Recognition and Fingerprint Verification", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/e478/c322de923337627487d8a688f5922b45b2ff.pdf"], "doi": []}, {"id": "8a3b481d8e06b4acf6e95d8bc2484016f5862668", "title": "Text Detection in Traffic Informatory Signs Using Synthetic Data", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8270075", "http://doi.ieeecomputersociety.org/10.1109/ICDAR.2017.144", "http://doi.org/10.1109/ICDAR.2017.144"]}, {"id": "7c594c0b9482624745dd95767f3eebde1ee7f043", "title": "Representing Visual Scenes for Robot Control", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/7c59/4c0b9482624745dd95767f3eebde1ee7f043.pdf"], "doi": []}, {"id": "0ceda9dae8b9f322df65ca2ef02caca9758aec6f", "title": "Context-Aware CNNs for Person Head Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410688"]}, {"id": "5f0e9cc18374a670dfea4698424c9d48494f3093", "title": "Online Domain Adaptation for Multi-Object Tracking", "year": "2015", "pdf": ["https://arxiv.org/pdf/1508.00776.pdf"], "doi": []}, {"id": "d47d72afc590f5b96117a5227d45157135da21ad", "title": "Attribute-based knowledge transfer learning for human pose estimation", "year": "2013", "pdf": [], "doi": ["http://doi.org/10.1016/j.neucom.2012.05.032"]}, {"id": "05db46c7745c360fa5938ee204c81efdcc84c1da", "title": "An Empirical Evaluation of Current Convolutional Architectures\u2019 Ability to Manage Nuisance Location and Scale Variability", "year": "2016", "pdf": ["https://arxiv.org/pdf/1505.06795.pdf"], "doi": []}, {"id": "0d4cdadd765c3003b0bd5f762b84bef93408f548", "title": "Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909618"]}, {"id": "5d16ce0c66cd87dd48cb8c53f5b6a7ee73d33abb", "title": "Robust and Real-Time Object Tracking Using Scale-Adaptive Correlation Filters", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7797075", "http://doi.org/10.1109/DICTA.2016.7797075"]}, {"id": "050e5b4043009e54dff9319877fe947885db2d6e", "title": "Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Lai_Saliency_Guided_Dictionary_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Lai_Saliency_Guided_Dictionary_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780764", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.395", "http://doi.org/10.1109/CVPR.2016.395"]}, {"id": "926dd1c4db38356ac5bf87c1a4c6b93625f9a850", "title": "Pulling Actions out of Context: Explicit Separation for Effective Combination", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578834"]}, {"id": "b705ca751a947e3b761e2305b41891051525d9df", "title": "Exploring Context with Deep Structured Models for Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1603.03183.pdf"], "doi": []}, {"id": "be48b5dcd10ab834cd68d5b2a24187180e2b408f", "title": "Constrained Low-Rank Learning Using Least Squares-Based Regularization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.04870.pdf"], "doi": []}, {"id": "b2f63863e73a8565895ca3d9d7d6a1e10a7695b1", "title": "Efficient Neural Network Compression via Transfer Learning for Industrial Optical Inspection", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b2f6/3863e73a8565895ca3d9d7d6a1e10a7695b1.pdf"], "doi": []}, {"id": "044ae9738c2445d4fda30fcd6c289eddf8b3add9", "title": "Multiple Instance Learning: A Survey of Problem Characteristics and Applications", "year": "2018", "pdf": ["https://arxiv.org/pdf/1612.03365.pdf"], "doi": []}, {"id": "2ba540ca70c7dee81e13768792aa7571952987f6", "title": "Drivable Road Detection Based on Dilated FPN with Feature Aggregation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8372075", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2017.00172", "http://doi.org/10.1109/ICTAI.2017.00172"]}, {"id": "6c9f45c76b4f96fe66d8e1d7b31f89b7cc6caa44", "title": "DeNet: Scalable Real-Time Object Detection with Directed Sparse Sampling", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.10295.pdf"], "doi": []}, {"id": "a0ae4ffe252f32514240cf6d82d52538de5fb78c", "title": "AN ALGORITHM FOR PEDESTRIAN DETECTION IN MULTISPECTRAL IMAGE SEQUENCES", "year": "", "pdf": ["https://pdfs.semanticscholar.org/a0ae/4ffe252f32514240cf6d82d52538de5fb78c.pdf"], "doi": []}, {"id": "115e8a4f76a57b893c985ea4f7530b90d071679c", "title": "FSSD: Feature Fusion Single Shot Multibox Detector", "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.00960.pdf"], "doi": []}, {"id": "92f2639dbd9f7c4284b7012809e4d2c407834774", "title": "Point-based Medialness 2 D Shape Description and Identification", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/92f2/639dbd9f7c4284b7012809e4d2c407834774.pdf"], "doi": []}, {"id": "4ace7c8edd9467c7d5bfa00e942531e7b889e650", "title": "Depth-Based Hand Pose Estimation: Data, Methods, and Challenges", "year": "2015", "pdf": ["http://vision.ics.uci.edu/papers/SupancicRYSR_ICCV_2015/SupancicRYSR_ICCV_2015.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Supancic_Depth-Based_Hand_Pose_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410574", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.217", "http://doi.org/10.1109/ICCV.2015.217"]}, {"id": "4c454fda214e00c9cba4bb759da78949a4130873", "title": "Specialization of a Generic Pedestrian Detector to a Specific Traffic Scene by the Sequential Monte-Carlo Filter and the Faster R-CNN", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/4c45/4fda214e00c9cba4bb759da78949a4130873.pdf"], "doi": []}, {"id": "f541dac9d0d49cadb3cfd018e87b26e03e3f13aa", "title": "Trio Constrained Adaptive Noise Removal ( TCANR ) Mechanism for Salt and Pepper Noise in Image Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f541/dac9d0d49cadb3cfd018e87b26e03e3f13aa.pdf"], "doi": []}, {"id": "aa2ad3df24d8d8c4a4d2fe85f0d4e635d595f0a2", "title": "PedCut: an iterative framework for pedestrian segmentation combining shape models and multiple data cues", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/c029/edca476ddda4050c3c67748056c6189cd1e3.pdf"], "doi": []}, {"id": "d250e57f6b7e06bb1dac41c8b89700086a85999e", "title": "Self-Supervised Generalisation with Meta Auxiliary Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08933.pdf"], "doi": []}, {"id": "de35ea60396629b2d1ceb73df56a97ed21012680", "title": "Robust object tracking via multi-scale patch based sparse coding histogram", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-016-3289-2"]}, {"id": "a0e286f3c6a72c857ffd03bd8ab9a9f9b98c4432", "title": "AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04452.pdf"], "doi": []}, {"id": "19339e816d8006ad462868b01812b03eb463ead1", "title": "Collective activity localization by spatiality preservation search", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1080/01691864.2016.1172506", "https://www.wikidata.org/entity/Q58025855"]}, {"id": "899e7ff67aa2630edc8776758cc5d65823f099c1", "title": "G-CNN: Object Detection via Grid Convolutional Neural Network", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8097417", "http://doi.org/10.1109/ACCESS.2017.2770178"]}, {"id": "139ab79a0aae5d4346f907b7b29288d09ef373fa", "title": "A Baseline for Multi-Label Image Classification Using Ensemble Deep CNN", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08412.pdf"], "doi": []}, {"id": "94780b00dc2807ec507ae91500b622ec7a8ddb12", "title": "Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.06295.pdf"], "doi": []}, {"id": "fa496716a5b8520e94a0126b5baa4f636623c997", "title": "Revisiting Knowledge Transfer for Training Object Class Detectors", "year": "2018", "pdf": ["https://arxiv.org/pdf/1708.06128.pdf"], "doi": []}, {"id": "c2cb4da617168c76c4560a01de8b5e68b5250749", "title": "FineTag: Multi-attribute Classification at Fine-grained Level in Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.07124.pdf"], "doi": []}, {"id": "87d5b53580ca5f77ccc3ff157337ef3456308943", "title": "Augmented Autoencoders for object orientation estimation trained on synthetic RGB images", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/87d5/b53580ca5f77ccc3ff157337ef3456308943.pdf"], "doi": []}, {"id": "eb2333a759788903848c49111a03c4c00d188e70", "title": "Color-based and Rotation Invariant Self-similarities", "year": "2017", "pdf": ["http://www.scitepress.org/Papers/2017/61075/61075.pdf"], "doi": ["https://doi.org/10.5220/0006107503440351"]}, {"id": "af9cc1767f50f63291d7ca9ab709f6849cd1e46c", "title": "Graph-Driven Diffusion and Random Walk Schemes for Image Segmentation.", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/af9c/c1767f50f63291d7ca9ab709f6849cd1e46c.pdf"], "doi": []}, {"id": "4fe91feab83d947a0d3bd85adcf18ab1b3d9e05f", "title": "Transductive People Tracking in Unconstrained Surveillance", "year": "2016", "pdf": ["http://imagelab.ing.unimore.it/Pubblicazioni/pubblicazioni/2015TCSVT.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7067436", "http://doi.org/10.1109/TCSVT.2015.2416555"]}, {"id": "8eaade06b75dac977574d05ce1058b86df059d47", "title": "Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation", "year": "2014", "pdf": ["http://people.eecs.berkeley.edu/~sgupta/pdf/ijcv14a.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0777-6"]}, {"id": "b9b21cfa7de32677151571ab44d27d2d246b7a03", "title": "Towards Explanation of DNN-based Prediction with Guided Feature Inversion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00506.pdf"], "doi": []}, {"id": "4152d2c8585f7e3f85d3b3d84036171de104cbd7", "title": "Rethinking ImageNet Pre-training", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08883.pdf"], "doi": []}, {"id": "b31f37fd71b7b45e6fd8978960e271a7db1ee212", "title": "DICTING IMAGE ROTATIONS", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b31f/37fd71b7b45e6fd8978960e271a7db1ee212.pdf"], "doi": []}, {"id": "149f3cc167b046dc790b1f4f1c48eeb31e898403", "title": "A study of vehicle detector generalization on U.S. highway", "year": "2016", "pdf": ["http://cvrr.ucsd.edu/publications/2016/0669.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7795567", "http://doi.org/10.1109/ITSC.2016.7795567"]}, {"id": "1a1654456decd116f4ca84c98006dfda0a8a3134", "title": "INTEGRATED VISUAL INFORMATION FOR MARITIME SURVEILLANCE", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1a16/54456decd116f4ca84c98006dfda0a8a3134.pdf"], "doi": []}, {"id": "3e00dd86c084d8680409c65c1a48f1b3aa864eb7", "title": "Deep Crisp Boundaries: From Boundaries to Higher-Level Tasks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1801.02439.pdf"], "doi": []}, {"id": "1e5edbd39b4c61f785515e117a74e2d280aefbe7", "title": "The urrent tate and TRL ssessment of eople racking echnology for ideo urveillance pplications", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1e5e/dbd39b4c61f785515e117a74e2d280aefbe7.pdf"], "doi": []}, {"id": "2e1f0b522014c942197e51b556eeb48b6ad66cda", "title": "Automatic object classification using motion blob based local feature fusion for traffic scene surveillance", "year": "2012", "pdf": [], "doi": ["http://doi.org/10.1007/s11704-012-1296-7"]}, {"id": "25858dc59faf2630bf0eefe23297ce262370cff0", "title": "Monitoring Giraffe Behavior in Thermal Video", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7046812"]}, {"id": "e545f1c06799bfd2bd5f7eaed085fd60a388202f", "title": "A top-down manner-based DCNN architecture for semantic image segmentation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/e545/f1c06799bfd2bd5f7eaed085fd60a388202f.pdf"], "doi": []}, {"id": "7b3a63d030d03e536ddcbc217bc8d6fd630e3b53", "title": "xView: Objects in Context in Overhead Imagery", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.07856.pdf"], "doi": []}, {"id": "4a6049e1926cc8e574301cfb229599cdc0a64e62", "title": "Characterizing the performance of an image-based recognizer for planar mechanical linkages in textbook graphics and hand-drawn sketches", "year": "2015", "pdf": ["http://vdel.me.cmu.edu/publications/2015cag/paper.pdf"], "doi": ["http://doi.org/10.1016/j.cag.2015.06.002"]}, {"id": "ec6f1a4b9367675833f0111c44a22ba217fcbd23", "title": "Visual Tracking via Constrained Incremental Non-negative Matrix Factorization", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7045563", "http://doi.org/10.1109/LSP.2015.2404856"]}, {"id": "5950512e21114236208b9eaeebc9a09735e367a6", "title": "Master research Internship Internship report Segmentation and recognition of symbols for printed and handwritten music scores", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5950/512e21114236208b9eaeebc9a09735e367a6.pdf"], "doi": []}, {"id": "c7780cff11068fecb322a43e459c56267a88aee7", "title": "DeepVoting: An Explainable Framework for Semantic Part Detection under Partial Occlusion", "year": "2017", "pdf": [], "doi": []}, {"id": "98bf42055160845e6f8f3c022298e3b8e4e55f80", "title": "Vision Meets Drones: A Challenge", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.07437.pdf"], "doi": []}, {"id": "19b6b0649cc669791c799c52fc56bdc556f06916", "title": "Efficient Model Evaluation with Bilinear Separation Model", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7045964"]}, {"id": "cf58f90e14b49ce35548d89c7339b7fc4db9ba4f", "title": "Generating Diverse Image Datasets with Limited Labeling", "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2967285"]}, {"id": "4ff486644be5e451784d6ae83f8073c8320fa974", "title": "Visual Tracking with Convolutional Neural Network", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7379494", "http://doi.org/10.1109/SMC.2015.362"]}, {"id": "a43f460f6c1abbe8eb0097594df6eafc0f651d49", "title": "Saliency-based object recognition in video", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a43f/460f6c1abbe8eb0097594df6eafc0f651d49.pdf"], "doi": []}, {"id": "b4df58f1fd8a3bd0815e7fb957f7f07fddd77338", "title": "Rethinking the sGLOH Descriptor", "year": "2018", "pdf": ["http://cvg.dsi.unifi.it/colombo_now/CC/Public/sGLOH2_TPAMI_2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7911291", "http://doi.org/10.1109/TPAMI.2017.2697849", "https://www.ncbi.nlm.nih.gov/pubmed/28459683", "https://www.wikidata.org/entity/Q38811217"]}, {"id": "ceee9ba72a021ae5604db04a93fdcff421d60216", "title": "Encoder Based Lifelong Learning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.01920.pdf"], "doi": []}, {"id": "c4a0e89793961dc486964802df55ae73fbba60ee", "title": "Soccer: Who Has the Ball? Generating Visual Analytics and Player Statistics", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w34/Theagarajan_Soccer_Who_Has_CVPR_2018_paper.pdf", "http://vislab.ucr.edu/PUBLICATIONS/pubs/Journal%20and%20Conference%20Papers/after10-1-1997/Conference/2018/FINAL-published-soccer-ball-generating.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575390", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00227", "http://doi.org/10.1109/CVPRW.2018.00227"]}, {"id": "2622d2467f19bc60427f8ea495515e7da82316c9", "title": "Tell Me Where to Look: Guided Attention Inference Network", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579058"]}, {"id": "ccee8af5667d1d3bccf30baf2c6f049f031bb5ad", "title": "Mixing Hierarchical Contexts for Object Recognition", "year": "2011", "pdf": ["http://web.ing.puc.cl/~asoto/papers/Peralta-2011.pdf"], "doi": ["https://doi.org/10.1007/978-3-642-25085-9_27"]}, {"id": "c96f012f4915398259e7e223810c57898b5e1a76", "title": "Fast LIDAR-based Road Detection Using Convolutional Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c96f/012f4915398259e7e223810c57898b5e1a76.pdf"], "doi": []}, {"id": "7142e659d6466717cdb8a242d8e34fce176b3f4a", "title": "Improved scene identification and object detection on egocentric vision of daily activities", "year": "2017", "pdf": ["http://crcv.ucf.edu/news&info/DefenseBooklet_FA17.pdf", "http://crcv.ucf.edu/papers/cviu2016-gonzalo.pdf", "http://vision.eecs.ucf.edu/papers/cviu2016-gonzalo.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2016.10.016"]}, {"id": "3b483c986b973856e016f761ec312c1a339766a5", "title": "DOTA: A Large-Scale Dataset for Object Detection in Aerial Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578516"]}, {"id": "1281e443d2cf1c1dd71ed3b7b0376d408d0958af", "title": "SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks", "year": "2015", "pdf": ["http://www.cs.cornell.edu/~xhuang/publications/salicon_poster.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Huang_SALICON_Reducing_the_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410395", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.38", "http://doi.org/10.1109/ICCV.2015.38"]}, {"id": "71f7be73a575f3689b0137446289d02462e1c5b0", "title": "Adaptive Multi-Scale Information Flow for Object Detection.", "year": "2018", "pdf": ["http://bmvc2018.org/contents/papers/0266.pdf"], "doi": []}, {"id": "581fb0f0405c7f0e60610d88ceaceb9af44d8569", "title": "Final Report : Smart Trash Net : Waste Localization and Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/581f/b0f0405c7f0e60610d88ceaceb9af44d8569.pdf"], "doi": []}, {"id": "eaa7c6293c9d858bd4c9897a5dfc7c670f2a8671", "title": "Distant Vehicle Detection Using Radar and Vision", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.10951.pdf"], "doi": []}, {"id": "2cea306754ed83eaf1d0433abbfb05b5a4c4cf48", "title": "BIG-OH: BInarization of gradient orientation histograms", "year": "2014", "pdf": ["http://vgl-ait.org/mdailey/uploads/publication_file/filename/110/Baber-BIG-OH.pdf"], "doi": ["http://doi.org/10.1016/j.imavis.2014.08.006"]}, {"id": "eb2ab9caa61b021c1cd7aff6d08163768faba99e", "title": "Cleaning Up Multiple Detections Caused by Sliding Window Based Object Detectors", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/eb2a/b9caa61b021c1cd7aff6d08163768faba99e.pdf"], "doi": []}, {"id": "5a364ecb2d10b637c63b885d27eb372390232277", "title": "Unsupervised Robust Feature-Based Partition Ensembling to Discover Categories", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7789641"]}, {"id": "1114c2aba97a5782a48341817811df2438d0fdbf", "title": "Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07498.pdf"], "doi": []}, {"id": "367008b91eb57c5ea64ef7520dfcabc0c5c85532", "title": "Person Re-identification: Past, Present and Future", "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.02984.pdf"], "doi": []}, {"id": "8211c974ec152e79235cb57a03ba2971e913508f", "title": "Multimodal Image Retrieval", "year": "2012", "pdf": [], "doi": ["https://doi.org/10.1007/s13735-012-0006-4"]}, {"id": "eb69f89588e9538194750f12bf8c8df6d5301f3b", "title": "Object Tracking by a Combination of Discriminative Global and Generative Multi-Scale Local Models", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/eb69/f89588e9538194750f12bf8c8df6d5301f3b.pdf"], "doi": []}, {"id": "d6bdc70d259b38bbeb3a78db064232b4b4acc88f", "title": "Video-Based Face Association and Identification", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7961735", "http://doi.ieeecomputersociety.org/10.1109/FG.2017.27", "http://doi.org/10.1109/FG.2017.27"]}, {"id": "d2e8efaa0d095c22455fe4eab260f94994bfb116", "title": "Stand-alone quality estimation of background subtraction algorithms", "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1016/j.cviu.2017.08.005"]}, {"id": "abe9f3b91fd26fa1b50cd685c0d20debfb372f73", "title": "The Pascal Visual Object Classes Challenge: A Retrospective", "year": "2014", "pdf": ["http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc14.pdf", "http://www.robots.ox.ac.uk/~vgg/publications/2015/Everingham15/everingham15.pdf", "https://www.research.ed.ac.uk/portal/files/20017166/ijcv_voc14.pdf"], "doi": ["http://doi.org/10.1007/s11263-014-0733-5"]}, {"id": "10d3f77225eca1d576268ba84ed83f230a5e47c4", "title": "Crafting a multi-task CNN for viewpoint estimation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.03894.pdf"], "doi": []}, {"id": "a01c7eec51fa901b2526325f563480c152c58ee5", "title": "Contour Box: Rejecting Object Proposals without Explicit Closed Contours", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Lu_Contour_Box_Rejecting_ICCV_2015_paper.pdf", "http://www.cse.cuhk.edu.hk/leojia/papers/contour_iccv15.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Lu_Contour_Box_Rejecting_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410591", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.234", "http://doi.org/10.1109/ICCV.2015.234"]}, {"id": "3db4bdee7bc03239ef25d23cf8dc14ce5a5300e2", "title": "Sparse Coding for Object Recognition", "year": "2013", "pdf": [], "doi": []}, {"id": "32cde90437ab5a70cf003ea36f66f2de0e24b3ab", "title": "The Cityscapes Dataset for Semantic Urban Scene Understanding", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.01685.pdf"], "doi": []}, {"id": "04e1c7618e4ef3e16159b27c522ddf94068c4f99", "title": "Reconstructing PASCAL VOC", "year": "2014", "pdf": ["http://home.isr.uc.pt/~joaoluis/papers/cvpr14_reconstruct_pascal_slides.pdf", "http://home.isr.uc.pt/~joaoluis/papers/cvpr2014_1.pdf", "http://people.eecs.berkeley.edu/~carreira/papers/cvpr14_reconstruct_pascal_slides.pdf", "http://people.eecs.berkeley.edu/~carreira/papers/cvpr2014_1.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Vicente_Reconstructing_PASCAL_VOC_2014_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909407", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.13", "http://doi.org/10.1109/CVPR.2014.13"]}, {"id": "ec187cedb69b389d06da26b17d889020e36ba6f6", "title": "ModaNet: A Large-scale Street Fashion Dataset with Polygon Annotations", "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240652"]}, {"id": "729f20fa5928514768f4e0d848e74e5eecc33174", "title": "Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8270088"]}, {"id": "8ecf9e6428edd33986e8c6a143870e57142fd5a1", "title": "DOTA: A Large-Scale Dataset for Object Detection in Aerial Images", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578516"]}, {"id": "8bb4e1ddfec4c5868c31685b6dfe8673df1d3e38", "title": "What is a Salient Object? A Dataset and a Baseline Model for Salient Object Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6990522"]}, {"id": "1fef45786e707e6b9b8517b0403e596ecbdea6a5", "title": "Sketch-based manga retrieval using manga109 dataset", "year": "2016", "pdf": ["https://arxiv.org/pdf/1510.04389.pdf"], "doi": []}, {"id": "12660f0defc6580e566c0fa2ac909971d6c6883b", "title": "The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780721", "http://doi.org/10.1109/CVPR.2016.352", "https://www.wikidata.org/entity/Q57840870"]}, {"id": "dc7a6156c90b5e9b0ff3e95413e9139024c460a5", "title": "Semantic Understanding of Scenes Through the ADE20K Dataset", "year": "2016", "pdf": ["http://arxiv.org/pdf/1608.05442", "http://arxiv.org/pdf/1608.05442v1.pdf", "http://bzhou.ie.cuhk.edu.hk/publication/ADE20K_IJCV.pdf", "https://arxiv.org/pdf/1608.05442.pdf", "https://export.arxiv.org/pdf/1608.05442"], "doi": ["https://doi.org/10.1007/s11263-018-1140-0"]}, {"id": "b7ff61c0807d50266fdd3a9770a7d66399b5f087", "title": "Drishti-GS: Retinal image dataset for optic nerve head(ONH) segmentation", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6867807"]}, {"id": "58a6eb3584b2f5df2f25d39a218904d510cae516", "title": "The UAVid Dataset for Video Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.10438.pdf"], "doi": []}, {"id": "2f4df08d9072fc2ac181b7fced6a245315ce05c8", "title": "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909475"]}, {"id": "dcb6f06631021811091ce691592b12a237c12907", "title": "SeaShips: A Large-Scale Precisely Annotated Dataset for Ship Detection", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8438999", "http://doi.org/10.1109/TMM.2018.2865686"]}, {"id": "127316fbe268c78c519ceb23d41100e86639418a", "title": "CNN Features Off-the-Shelf: An Astounding Baseline for Recognition", "year": "2014", "pdf": ["https://arxiv.org/pdf/1403.6382.pdf"], "doi": []}, {"id": "e74f9b7f8eec6ba4704c206b93bc8079af3da4bd", "title": "ImageNet Large Scale Visual Recognition Challenge", "year": "2014", "pdf": ["https://dspace.mit.edu/bitstream/1721.1/104944/1/11263_2015_Article_816.pdf", "http://arxiv.org/pdf/1409.0575v1.pdf", "http://dspace.mit.edu/bitstream/handle/1721.1/104944/11263_2015_Article_816.pdf;jsessionid=7277F2E4B792AF15009A8777BCC84DD1?sequence=1", "http://hci.stanford.edu/publications/2015/scenegraphs/imagenet-challenge.pdf", "https://arxiv.org/pdf/1409.0575.pdf", "https://dspace.mit.edu/bitstream/handle/1721.1/104944/11263_2015_Article_816.pdf;jsessionid=D47A767FE49C452E89782919F8DCDCE6?sequence=1"], "doi": ["https://doi.org/10.1007/s11263-015-0816-y", "http://dspace.mit.edu/openaccess-disseminate/1721.1/104944", "https://www.wikidata.org/entity/Q56594393"]}, {"id": "39978ba7c83333475d6825d0ff897692933895fc", "title": "Conditional Random Fields as Recurrent Neural Networks", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410536"]}, {"id": "aa4cc6506e837390486e5b836fb3dac8d15daafa", "title": "ThermalGAN: Multimodal Color-to-Thermal Image Translation for Person Re-identification in Multispectral Dataset", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_ECCVW_2018/papers/11134/Kniaz_ThermalGAN_Multimodal_Color-to-Thermal_Image_Translation_for_Person_Re-Identification_in_Multispectral_ECCVW_2018_paper.pdf"], "doi": ["https://doi.org/10.1007/978-3-030-11024-6_46"]}, {"id": "562463fafacca4bbe5256e318eb628bf915f4114", "title": "SLNSW-UTS: A Historical Image Dataset for Image Multi-Labeling and Retrieval", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7797084"]}, {"id": "2c0b510ebf995ef172cb64ed7ce24aa7903dced8", "title": "Learning Rich Features from RGB-D Images for Object Detection and Segmentation", "year": "2014", "pdf": ["https://arxiv.org/pdf/1407.5736.pdf"], "doi": []}, {"id": "21a1654b856cf0c64e60e58258669b374cb05539", "title": "You Only Look Once: Unified, Real-Time Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1506.02640.pdf"], "doi": []}, {"id": "38b6540ddd5beebffd05047c78183f7575559fb2", "title": "Selective Search for Object Recognition", "year": "2013", "pdf": ["https://pure.uva.nl/ws/files/19494140/UijlingsIJCV2013.pdf", "http://graphics.cs.cmu.edu/courses/16-824/2016_spring/slides/seg_3.pdf", "http://koen.me/research/pub/uijlings-ijcv2013-draft.pdf", "http://www.cs.cornell.edu/courses/cs7670/2014sp/slides/VisionSeminar14.pdf", "http://www.tpbin.com/Uploads/Subjects/de55b048-461f-4962-b851-fd020c47c982.pdf", "https://staff.fnwi.uva.nl/th.gevers/pub/GeversIJCV2013.pdf", "https://webcourse.cs.technion.ac.il/236815/Spring2016/ho/WCFiles/01_object_proposals_6pp.pdf"], "doi": ["https://doi.org/10.1007/s11263-013-0620-5"]}, {"id": "616b246e332573af1f4859aa91440280774c183a", "title": "The Pascal Visual Object Classes Challenge: A Retrospective", "year": "2014", "pdf": ["https://www.pure.ed.ac.uk/ws/files/20017166/ijcv_voc14.pdf", "http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc14.pdf", "http://www.robots.ox.ac.uk/~vgg/publications/2015/Everingham15/everingham15.pdf", "https://www.research.ed.ac.uk/portal/files/20017166/ijcv_voc14.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0733-5"]}, {"id": "abe80983d7773b51f1e30c02c50bcbe774c15a12", "title": "PLS/OPLS models in metabolomics: the impact of permutation of dataset rows on the K-fold cross-validation quality parameters.", "year": "2015", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/25382277", "https://doi.org/10.1039/c4mb00414k"]}, {"id": "784da2a7b53a16d2243f747e14946cc5e3476af0", "title": "VQA: Visual Question Answering", "year": "2015", "pdf": ["http://arxiv.org/pdf/1505.00468"], "doi": ["https://doi.org/10.1109/iccv.2015.279", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.279"]}, {"id": "4cef5476f9da50c1a8fefdcb7114863966f61d67", "title": "Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780717"]}, {"id": "7d39d69b23424446f0400ef603b2e3e22d0309d6", "title": "YOLO9000: Better, Faster, Stronger", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.08242.pdf"], "doi": []}, {"id": "20a78d3145279dcd799cd7a856ae2714f4863a16", "title": "SSD: Single Shot MultiBox Detector", "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.02325.pdf"], "doi": []}, {"id": "28fa525ca1e101335e877bb1f6999b6ccf476959", "title": "Semantic Segmentation with Second-Order Pooling", "year": "2012", "pdf": ["http://home.isr.uc.pt/~joaoluis/papers/eccv2012.pdf", "http://videolectures.net/site/normal_dl/tag=725540/eccv2012_carreira_semantic_01.pdf", "http://www.eecs.berkeley.edu/~carreira/papers/eccv2012.pdf"], "doi": ["https://doi.org/10.1007/978-3-642-33786-4_32"]}, {"id": "1e9b1f6061ef779e3ad0819c2832a29168eaeb9d", "title": "Instance-Aware Semantic Segmentation via Multi-task Network Cascades", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780712"]}, {"id": "428017f7a6df4d667275c7ac9b3feba39b70e4ae", "title": "CNN-RNN: A Unified Framework for Multi-label Image Classification", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.04573.pdf"], "doi": []}, {"id": "28ef938aaa312d76df988f636e248a6b267b6352", "title": "Unsupervised Visual Domain Adaptation Using Subspace Alignment", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751479"]}, {"id": "cab372bc3824780cce20d9dd1c22d4df39ed081a", "title": "DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs", "year": "2018", "pdf": ["https://arxiv.org/pdf/1606.00915.pdf"], "doi": []}, {"id": "851a884a89a95968c2edcad9787994ccaa8b51a8", "title": "BING: Binarized normed gradients for objectness estimation at 300fps", "year": "2018", "pdf": ["http://mmcheng.net/mftp/Papers/ObjectnessBING.pdf", "http://vision.ia.ac.cn/zh/senimar/reports/2014.5.6PPT.pdf"], "doi": ["https://doi.org/10.1007/s41095-018-0120-1"]}, {"id": "94c5ced03a6f896a4b3bc5a98b8b2baf349d8852", "title": "Fully Convolutional Instance-Aware Semantic Segmentation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099955"]}, {"id": "cbba352a37426a21b020d1ba8f61e5bca9ca20ae", "title": "Fully convolutional networks for semantic segmentation", "year": "2015", "pdf": ["http://arxiv.org/pdf/1411.4038"], "doi": ["https://doi.org/10.1109/cvpr.2015.7298965", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7298965"]}, {"id": "79cfb51a51fc093f66aac8e858afe2e14d4a1f20", "title": "Focal Loss for Dense Object Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237586"]}, {"id": "74cd38f585cfc48b7e01d95e127204d36b3c02c0", "title": "Anthropogenic VOC in Abidjan, southern West Africa: from source quantification to atmospheric impacts", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/74cd/38f585cfc48b7e01d95e127204d36b3c02c0.pdf"], "doi": []}, {"id": "71b7178df5d2b112d07e45038cb5637208659ff7", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"], "doi": []}, {"id": "a971fb267c150834ba823156841eca8845ae1c7f", "title": "Hierarchical Saliency Detection", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6618997"]}, {"id": "83d1118c2b2995a3e0cf9b6159e4c59e85cabb7e", "title": "Multiscale Combinatorial Grouping", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909443"]}, {"id": "f251d1d8eb5f3e5b8cf2b4c4550f25ef4c832b5e", "title": "Regionlets for Generic Object Detection", "year": "2013", "pdf": [], "doi": ["https://doi.org/10.1109/iccv.2013.10", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.10"]}, {"id": "2c03df8b48bf3fa39054345bafabfeff15bfd11d", "title": "Deep Residual Learning for Image Recognition", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780459"]}, {"id": "1a2a770d23b4a171fa81de62a78a3deb0588f238", "title": "Visualizing and Understanding Convolutional Networks", "year": "2013", "pdf": ["https://arxiv.org/pdf/1311.2901.pdf"], "doi": []}, {"id": "3dd2f70f48588e9bb89f1e5eec7f0d8750dd920a", "title": "Fast R-CNN", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410526"]}, {"id": "c1994ba5946456fc70948c549daf62363f13fa2d", "title": "Indoor Segmentation and Support Inference from RGBD Images", "year": "2012", "pdf": ["http://cs.nyu.edu/~silberman/papers/indoor_seg_support.pdf", "http://cs.nyu.edu/~silberman/papers/indoor_seg_support_supplementary.pdf", "http://videolectures.net/site/normal_dl/tag=725527/eccv2012_silberman_images_01.pdf", "http://web.engr.illinois.edu/~dhoiem/publications/eccv2012_indoorkinect_nathan.pdf"], "doi": ["https://doi.org/10.1007/978-3-642-33715-4_54"]}, {"id": "abd1c342495432171beb7ca8fd9551ef13cbd0ff", "title": "ImageNet Classification with Deep Convolutional Neural Networks", "year": "2012", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3065386"]}, {"id": "6de2b1058c5b717878cce4e7e50d3a372cc4aaa6", "title": "Generative Adversarial Nets", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/6de2/b1058c5b717878cce4e7e50d3a372cc4aaa6.pdf"], "doi": []}, {"id": "16fc1065c296840cb0f8ca62601aa17b7f0a02bf", "title": "Object Detection with Discriminatively Trained Part-Based Models", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/16fc/1065c296840cb0f8ca62601aa17b7f0a02bf.pdf"], "doi": []}, {"id": "3a0130cfab8192a397d79fc1c7c398470157cf48", "title": "Mask R-CNN.", "year": "2018", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/29994331", "https://doi.org/10.1109/tpami.2018.2844175"]}, {"id": "0023582fde36430c7e3ae81611a14e558c8f4bae", "title": "The Algorithmic Foundations of Differential Privacy", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/7f7e/9fd30ff0d1937f83ed0705de49cb9a7e7719.pdf"], "doi": []}, {"id": "2640a376c2b51f83420526646613e85d730eab37", "title": "Saliency Detection via Graph-Based Manifold Ranking", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619251"]}, {"id": "4a3fd686ce675659f238c46c629b055cd58651a0", "title": "Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099834"]}, {"id": "2f56b1ac5b9faac9527b6814778925e9242cf5fd", "title": "Training Region-Based Object Detectors with Online Hard Example Mining", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780458"]}, {"id": "272216c1f097706721096669d85b2843c23fa77d", "title": "Adam: A Method for Stochastic Optimization", "year": "2015", "pdf": ["https://arxiv.org/pdf/1412.6980.pdf"], "doi": []}, {"id": "2a94c84383ee3de5e6211d43d16e7de387f68878", "title": "Feature Pyramid Networks for Object Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099589"]}, {"id": "3cdb1364c3e66443e1c2182474d44b2fb01cd584", "title": "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1511.00561.pdf"], "doi": []}, {"id": "33da83b54410af11d0cd18fd07c74e1a99f67e84", "title": "DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition", "year": "2014", "pdf": ["https://arxiv.org/pdf/1310.1531.pdf"], "doi": []}, {"id": "8ac2736683dac9a467602ee19f5a290096259148", "title": "HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.00600.pdf"], "doi": []}, {"id": "0da75bded3ae15e255f5bd376960cfeffa173b4e", "title": "The Role of Context for Object Detection and Semantic Segmentation in the Wild", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909514"]}, {"id": "522fab628aab972f39835521e31564b4b6c64fe5", "title": "Vehicle Classification on Low-resolution and Occluded images : A low-cost labeled dataset for augmentation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/522f/ab628aab972f39835521e31564b4b6c64fe5.pdf"], "doi": []}, {"id": "f78db8e59ba354258c3eb4fff2ec67564975436f", "title": "Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.09263.pdf"], "doi": []}, {"id": "3aa681914a7da79f7d7293f51a058eefe61c8bb7", "title": "MVTec AD -- A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/0222/42d33927ef415754e116df1a122961edb6e9.pdf"], "doi": []}, {"id": "7df435390fa21d623d066d76c53c8cd6b8211891", "title": "What Makes a Patch Distinct?", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6618995"]}, {"id": "e3ea1c7a3c6cc15590ab5e62a171536fe01b9b1c", "title": "Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410492"]}, {"id": "2b7c2e4e888f4ca6bc8def17497504ea4012aa0f", "title": "Articulated Pose Estimation Using Discriminative Armlet Classifiers", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619273"]}, {"id": "5f5c075e8675d00a2e12bf12a99dafeba444e199", "title": "Semantic Segmentation with Reverse Attention", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06426.pdf"], "doi": []}, {"id": "2bcf46c0b52d8e9535ab3dcfdfb793a3da2a6271", "title": "Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7781017"]}, {"id": "c88c233c50f49b4b85a8702d5ee384d96fca8c23", "title": "Object-Proposal Evaluation Protocol is \u2018Gameable\u2019", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780466"]}, {"id": "09e15bb266da86d0a9525d2a94ac0b38f0b53b88", "title": "Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.2031.pdf"], "doi": []}, {"id": "6a1b76f1ef876061ec479ab9bc13fcd517eb4188", "title": "Large Kernel Matters \u2014 Improve Semantic Segmentation by Global Convolutional Network", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02719.pdf"], "doi": []}, {"id": "1a767a8af36252bb557117c021393292d8a83b24", "title": "Generic Object Detection With Dense Neural Patterns and Regionlets", "year": "2014", "pdf": ["https://arxiv.org/pdf/1404.4316.pdf"], "doi": []}, {"id": "f0550daaf6b173759aa5a2e39a3a9d874d65e858", "title": "Improvements to Context Based Self-Supervised Learning", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579071"]}, {"id": "1779b6a17ee68afafb6801477b165f19901689b2", "title": "Object Contour Detection with a Fully Convolutional Encoder-Decoder Network", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780397"]}, {"id": "cdfe4e46d949b68c682e554c402d16679fd7247c", "title": "Stacked Deconvolutional Network for Semantic Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.04943.pdf"], "doi": []}, {"id": "b9c830332608afbbf452a20afeff38ca5aac2e27", "title": "Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410477"]}, {"id": "b92a1ed9622b8268ae3ac9090e25789fc41cc9b8", "title": "Pooling in image representation: The visual codeword point of view", "year": "2013", "pdf": ["http://cedric.cnam.fr/~thomen/papers/avila_CVIU2012_final.pdf", "http://webia.lip6.fr/~thomen/papers/avila_CVIU2012_accepted.pdf"], "doi": ["https://doi.org/10.1016/j.cviu.2012.09.007"]}, {"id": "031055c241b92d66b6984643eb9e05fd605f24e2", "title": "Multi-fold MIL Training for Weakly Supervised Object Localization", "year": "2014", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Cinbis_Multi-fold_MIL_Training_2014_CVPR_paper.pdf", "https://hal.inria.fr/hal-00975746/PDF/paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909705", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.309", "http://doi.org/10.1109/CVPR.2014.309"]}, {"id": "2a1f38e4451e826e01c9874954ba7c6f32ff79f4", "title": "Boosting Self-Supervised Learning via Knowledge Transfer", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579073"]}, {"id": "f2666a91f6844d7815f758ec1afbac18caf392f8", "title": "Single-Shot Object Detection with Enriched Semantics", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578707"]}, {"id": "57bfbd06e94c5def35c1dde901bb4f1c839dbcdf", "title": "Deep patch learning for weakly supervised object classification and discovery", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02429.pdf"], "doi": []}, {"id": "1cf25786f1e473fdbfcd817cfa37b0ad12806e72", "title": "Co-segmentation by Composition", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751271"]}, {"id": "ab9d87a03ce3538ff42b6c26d87e676107cc392c", "title": "Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619260"]}, {"id": "3bde1aae1db3577938ffe910a9de5a1f187840e9", "title": "RIFD-CNN: Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780684"]}, {"id": "647c6ac5e0bfee0241d583650f18c6314f28aaee", "title": "Segmentation Driven Object Detection with Fisher Vectors", "year": "2013", "pdf": ["http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Cinbis_Segmentation_Driven_Object_2013_ICCV_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751480", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.369", "http://doi.org/10.1109/ICCV.2013.369"]}, {"id": "67490b6f34c827f107b046adeef0f5476132d4f8", "title": "How good are detection proposals, really?", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.6962.pdf"], "doi": []}, {"id": "636cea485f77373ae18e32ac8e1c4e37555db5bd", "title": "BING: Binarized Normed Gradients for Objectness Estimation at 300fps", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909816"]}, {"id": "3fd90098551bf88c7509521adf1c0ba9b5dfeb57", "title": "Attribute-Based Classification for Zero-Shot Visual Object Categorization", "year": "2014", "pdf": ["http://pub.ist.ac.at/~chl/papers/lampert-pami2013.pdf", "https://staff.fnwi.uva.nl/t.e.j.mensink/zsl2016/zslpubs/lampert13pami.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6571196", "http://doi.org/10.1109/TPAMI.2013.140", "https://www.ncbi.nlm.nih.gov/pubmed/24457503", "https://www.wikidata.org/entity/Q38437353"]}, {"id": "15e024d8f5625ec03c8ac592fbc093687cfb5f02", "title": "The Visual Object Tracking VOT2015 Challenge Results", "year": "2015", "pdf": ["http://cell.missouri.edu/media/publications/Matej-KristanRengarajan_VOT2015-challenge-results_ICCVW-2015.pdf", "http://cmp.felk.cvut.cz/~vojirtom/publications/Kristan2013The.pdf", "http://data.votchallenge.net/vot2015/presentations/vot_2015_paper.pdf", "http://liris.cnrs.fr/Documents/Liris-6875.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w14/papers/Kristan_The_Visual_Object_ICCV_2015_paper.pdf", "http://www.epics-project.eu/publications/2013_kristan_iccvw.pdf", "http://www.epics-project.eu/publications/2014_kristan_iccvw.pdf", "https://hal.archives-ouvertes.fr/hal-01336773/file/Kristan2015The.pdf", "https://repositorio.uam.es/bitstream/handle/10486/674992/visual_kristan_ICCVW_2015_ps.pdf?isAllowed=y&sequence=1"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7406428", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2015.79", "http://doi.org/10.1109/ICCVW.2015.79", "https://hal.archives-ouvertes.fr/hal-01336773/document"]}, {"id": "a1bcdb820f6f0dde108996a18eefb239ef0e9566", "title": "Visual Tracking: An Experimental Survey.", "year": "2014", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/26353314", "https://doi.org/10.1109/TPAMI.2013.230"]}, {"id": "1af794673d64112edf60f071ca24066e6a227d2b", "title": "Online Object Tracking: A Benchmark", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619156"]}, {"id": "d082f64b8a0a07d105207eb822be58ffb61b353a", "title": "EMOTIC: Emotions in Context Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w41/papers/Lapedriza_EMOTIC_Emotions_in_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8015019", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.285", "http://doi.org/10.1109/CVPRW.2017.285"]}, {"id": "2822a883d149956934a20614d6934c6ddaac6857", "title": "A survey of appearance models in visual object tracking", "year": "2013", "pdf": ["https://arxiv.org/pdf/1303.4803.pdf"], "doi": []}, {"id": "f727837e03a039d9bcec6d02cd87256f5a5854a4", "title": "Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.03409.pdf"], "doi": []}, {"id": "ebe5a4c2dc3ca55a5aeedcd25a98ca6e446ce9cc", "title": "Hippocampal Activity Patterns Carry Information about Objects in Temporal Context", "year": "2014", "pdf": ["http://cogns.northwestern.edu/cbmg/pdfs/2.Hsieh_2014.pdf", "http://dml.ucdavis.edu/uploads/6/1/9/7/61974117/hseih_2014_hippocampal.pdf", "http://orca.cf.ac.uk/96034/7/Hsieh_NEURON-D-13-01629.1.pdf"], "doi": ["https://www.sciencedirect.com/science/article/pii/S0896627314000208", "https://doi.org/10.1016/j.neuron.2014.01.015", "https://www.ncbi.nlm.nih.gov/pubmed/24607234"]}, {"id": "b7d540cd0de72e984cdec44afa4a4d039cfd5eea", "title": "Object Tracking Benchmark", "year": "2015", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/pami15_tracking_benchmark.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7001050", "http://doi.org/10.1109/TPAMI.2014.2388226", "https://www.ncbi.nlm.nih.gov/pubmed/26353130", "https://www.wikidata.org/entity/Q35768210"]}, {"id": "aa23d33983b1abd2d8a677040eb875e93c478a7f", "title": "Measuring the Objectness of Image Windows", "year": "2012", "pdf": ["http://groups.inf.ed.ac.uk/calvin/Publications/alexe11-techreport.pdf", "http://groups.inf.ed.ac.uk/calvin/Publications/alexe12pami.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/techreports/eth_biwi_00882.pdf", "https://www.research.ed.ac.uk/portal/files/17686204/Alexe_et_al_2010_Measuring_the_objectnessi.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6133291", "http://doi.org/10.1109/TPAMI.2012.28", "https://www.ncbi.nlm.nih.gov/pubmed/22248633", "https://www.wikidata.org/entity/Q50666022"]}, {"id": "149e5e5eeea5a9015ab5ae755f62c45ef70fa79b", "title": "Hierarchical Convolutional Features for Visual Tracking", "year": "2015", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/iccv15_tracking.pdf", "http://openaccess.thecvf.com/content_iccv_2015/papers/Ma_Hierarchical_Convolutional_Features_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Ma_Hierarchical_Convolutional_Features_ICCV_2015_paper.pdf", "https://filebox.ece.vt.edu/~jbhuang/poster/ICCV_2015_HCF_Poster.pdf", "https://filebox.ece.vt.edu/~jbhuang/slides/ICCV_2015_HCF_Slides.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410709", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.352", "http://doi.org/10.1109/ICCV.2015.352"]}, {"id": "05375a7489f0a84d47a316bacb4d86e8a7bda0df", "title": "Analysis of Scores, Datasets, and Models in Visual Saliency Prediction", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751224"]}, {"id": "58e6eaacaab3fbf9b307a8aec1c614027ff501ce", "title": "Dynamic Eye Movement Datasets and Learnt Saliency Models for Visual Action Recognition", "year": "2012", "pdf": ["http://109.101.234.42/documente/publications/19-62.pdf", "http://sminchisescu.ins.uni-bonn.de/papers/ms12eccv.pdf", "http://web.cs.hacettepe.edu.tr/~erkut/bil722.f12/w09-levent.pdf"], "doi": ["https://doi.org/10.1007/978-3-642-33709-3_60"]}, {"id": "36c91b1342c1357877e89b4c43f8eadb39755c0b", "title": "Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses", "year": "2012", "pdf": ["http://cs.stanford.edu/groups/vision/documents/YaoFei-Fei_PAMI2012.pdf", "http://cs.stanford.edu/groups/vision/pdf/yaopami12.pdf", "http://vision.stanford.edu/pdf/yaopami12.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6165303", "http://doi.org/10.1109/TPAMI.2012.67", "https://www.ncbi.nlm.nih.gov/pubmed/22392710", "https://www.wikidata.org/entity/Q34185448"]}, {"id": "f0ee079a1f40736e5b7760b38781f090744f37fc", "title": "Contextualizing Object Detection and Classification", "year": "2015", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/26353205", "https://doi.org/10.1109/TPAMI.2014.2343217", "https://www.wikidata.org/entity/Q40558547"]}, {"id": "5b130e2a1fc3f71b7638cc5dde72481cf33264cc", "title": "Scene Recognition with CNNs: Objects, Scales and Dataset Bias", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780437"]}, {"id": "bfa6ad4d71008505729274d008a9b4a7d92b2985", "title": "Semantic Understanding of Scenes Through the ADE20K Dataset", "year": "2018", "pdf": ["https://arxiv.org/pdf/1608.05442.pdf"], "doi": []}, {"id": "1883116d33a3e0321d2fe96e0a8a62546aca4ee9", "title": "Visual Question Answering: Datasets, Algorithms, and Future Challenges", "year": "2017", "pdf": ["https://arxiv.org/pdf/1610.01465.pdf"], "doi": []}, {"id": "88c307c51594c6d802080a0780d0d654e2e2891f", "title": "Visual Question Answering: A Survey of Methods and Datasets", "year": "2017", "pdf": ["https://arxiv.org/pdf/1607.05910.pdf"], "doi": []}, {"id": "3cfbb77e5a0e24772cfdb2eb3d4f35dead54b118", "title": "Don't count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/2353/17b7ce64b4b3aefe57c1304e8157a4832d2c.pdf"], "doi": []}, {"id": "18e39b6f8f5c538d639bc0b46136ed93b5e3ef35", "title": "A Large Dataset of Object Scans", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.02481.pdf"], "doi": []}, {"id": "b31d6f201340ecec35bbe0f477710436f860605e", "title": "Learning Video Object Segmentation with Visual Memory", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237742"]}, {"id": "4a19f6545473363b16d4a10ed13fef29b38856d3", "title": "What is a Salient Object? A Dataset and a Baseline Model for Salient Object Detection", "year": "2015", "pdf": ["https://arxiv.org/pdf/1412.5027.pdf"], "doi": []}, {"id": "0558c94a094158ecd64f0d5014d3d9668054fb97", "title": "Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/528d/141aba97074977a332bb2d96364b716f246c.pdf"], "doi": []}, {"id": "09a503095db2d68b439e48d67481399198ed0e5b", "title": "Recurrent Models of Visual Attention", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.6247.pdf"], "doi": []}, {"id": "350d507f5d899e4d7293b1aa951aa0f81b9fd30a", "title": "The Visual Object Tracking VOT2017 Challenge Results", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w28/Kristan_The_Visual_Object_ICCV_2017_paper.pdf", "https://hal.archives-ouvertes.fr/hal-01336773/file/Kristan2015The.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265440", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2017.230", "http://doi.org/10.1109/ICCVW.2017.230"]}, {"id": "7e232313a59d735ef7c8a9f4cc7bc980a29deb5e", "title": "Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1007/s11263-018-1116-0"]}, {"id": "b4ee2a6b5fdf66f57e94a998cff2acef4af7d256", "title": "Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes", "year": "2013", "pdf": ["https://www.d2.mpi-inf.mpg.de/sites/default/files/wojek2013pami.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6265058", "http://doi.org/10.1109/TPAMI.2012.174", "https://www.ncbi.nlm.nih.gov/pubmed/22889818", "https://www.wikidata.org/entity/Q45823527"]}, {"id": "2ce63d77eecc35faef85a3b752a314c93a077ac9", "title": "Learning Multi-domain Convolutional Neural Networks for Visual Tracking", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780834"]}, {"id": "1c66fa1f3f189ca25bd657f53d77fde64c75f3da", "title": "Adaptive Color Attributes for Real-Time Visual Tracking", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909539"]}, {"id": "eb66303192a89c314ce4acae640ba700fa3293a3", "title": "Unsupervised Object Annotation through Context Analysis", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/eb66/303192a89c314ce4acae640ba700fa3293a3.pdf"], "doi": []}, {"id": "51a4d658c93c5169eef7568d3d1cf53e8e495087", "title": "Unsupervised Visual Domain Adaptation Using Subspace Alignment", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751479"]}, {"id": "079ed21601974d0604544a6d816c2f51b5c039b8", "title": "Enriching Visual Knowledge Bases via Object Discovery and Segmentation", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909658"]}, {"id": "7574b7e5a75fdd338c27af5aeb77ab79460c4437", "title": "Learning Dynamic Siamese Network for Visual Object Tracking", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237458"]}, {"id": "38a169b6e67ef7768f91fa208c9b5544f6f57f16", "title": "Object Bank: An Object-Level Image Representation for High-Level Visual Recognition", "year": "2013", "pdf": ["http://cs.stanford.edu/groups/vision/pdf/li_ijcv2013.pdf", "http://vision.stanford.edu/pdf/li_ijcv2013.pdf", "http://www.tpbin.com/Uploads/Subjects/79181d36-c45c-4f6c-821f-b7f9fcac3881.pdf"], "doi": ["http://doi.org/10.1007/s11263-013-0660-x"]}, {"id": "5527dd901b836e2f164c9fa3e62f57cd70c21745", "title": "3D object retrieval via range image queries in a bag-of-visual-words context", "year": "2013", "pdf": ["http://graphics.di.uoa.gr/Downloads/papers/journals/p43.pdf", "http://www.idi.ntnu.no/grupper/vis/wp-content/uploads/2013/09/Range3DRetrievalTVCfinal.pdf"], "doi": ["https://doi.org/10.1007/s00371-013-0876-3"]}, {"id": "5ea8a9ae2bf40c4722e618b732f769744ab57dfe", "title": "Context Driven Scene Parsing with Attention to Rare Classes", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909817"]}, {"id": "2d84f49572c2b29b6c9e1818eb57e7f12bc4236e", "title": "Query-Adaptive Asymmetrical Dissimilarities for Visual Object Retrieval", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751322"]}, {"id": "00319cd17cebae5e1095a248260bd7be15781362", "title": "A Dataset for Improved RGBD-Based Object Detection and Pose Estimation for Warehouse Pick-and-Place", "year": "2016", "pdf": ["https://arxiv.org/pdf/1509.01277.pdf"], "doi": []}, {"id": "0f060f011fe3093a24bf2cde96a4a833f58ec5a5", "title": "Object-based visual query suggestion", "year": "2012", "pdf": ["https://www.researchgate.net/profile/Pierre_Letessier/publication/257627352_Object-based_visual_query_suggestion/links/00b7d5260034959679000000.pdf"], "doi": ["https://doi.org/10.1007/s11042-012-1340-5"]}, {"id": "33baa52f583fb049f473a53d8e0ca5ac8e7abbf2", "title": "Reinforcement Learning for Visual Object Detection", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780685"]}, {"id": "1631bc8b8fe853278b8e54bd3e9fff1445fa9f91", "title": "Visual Distance Measures for Object Retrieval", "year": "2012", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6411668"]}, {"id": "4a8e9e179b58d3e10448f5e4680b66f34c8bc573", "title": "Learning to segment moving objects in videos", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7299035"]}, {"id": "0f6a8e9139cdd15fd0a8a292204aed21a8b51c5a", "title": "ReferItGame: Referring to Objects in Photographs of Natural Scenes", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/0f6a/8e9139cdd15fd0a8a292204aed21a8b51c5a.pdf"], "doi": []}, {"id": "1ced31e02234bc3d1092ffb2c7442ffbd51cb309", "title": "A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780807"]}, {"id": "5ac18d505ed6d10e8692cbb7d33f6852e6782692", "title": "The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00982.pdf"], "doi": []}, {"id": "efa08283656714911acff2d5022f26904e451113", "title": "Active Object Localization in Visual Situations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.00548.pdf"], "doi": []}, {"id": "1f7127b9ae86d7fac305c6b824801e455e82f511", "title": "Visual relationship detection with object spatial distribution", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8019448", "http://doi.ieeecomputersociety.org/10.1109/ICME.2017.8019448", "http://doi.org/10.1109/ICME.2017.8019448"]}, {"id": "051830b0ea58d1568f19ec3297e301d9789c9a76", "title": "Bringing Semantics into Focus Using Visual Abstraction", "year": "2013", "pdf": ["http://courses.cs.washington.edu/courses/cse590v/13au/cse590v_au13_wk5_abstract_scenes.pdf", "http://courses.cs.washington.edu/courses/cse590v/13au/cse590v_au13_wk5_abstract_scenes_rob.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d009.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Zitnick_Bringing_Semantics_into_2013_CVPR_paper.pdf", "https://filebox.ece.vt.edu/~parikh/Publications/ZitnickParikh_CVPR_2013_clipart.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619231", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.387", "http://doi.org/10.1109/CVPR.2013.387"]}, {"id": "64c4019f1ea9b54b1848418ac53c4e2584dc62d4", "title": "ActionNet-VE Dataset: A Dataset for Describing Visual Events by Extending VIRAT Ground 2.0", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7433003"]}, {"id": "9a8e61cc9a95efe9e35df4d4230c7b8a655b7392", "title": "Unsupervised Joint Object Discovery and Segmentation in Internet Images", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619097"]}, {"id": "022027ce7475029f78fb3cdb758d947a8978ab5c", "title": "Invariant visual object recognition: biologically plausible approaches", "year": "2015", "pdf": ["http://wrap.warwick.ac.uk/77413/1/WRAP_422_2015_Article_658.pdf", "http://www.oxcns.org/papers/554%20Robinson%20Rolls%202015%20Invariant%20visual%20object%20recognition%20Biologically%20plausible%20models.pdf"], "doi": ["https://doi.org/10.1007/s00422-015-0658-2", "https://www.ncbi.nlm.nih.gov/pubmed/26335743", "https://www.wikidata.org/entity/Q43248757"]}, {"id": "e8e662e45e39249756d2b0090782434a5cf1f4aa", "title": "VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Hou_VegFru_A_Domain-Specific_ICCV_2017_paper.pdf", "http://openaccess.thecvf.com/content_ICCV_2017/supplemental/Hou_VegFru_A_Domain-Specific_ICCV_2017_supplemental.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237328", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.66", "http://doi.org/10.1109/ICCV.2017.66"]}, {"id": "54c7c3909c7e1e827befdbe8d2595a3b196ba1b8", "title": "AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578731"]}, {"id": "ac6c28cd866bccbbca54da8b7bd5b2e0d5e9d0b4", "title": "Cross-Dataset Learning of Visual Concepts", "year": "2012", "pdf": ["https://hpi.de/fileadmin/user_upload/fachgebiete/meinel/Semantic-Technologies/paper/amr2012.pdf"], "doi": ["https://doi.org/10.1007/978-3-319-12093-5_4"]}, {"id": "bbe7f4217a9bd9c6d3826b5b62d59d183e729383", "title": "Discriminative Hough context model for object detection", "year": "2013", "pdf": [], "doi": ["https://doi.org/10.1007/s00371-013-0780-x"]}, {"id": "55ca9fe4ae98904bfe026d22dcf1420ff9c0dd86", "title": "Dataset for Visual Reasoning", "year": "2017", "pdf": [], "doi": []}, {"id": "20f9a09defe5b02b98c464ca6df36b3b6358f60b", "title": "The State-of-the-Art in Visual Object Tracking", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/cd46/4a309fa1736e1373f0bb06baf75e3d0abcac.pdf"], "doi": []}, {"id": "d86fabd4498c8feaed80ec342d254fb877fb92f5", "title": "Region-Object Relevance-Guided Visual Relationship Detection", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d86f/abd4498c8feaed80ec342d254fb877fb92f5.pdf"], "doi": []}, {"id": "4405b44b5597787c42abeca6d0b3172175557b7b", "title": "Object discovery in 3D scenes via shape analysis", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6630857"]}, {"id": "8da0771e47c32405c4877cedce3ff84ac7390646", "title": "A survey of datasets for visual tracking", "year": "2015", "pdf": ["http://www.isir.upmc.fr/files/2015ACLI3545.pdf"], "doi": ["https://doi.org/10.1007/s00138-015-0713-y", "http://hal.upmc.fr/hal-01217152/document"]}, {"id": "4a75c3441cef2069458fe61a01196c2c8b32ee92", "title": "Single-trial classification of EEG in a visual object task using ICA and machine learning", "year": "2014", "pdf": ["https://www.research.ed.ac.uk/portal/files/14632594/Stewart.JNeurosciMeth.228.2014.pdf"], "doi": ["https://www.sciencedirect.com/science/article/pii/S0165027014000752", "https://doi.org/10.1016/j.jneumeth.2014.02.014", "https://www.ncbi.nlm.nih.gov/pubmed/24613798"]}, {"id": "1456f147381bf7c385225d854c2fb48c19eca285", "title": "LCAV-31: a dataset for light field object recognition", "year": "2014", "pdf": ["http://infoscience.epfl.ch/record/197737/files/902014.pdf"], "doi": ["http://doi.org/10.1117/12.2041097"]}, {"id": "d7ed761cfe1b71aa7e4d08c355fcab131558f8c8", "title": "Learning Object Models on a Robot using Visual Context and Appearance Cues", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/d7ed/761cfe1b71aa7e4d08c355fcab131558f8c8.pdf"], "doi": []}, {"id": "d53c79cce46820642f2d4e0f0dac9b31d1201f24", "title": "Visual object trapping", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1016/j.cviu.2016.07.007"]}, {"id": "5ffd74d2873b7cba2cbc5fd295cc7fbdedca22a2", "title": "The Cityscapes Dataset", "year": "2015", "pdf": [], "doi": []}, {"id": "14ca963b4e0b87fc7213b8e3a3e2371cee7ffad6", "title": "Exploring Causal Relationships in Visual Object Tracking", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410708"]}, {"id": "f9c602cc436a9ea2f9e7db48c77d924e09ce3c32", "title": "Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.07747.pdf"], "doi": []}, {"id": "3ecb007d46614d5e5566b0ad7c96c0c4c8ac0d14", "title": "Enhancing Object Recognition With Dynamic Cognitive Context", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3ecb/007d46614d5e5566b0ad7c96c0c4c8ac0d14.pdf"], "doi": []}, {"id": "c8018f3dc6121d92da37f1756e7bd11a128aa55c", "title": "Region Filling and Object Removal by Exemplar based Image Inpainting", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/c801/8f3dc6121d92da37f1756e7bd11a128aa55c.pdf"], "doi": []}, {"id": "051d8bbf12877c46ae9a598a386c5b72d1b103ac", "title": "Object Detection using Geometrical Context Feedback", "year": "2012", "pdf": ["http://cvgl.stanford.edu/papers/Sun_IJCV_2012.pdf"], "doi": ["http://doi.org/10.1007/s11263-012-0547-2"]}, {"id": "b0cd469a06fb2eae3a5cc0c860aa592f71b13f6d", "title": "IQA: Visual Question Answering in Interactive Environments", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578528"]}]}
\ No newline at end of file
+{"id": "0ee1916a0cb2dc7d3add086b5f1092c3d4beb38a", "citations": [{"id": "c399c0089fb134d1476fadf5f0426e0e8b70eebd", "title": "The Lov\u00e1sz Hinge: A Novel Convex Surrogate for Submodular Losses.", "year": "2018", "pdf": ["https://arxiv.org/pdf/1512.07797.pdf"], "doi": []}, {"id": "6b6fcf1220ea100aa80004018c78b137289d3c50", "title": "CAD: Scale Invariant Framework for Real-Time Object Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265304"]}, {"id": "656f05741c402ba43bb1b9a58bcc5f7ce2403d9a", "title": "Supervised Learning Approaches for Automatic Structuring of Videos. (M\u00e9thodes d'apprentissage supervis\u00e9 pour la structuration automatique de vid\u00e9os)", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/656f/05741c402ba43bb1b9a58bcc5f7ce2403d9a.pdf"], "doi": []}, {"id": "aa3398e15395a2a380c7c6b3f274c8c60fb0b48c", "title": "Chained Cascade Network for Object Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237476"]}, {"id": "e58434a01c45505995b000f5e631843a2f2ea582", "title": "Scale coding bag of deep features for human attribute and action recognition", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.04884.pdf"], "doi": []}, {"id": "eaf65c7cf4e9f7868c61f48656cb608fae0adcee", "title": "Visual dictionaries as intermediate features in the human brain", "year": "2014", "pdf": ["http://journal-cdn.frontiersin.org/article/104962/files/pubmed-zip/versions/1/pdf", "http://journal.frontiersin.org/article/10.3389/fncom.2014.00168/pdf", "https://pure.uva.nl/ws/files/2455021/162945_fncom_08_00168.pdf"], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/25642183", "http://doi.org/10.3389/fncom.2014.00168", "https://www.wikidata.org/entity/Q34969835"]}, {"id": "4c5d723dd83250c6b289c94318717de2d373a6ed", "title": "Learning Image Classification and Retrieval Models", "year": "2012", "pdf": [], "doi": []}, {"id": "841a5de1d71a0b51957d9be9d9bebed33fb5d9fa", "title": "PCANet: A Simple Deep Learning Baseline for Image Classification?", "year": "2015", "pdf": ["https://arxiv.org/pdf/1404.3606.pdf"], "doi": []}, {"id": "095ccb4e2e0f3934dc1aa51c685b2f54c8a6e588", "title": "Derivate-based Component-Trees for Multi-Channel Image Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.01906.pdf"], "doi": []}, {"id": "a221588fd2d062462254481cfd9563fec2f7c387", "title": "Deep neural network ensemble architecture for eye movements classification", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8345537"]}, {"id": "67126ad0af544740c455311d08cb180aec830a6c", "title": "Generating Descriptions of Spatial Relations between Objects in Images", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/6712/6ad0af544740c455311d08cb180aec830a6c.pdf"], "doi": []}, {"id": "823db813f036365cf9b22b2081ec167a2b582532", "title": "Segmentation and Shape Extraction from Convolutional Neural Networks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354273", "http://doi.ieeecomputersociety.org/10.1109/WACV.2018.00169", "http://doi.org/10.1109/WACV.2018.00169", "http://www.grk1564.uni-siegen.de/publicationPDFbyID?ID=926"]}, {"id": "f3ccdf54a3384e601fa36969e7b3f657e2516a3b", "title": "Paying More A ention to Saliency : Image Captioning with Saliency and Context A ention 1 : 3", "year": "2017", "pdf": [], "doi": []}, {"id": "2c9c597ab660815e07980e9655c3c5989402205b", "title": "Vision-Based Reacquisition for Task-Level Control", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/2c9c/597ab660815e07980e9655c3c5989402205b.pdf"], "doi": []}, {"id": "aae1bf434983545c8a99a5dbfc2ce37435c76e03", "title": "SampleAhead: Online Classifier-Sampler Communication for Learning from Synthesized Data", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00248.pdf"], "doi": []}, {"id": "ff18125a8f549135e6320fed91d0002bd2dae635", "title": "Colour Terms: a Categorisation Model Inspired by Visual Cortex Neurons", "year": "2017", "pdf": ["https://arxiv.org/pdf/1709.06300.pdf"], "doi": []}, {"id": "3e50e351687779c05390daf117f0394d1556cd3c", "title": "Die Detektion interessanter Objekte unter Verwendung eines objektbasierten Aufmerksamkeitsmodells", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3e50/e351687779c05390daf117f0394d1556cd3c.pdf"], "doi": []}, {"id": "065f05c9cb2a6080191851dd82cd9b439a77499a", "title": "Comparing Boosted Cascades to Deep Learning Architectures for Fast and Robust Coconut Tree Detection in Aerial Images", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/065f/05c9cb2a6080191851dd82cd9b439a77499a.pdf"], "doi": []}, {"id": "4ba503d8f173880d8e8402808f54b78b653e5d20", "title": "Accelerating Stochastic Gradient Descent via Online Learning to Sample", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/4ba5/03d8f173880d8e8402808f54b78b653e5d20.pdf"], "doi": []}, {"id": "03a2235fea70317461222fac05e38ee35ead9711", "title": "Implementation of a Computer Vision Algorithm for Onboard Detection of Unmanned Aircraft submitted by Luk\u00e1\u0161 Bauer", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/03a2/235fea70317461222fac05e38ee35ead9711.pdf"], "doi": []}, {"id": "d07dabdea9e2e4546b09d07a019723ceb6c61b84", "title": "Deep learning for text spotting", "year": "2015", "pdf": [], "doi": []}, {"id": "7f66ff8dd0313fc9c7d67be7ea5aecdda956657c", "title": "Tracking-by-Segmentation with Online Gradient Boosting Decision Tree", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Son_Tracking-by-Segmentation_With_Online_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Son_Tracking-by-Segmentation_With_Online_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410707", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.350", "http://doi.org/10.1109/ICCV.2015.350"]}, {"id": "4896c9f6958137c88db29a3a707aafae3c29d106", "title": "Discriminative Re-ranking of Diverse Segmentations", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619095"]}, {"id": "858555b6f4663fe083d6c81a2671c9cd8130bbf3", "title": "Object Discovery via Cohesion Measurement", "year": "2018", "pdf": ["https://arxiv.org/pdf/1704.08944.pdf"], "doi": []}, {"id": "f81f5da2a1e4eb80b465b8dffca4c9e583a8a8a6", "title": "Rapid Object Detection Systems , Utilising Deep Learning and Unmanned Aerial Systems ( Uas ) for Civil Engineering Applications", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/f81f/5da2a1e4eb80b465b8dffca4c9e583a8a8a6.pdf"], "doi": []}, {"id": "369bd35ab8bad4c7bc5e376cc776a5366d97b12e", "title": "An Object Detector Trained on Line Drawings", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/369b/d35ab8bad4c7bc5e376cc776a5366d97b12e.pdf"], "doi": []}, {"id": "46971fb6caa61c606b046da855be4e196a830ccf", "title": "Identification of Scene Text by Character Descriptor in Smart Mobile Devices", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/4697/1fb6caa61c606b046da855be4e196a830ccf.pdf"], "doi": []}, {"id": "afad16c9fee11d8f78785af6b1856beb86b5ccf4", "title": "Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08011.pdf"], "doi": []}, {"id": "9089280062cf40870a322d687c2850d45c02ebae", "title": "Single Image Action Recognition by Predicting Space-Time Saliency", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.04641.pdf"], "doi": []}, {"id": "cf384eda31030a45238ebd8356ace7600da5076b", "title": "Cross-Domain CNN for Hyperspectral Image Classification", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.00093.pdf"], "doi": []}, {"id": "44c5e66e58dd8212b753662e08cc0a7c8327ec50", "title": "Scene Parsing with Object Instance Inference Using Regions and Per-exemplar Detectors", "year": "2014", "pdf": ["http://slazebni.cs.illinois.edu/publications/jtighe-ijcv14.pdf", "http://wwwx.cs.unc.edu/~mn/sites/default/files/jtighe-ijcv14.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0778-5"]}, {"id": "83acbf0bee402b0472ff101cee5942f4137d91c3", "title": "Semi-automatic Annotation on Image Segmentation Hierarchies", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/83ac/bf0bee402b0472ff101cee5942f4137d91c3.pdf"], "doi": []}, {"id": "e9af96d478b487fec9a06dde9e43b2ed3355ea7b", "title": "Automatic thresholding of SIFT descriptors", "year": "2016", "pdf": ["https://arxiv.org/pdf/1811.03173.pdf"], "doi": []}, {"id": "b1369e4785dd0b23f89ca76f45468049c8667863", "title": "1 DARTS : Deceiving Autonomous Cars with Toxic Signs", "year": "2018", "pdf": [], "doi": []}, {"id": "1a5151b4205ab27b1c76f98964debbfc11b124d5", "title": "Self Paced Deep Learning for Weakly Supervised Object Detection", "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.07651.pdf"], "doi": []}, {"id": "f1d8c377093ecf64afd7f17383738e81666fe5ae", "title": "Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.10805.pdf"], "doi": []}, {"id": "12ff1c48f5776fda9d156c7b324af3f2674420a9", "title": "Are Large Scale Training Images or Discriminative Features Important for Codebook Construction?", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/12ff/1c48f5776fda9d156c7b324af3f2674420a9.pdf"], "doi": []}, {"id": "e4dc24e4926df4de3e8d7ca7cd1f4115e91f03e1", "title": "Instance-level video segmentation from object tracks Anonymous CVPR submission", "year": "", "pdf": ["https://pdfs.semanticscholar.org/e4dc/24e4926df4de3e8d7ca7cd1f4115e91f03e1.pdf"], "doi": []}, {"id": "194af94f1ea9357bebb0aab5ab98aa0daa21ddbd", "title": "Snapshot Distillation: Teacher-Student Optimization in One Generation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1812.00123.pdf"], "doi": []}, {"id": "9d67f5adf4497ba99201d318cfbbed07e926c05b", "title": "Unseen Object Segmentation in Videos via Transferable Representations", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.02444.pdf"], "doi": []}, {"id": "0caef87116f62fcc86735401a9aa9d4e170ffbef", "title": "On Performance Evaluation of Driver Hand Detection Algorithms: Challenges, Dataset, and Metrics", "year": "2015", "pdf": ["http://cvrr.ucsd.edu/eshed/papers/Das_ITSC2015.pdf", "http://cvrr.ucsd.edu/publications/2015/DasOhnbarTrivedi_ITSC2015.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7313566", "http://doi.org/10.1109/ITSC.2015.473"]}, {"id": "806aea24148fc2ef851803c216a0a25894d78bf4", "title": "Correlation filter based visual trackers for person pursuit using a low-cost Quadrotor", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7294481", "http://doi.org/10.1109/I4CS.2015.7294481"]}, {"id": "63ed42249d7cbb21a4b0d42419d42b014ff114eb", "title": "Comprehensive Parameter Sweep for Learning-Based Detector on Traffic Lights", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/4817/826f1af10e0c31dee067f8d9255d6387d486.pdf"], "doi": []}, {"id": "1b1323b4677c640ae8835a9ccab611ca1e9652e3", "title": "Robust object tracking with a hierarchical ensemble framework", "year": "2016", "pdf": ["https://arxiv.org/pdf/1509.06925.pdf"], "doi": []}, {"id": "557e5e38a4c5b95e2bc86f491b03e5c8c7add857", "title": "Thin-Slicing for Pose: Learning to Understand Pose without Explicit Pose Estimation", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Kwak_Thin-Slicing_for_Pose_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Kwak_Thin-Slicing_for_Pose_CVPR_2016_paper.pdf", "http://www.di.ens.fr/willow/pdfscurrent/kwak2016.pdf", "https://vlg.dgist.ac.kr/research/pose_emb/data/CVPR2016_pose.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780903", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.534", "http://doi.org/10.1109/CVPR.2016.534"]}, {"id": "6bcc2b50e32bdbb0c668f75000badf21e6cd0839", "title": "Knowledge Projection for Deep Neural Networks", "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.09505.pdf"], "doi": []}, {"id": "071680ca97de050a372ea79f2b99f102bb3ca6ef", "title": "Inferring Unseen Views of People", "year": "2014", "pdf": ["http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/inferring-unseen-views-of-people-paper.pdf", "http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/inferring-unseen-views-of-people-poster.pdf", "http://vision.cs.utexas.edu/projects/infering_unseen_views_of_people/supp.pdf", "http://www.cs.utexas.edu/~chaoyeh/cvpr_2014_Inferring_Unseen_Views_of_People%20(2).pdf", "http://www.cs.utexas.edu/~grauman/papers/chen-pose-cvpr2014.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Chen_Inferring_Unseen_Views_2014_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909655", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.258", "http://doi.org/10.1109/CVPR.2014.258"]}, {"id": "415c0eecce9fde7d1ba9c70bd0bfa5471760c117", "title": "Oriented Object Proposals", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/He_Oriented_Object_Proposals_ICCV_2015_paper.pdf", "http://www.cs.cityu.edu.hk/~rynson/papers/iccv15.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/He_Oriented_Object_Proposals_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410397", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.40", "http://doi.org/10.1109/ICCV.2015.40"]}, {"id": "f865248065b8d6bcbce4a4053b73e4de2080ba23", "title": "Efficient object detection for high resolution images", "year": "2015", "pdf": ["https://arxiv.org/pdf/1510.01257.pdf"], "doi": []}, {"id": "e0e19769ad446c2a74c0616fcfb551059c899ce6", "title": "Part level transfer regularization for enhancing exemplar SVMs", "year": "2015", "pdf": ["http://people.csail.mit.edu/yusuf/publications/2015/Aytar15/aytar15.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2015.04.004"]}, {"id": "009fba8df6bbca155d9e070a9bd8d0959bc693c2", "title": "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909475"]}, {"id": "a0703bef11c978cc8faf05eb229e29a889f8a0b1", "title": "Superpixel Hierarchy", "year": "2018", "pdf": ["https://arxiv.org/pdf/1605.06325.pdf"], "doi": []}, {"id": "472de7b3c674e8f06702385569779d11b71bc8f2", "title": "Superpixel Coherency and Uncertainty Models for Semantic Segmentation", "year": "2013", "pdf": ["http://cvlab.postech.ac.kr/~tgx.lim/paper/iccv2013_semantic.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_workshops_2013/W08/papers/Baek_Superpixel_Coherency_and_2013_ICCV_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6755909"]}, {"id": "73818ae13a89c2377c30cdb029fdb7e490fe5367", "title": "Joint cost minimization for multi-object tracking", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8078481", "http://doi.ieeecomputersociety.org/10.1109/AVSS.2017.8078481", "http://doi.org/10.1109/AVSS.2017.8078481"]}, {"id": "ba51ce1ec7b18fa808985b919f4a201fe5e4bafb", "title": "Semantic parsing for priming object detection in indoors RGB-D scenes", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/ba51/ce1ec7b18fa808985b919f4a201fe5e4bafb.pdf"], "doi": []}, {"id": "23e707600c3e9a240e24eaa4ed4b0e4ec6a436c1", "title": "Automatic foreground extraction via joint CRF and online learning", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/7f3b/115dd38a933f3a88e3b20b58862216297d63.pdf"], "doi": []}, {"id": "c5632e2117d268159225d5c307b7efbb6428ccba", "title": "Understanding image concepts using ISTOP model", "year": "2016", "pdf": ["http://www.cs.uu.nl/groups/MG/multimedia/publications/art/PR2016b.pdf"], "doi": ["http://doi.org/10.1016/j.patcog.2015.11.010"]}, {"id": "773fd71d3d24c268c99e1c53ae87a28da3bbe0f6", "title": "Conditional Entropies as Over-Segmentation and Under-Segmentation Metrics for Multi-Part Image Segmentation", "year": "2011", "pdf": [], "doi": []}, {"id": "0435a34e93b8dda459de49b499dd71dbb478dc18", "title": "VEGAC: Visual Saliency-based Age, Gender, and Facial Expression Classification Using Convolutional Neural Networks", "year": "2018", "pdf": [], "doi": []}, {"id": "02567fd428a675ca91a0c6786f47f3e35881bcbd", "title": "Deep Label Distribution Learning With Label Ambiguity", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.01731.pdf"], "doi": []}, {"id": "9ea7205ef136f207123cd6b54e15075835ae0049", "title": "Self-supervised language grounding by active sensing combined with Internet acquired images and text", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9ea7/205ef136f207123cd6b54e15075835ae0049.pdf"], "doi": []}, {"id": "6452d294af27b1f9408c9522bfb98bf00e1e4732", "title": "A novel infrared video surveillance system using deep learning based techniques", "year": "2018", "pdf": ["https://ore.exeter.ac.uk/repository/bitstream/handle/10871/32083/MTA-manuscript-revision-R2-accepted.pdf?isAllowed=y&sequence=1", "https://repository.edgehill.ac.uk/10281/6/MTA-manuscript-revision-R2.pdf"], "doi": ["https://doi.org/10.1007/s11042-018-5883-y"]}, {"id": "191beb87f84326d2cc9c427efe2a5abee8f67574", "title": "Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05462.pdf"], "doi": []}, {"id": "5020a75c45416073d0b07b1deb7382bc80de1779", "title": "Human Detection Using Learned Part Alphabet and Pose Dictionary", "year": "2014", "pdf": ["http://cis-linux1.temple.edu/~latecki/Papers/HumanDetectionECCV2014.pdf", "http://mc.eistar.net/UpLoadFiles/Papers/%5B38%5D%202014%20ECCV%20Yaocong.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/ECCV_2014/papers/8693/86930251.pdf", "https://cis.temple.edu/~latecki/Papers/HumanDetectionECCV2014.pdf"], "doi": ["http://doi.org/10.1007/978-3-319-10602-1_17"]}, {"id": "6e7248f33be3f6b44d6089b7039a5c2d84acaed0", "title": "Object cosegmentation using deep Siamese network", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02555.pdf"], "doi": []}, {"id": "b8ccc5341a1b0214e9d155b019962023f344c2ee", "title": "Incremental Learning of Object Detectors without Catastrophic Forgetting", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06977.pdf"], "doi": []}, {"id": "37668092cf8b7695d4a85eb7a25e9a2ef0fd0739", "title": "Robust object detection under partial occlusion", "year": "2016", "pdf": [], "doi": []}, {"id": "49f276e1b8fd162ac3cd996becc63cab2b2535b7", "title": "Trained 3D Models for CNN based Object Recognition", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/49f2/76e1b8fd162ac3cd996becc63cab2b2535b7.pdf"], "doi": []}, {"id": "1426045c4188f09fec46d0d2f246357a230a1748", "title": "Structured Labels in Random Forests for Semantic Labelling and Object Detection", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6784137", "http://doi.org/10.1109/TPAMI.2014.2315814", "https://www.ncbi.nlm.nih.gov/pubmed/26352638", "https://www.wikidata.org/entity/Q38404154"]}, {"id": "efe133717899b41cd4c0b0c999da312d3af60a6e", "title": "Depth-Based Hand Pose Estimation: Methods, Data, and Challenges", "year": "2018", "pdf": ["https://arxiv.org/pdf/1504.06378.pdf"], "doi": []}, {"id": "9caa7605c16da42761c8a27327f5f037dbf901fa", "title": "q-Gaussian mixture models for image and video semantic indexing", "year": "2013", "pdf": [], "doi": ["http://doi.org/10.1016/j.jvcir.2013.10.005", "http://t2r2.star.titech.ac.jp/rrws/file/CTT100664441/ATD100000413/"]}, {"id": "4bb84c9b24456fb0bb920ca83280bd9c48ad4b66", "title": "Instance-Level Video Segmentation from Object Tracks", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Seguin_Instance-Level_Video_Segmentation_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Seguin_Instance-Level_Video_Segmentation_CVPR_2016_paper.pdf", "http://www.di.ens.fr/willow/pdfscurrent/seguin2016.pdf", "http://www.di.ens.fr/willow/research/instancelevel/seguin16instancelevel.pdf", "http://www.di.ens.fr/~bojanowski/papers/seguin16instance.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780769", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.400", "http://doi.org/10.1109/CVPR.2016.400"]}, {"id": "ce0dbe6b1abecb54dcc98dbe652aa63d190dbc94", "title": "Part-Based Models for Finding People and Estimating Their Pose", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/ce0d/be6b1abecb54dcc98dbe652aa63d190dbc94.pdf"], "doi": []}, {"id": "a5683661e80668e05170bf17bcbd754d1b07af74", "title": "Comparison of Data Set Bias in Object Recognition Benchmarks", "year": "2015", "pdf": ["http://vfacstaff.ltu.edu/lshamir/publications/object_recognition_dataset_bias.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7299607", "http://doi.org/10.1109/ACCESS.2015.2491921"]}, {"id": "646a669f1dc38ae961fe41fbd3c83cab64ce9d53", "title": "Real-Time Seamless Single Shot 6D Object Pose Prediction", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578136"]}, {"id": "575a0e97702edcb0621a47b574949bac50e34200", "title": "Unsupervised Learning by Predicting Noise", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.05310.pdf"], "doi": []}, {"id": "b9128ff3b0b96815ff41a7d5fb2b4bef69f635ca", "title": "Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.04984.pdf"], "doi": []}, {"id": "7c03a0ad5202a6a31ad3b78b11f6b45ecd840616", "title": "Scale-Invariant Feature Learning using Deconvolutional Neural Networks for Weakly-Supervised Semantic Segmentation", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/7c03/a0ad5202a6a31ad3b78b11f6b45ecd840616.pdf"], "doi": []}, {"id": "17342b1c4caccfc499d9ae55a68d7b93285c5d6b", "title": "Action recognition in still images using a combination of human pose and context information", "year": "2012", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6466977", "http://doi.org/10.1109/ICIP.2012.6466977"]}, {"id": "571d2b173c2db8ac751dabdfcf5a18c06f365e05", "title": "Improved Part Segmentation Performance by Optimising Realism of Synthetic Images using Cycle Generative Adversarial Networks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06301.pdf"], "doi": []}, {"id": "90e36f66c25a4c73a252102c6c6c329c36d82676", "title": "Probably Unknown: Deep Inverse Sensor Modelling In Radar", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.08151.pdf"], "doi": []}, {"id": "fb710e9d897b7c1fd5275a0bcfa22711c5768990", "title": "A Graphical Model for Rapid Obstacle Image-Map Estimation from Unmanned Surface Vehicles", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/fb71/0e9d897b7c1fd5275a0bcfa22711c5768990.pdf"], "doi": []}, {"id": "821ba3eba1e36a29cc482f5378f4a0d0f6893159", "title": "Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.07926.pdf"], "doi": []}, {"id": "b50156e76ae03a1c0b04cd2076a99b7f2b441506", "title": "An image classification method that considers privacy-preservation", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1016/j.neucom.2016.04.056"]}, {"id": "3481a544e28cfc14108b0785eef7c12747e622ee", "title": "Online Multi-object Tracking via Structural Constraint Event Aggregation", "year": "2016", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/cvpr16_mot.pdf", "http://vc.cs.nthu.edu.tw/home/paper/codfiles/melu/201703210652/Online%20Multi-Object%20Tracking%20via%20Structural%20Constraint%20Event%20Aggregation.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Yoon_Online_Multi-Object_Tracking_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780524", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.155", "http://doi.org/10.1109/CVPR.2016.155"]}, {"id": "7fd5d2b0a034da43a747f6b8be3e51d775a05625", "title": "A Method to Detect Boats in Images of the Amazonian Rivers", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8247064", "http://doi.ieeecomputersociety.org/10.1109/BRACIS.2017.73", "http://doi.org/10.1109/BRACIS.2017.73"]}, {"id": "13105c611a059b4825bc92ff9778f532b6a849b2", "title": "Compressing Sparse Feature Vectors Using Random Ortho-Projections", "year": "2010", "pdf": ["http://www.ee.oulu.fi/mvg/files/pdf/PID1267977.pdf", "http://www.ee.oulu.fi/research/mvmp/mvg/files/pdf/PID1267977.pdf", "http://www.rni.helsinki.fi/~msa/pub/ICPR2010.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5597593", "http://doi.ieeecomputersociety.org/10.1109/ICPR.2010.345", "http://doi.org/10.1109/ICPR.2010.345"]}, {"id": "0967341790643f680f3fc9dc87bfe311723be4e4", "title": "A Perception-Driven Transcale Display Scheme for Space Image Sequences", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/0967/341790643f680f3fc9dc87bfe311723be4e4.pdf"], "doi": []}, {"id": "a8bf49021017e19df051a3efb7337d93ea263e37", "title": "Deep Multiple Instance Hashing for Object-based Image Retrieval", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a8bf/49021017e19df051a3efb7337d93ea263e37.pdf"], "doi": []}, {"id": "347ce37f15cea5bb8d0a676562664f80e3609b78", "title": "Pixel Objectness: Learning to Segment Generic Objects Automatically in Images and Videos", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.04702.pdf"], "doi": []}, {"id": "0755ee472e2bc2968b16f851a16c39b3f3e2d0d0", "title": "From Weakly Supervised Object Localization to Semantic Segmentation by Probabilistic Image Modeling", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8227436", "http://doi.org/10.1109/DICTA.2017.8227436"]}, {"id": "659fc2a483a97dafb8fb110d08369652bbb759f9", "title": "Improving the Fisher Kernel for Large-Scale Image Classification", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/659f/c2a483a97dafb8fb110d08369652bbb759f9.pdf"], "doi": []}, {"id": "1e02dfeb93e8fd8753d2e69baf705baf8996cb81", "title": "Online Object Tracking, Learning and Parsing with And-Or Graphs", "year": "2014", "pdf": ["https://arxiv.org/pdf/1509.08067.pdf"], "doi": []}, {"id": "bdfb5f11d497b44b17d0315c3b6892f835723832", "title": "Object Captioning and Retrieval with Natural Language", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.06152.pdf"], "doi": []}, {"id": "43fe9006b90137d6ce85a539685ce66c13f0e38e", "title": "A review of image-based automatic facial landmark identification techniques", "year": "", "pdf": ["https://pdfs.semanticscholar.org/43fe/9006b90137d6ce85a539685ce66c13f0e38e.pdf"], "doi": []}, {"id": "642772c38ff690d17a3ce84a1d8646aefc802139", "title": "VIDEO OBJECT TRACKING BASED ON AUTOMATIC BACKGROUND SEGMENTATION : A SURVEY", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/6427/72c38ff690d17a3ce84a1d8646aefc802139.pdf"], "doi": []}, {"id": "303c08071500421c3aca758e6c7cd6a9fcbda1a8", "title": "Scene understanding with complete scenes and structured representations", "year": "2014", "pdf": [], "doi": []}, {"id": "86f0f71bff42e4bdc60014e4f94ec76d52c8eccf", "title": "Felzenszwalb-Baum-Welch: Event Detection by Changing Appearance", "year": "2013", "pdf": ["https://arxiv.org/pdf/1306.4746.pdf"], "doi": []}, {"id": "d9cc8bc5c4a4b29ab40f75b721bd9e5140d2baf6", "title": "Object Detection for Crime Scene Evidence Analysis Using Deep Learning", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/6926/4f28158f9245a06f7a2c1ae666241261cc0e.pdf"], "doi": []}, {"id": "d3f6b3ce8f7b67c1e112a79b3fe9764242c655f5", "title": "Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354202"]}, {"id": "9b6538d09e914c41345812b3086feff1dc1ae218", "title": "Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.08937.pdf"], "doi": []}, {"id": "bf417e1c265b31720b4fb980afb83cc3a573fa6f", "title": "Representations and Similarities of Images for Visual Classification", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bf41/7e1c265b31720b4fb980afb83cc3a573fa6f.pdf"], "doi": []}, {"id": "4dc57432fa8fea1614a39c324bf11ae0620cb26f", "title": "Aalborg Universitet Detection of U . S . Traffic", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/6e53/63af2bfb7d1b2bd13feb41c2688bd0cf12b3.pdf"], "doi": []}, {"id": "878169be6e2c87df2d8a1266e9e37de63b524ae7", "title": "Image interpretation above and below the object level.", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/8781/69be6e2c87df2d8a1266e9e37de63b524ae7.pdf"], "doi": []}, {"id": "3daafe6389d877fe15d8823cdf5ac15fd919676f", "title": "Human Action Localization with Sparse Spatial Supervision", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.05197.pdf"], "doi": []}, {"id": "04f9b591cdfa1e3667230ae1224b1dfdac0a8ef1", "title": "Discriminative Segment Annotation in Weakly Labeled Video", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619165"]}, {"id": "4e4f2c4d2ea47636ca2ab795770d6b3214640f37", "title": "Efficient Maximum Appearance Search for Large-Scale Object Detection", "year": "2013", "pdf": ["http://researcher.watson.ibm.com/researcher/files/us-liangliang.cao/qiangcvpr2013_final.pdf", "http://rogerioferis.com/publications/ChenCVPR2013.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d190.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Chen_Efficient_Maximum_Appearance_2013_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619254", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.410", "http://doi.org/10.1109/CVPR.2013.410"]}, {"id": "9434524669777d281a8a7358f20181c9e157942e", "title": "VSEM: An open library for visual semantics representation", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/9434/524669777d281a8a7358f20181c9e157942e.pdf"], "doi": []}, {"id": "0e0900b88c33b671be5dd2ded9885b6526d6b429", "title": "From captions to visual concepts and back", "year": "2015", "pdf": ["https://arxiv.org/pdf/1411.4952.pdf"], "doi": []}, {"id": "4d910c5ab0b70ddbef6be944077ed63821608135", "title": "On Dimensionality Reduction for Indexing and Retrieval of Large-Scale Solar Image Data", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/4d91/0c5ab0b70ddbef6be944077ed63821608135.pdf"], "doi": []}, {"id": "9076183dcdb28ebb3e547f7ffd3f9d5d0faec531", "title": "Describing Video Contents in Natural Language", "year": "2012", "pdf": [], "doi": []}, {"id": "07764e1607d9e3d8094455adb658077996eb38c4", "title": "End-to-End Trained CNN Encoder-Decoder Networks for Image Steganography", "year": "2018", "pdf": ["https://arxiv.org/pdf/1711.07201.pdf"], "doi": []}, {"id": "46f135110c5fc5f158bc3ffce21b9ae946c7ff68", "title": "Adaptive NormalHedge for robust visual tracking", "year": "2015", "pdf": ["https://core.ac.uk/download/pdf/33581176.pdf", "https://pure.qub.ac.uk/portal/files/13941301/main_huiyu.pdf"], "doi": ["https://doi.org/10.1016/j.sigpro.2014.08.027"]}, {"id": "b961009dedea99f948650df7291a28f18bbfc1dc", "title": "Towards Automated Visual Monitoring of Individual Gorillas in the Wild", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265544"]}, {"id": "7dbc61e2dc497e9dcff98e7df832780cc8a2b60c", "title": "A Flexible Object-of-Interest Annotation Framework for Online Video Portals", "year": "2012", "pdf": ["http://www.mdpi.com/1999-5903/4/1/179/pdf"], "doi": ["https://doi.org/10.3390/fi4010179"]}, {"id": "d4f454b24a7901dea14858808bbe277c7bee8ffb", "title": "Edge-based Component-Trees for Multi-Channel Image Segmentation", "year": "2017", "pdf": [], "doi": []}, {"id": "6768b558cc58e113096540c123ef3b2c2d2469a1", "title": "Maximum Margin Linear Classifiers in Unions of Subspaces", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/1a06/e518bf15015153b4973bb2e9e06e51485a4c.pdf"], "doi": []}, {"id": "ba6c19771926564e89be4ace7c33dc3da580249e", "title": "Utilisation du contexte pour l'indexation s\u00e9mantique des images et vid\u00e9os. (Using context for semantic indexing of images and videos)", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/ba6c/19771926564e89be4ace7c33dc3da580249e.pdf"], "doi": []}, {"id": "447b28c347172c6da0fb4d764a534fdee557b7f8", "title": "Studying Relationships between Human Gaze, Description, and Computer Vision", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6618945"]}, {"id": "782b21e803d149955c627c063ae60efeae04a9b1", "title": "Analysis of Multilayer Neural Networks for Object Recognition", "year": "2014", "pdf": [], "doi": []}, {"id": "3e01f2fefe219bfeb112f1d82e76ebba4c0e2aac", "title": "Transfer learning via attributes for improved on-the-fly classification", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6836097", "http://doi.ieeecomputersociety.org/10.1109/WACV.2014.6836097", "http://doi.org/10.1109/WACV.2014.6836097"]}, {"id": "ba156b81fe8fca1fd1bfb1c822e39205c4ff355b", "title": "Unsupervised Multi-class Joint Image Segmentation", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909798"]}, {"id": "72048081cfe678f700c52e1c7a56713a8e0865b6", "title": "Unsupervised Adversarial Visual Level Domain Adaptation for Learning Video Object Detectors from Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02074.pdf"], "doi": []}, {"id": "9cd8a2d07f07d888fcf50aa0735d0831edcf5e46", "title": "Bag of contour fragments for robust shape classification", "year": "2014", "pdf": ["http://cis-linux1.temple.edu/~latecki/Papers/XinggangPR2014.pdf", "http://mc.eistar.net/~xwang/pubs/BagOfShape.pdf", "http://mclab.eic.hust.edu.cn/~xwang/pubs/BagOfShape.pdf", "https://cis.temple.edu/~latecki/Papers/XinggangPR2014.pdf"], "doi": ["http://doi.org/10.1016/j.patcog.2013.12.008"]}, {"id": "8c21cd8d5e98c77d727fc900450c6223f9e1fa24", "title": "DARE: Dynamic Adaptive Mobile Augmented Reality with Edge Computing", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8526799"]}, {"id": "7fe203374ba3ddc8462a7c775b276e53f09dd036", "title": "NavigationNet: A Large-scale Interactive Indoor Navigation Dataset", "year": "2018", "pdf": ["https://arxiv.org/pdf/1808.08374.pdf"], "doi": []}, {"id": "8f8599012002dd3bbb6526b3be92d7a7355ad22a", "title": "Construction et \u00e9valuation d'un corpus pour la recherche d'instances d'images mus\u00e9ales", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/8f85/99012002dd3bbb6526b3be92d7a7355ad22a.pdf"], "doi": []}, {"id": "ebf35073e122782f685a0d6c231622412f28a53b", "title": "A High-Quality Denoising Dataset for Smartphone Cameras", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578280"]}, {"id": "9463f71b2d8e291d5fc5a7db6b95b3d01e759b29", "title": "Describing Spatial Relationships between Objects in Images in English and French", "year": "2015", "pdf": ["http://www.emnlp2015.org/proceedings/VL/pdf/VL16.pdf"], "doi": ["https://doi.org/10.18653/v1%2FW15-2816", "http://aclweb.org/anthology/W15-2816", "https://doi.org/10.18653/v1/W15-2816"]}, {"id": "aaa6fe8045e1a071e1762cffe4f59e0bd508daf9", "title": "Single-Pedestrian Detection Aided by Two-Pedestrian Detection", "year": "2015", "pdf": ["http://www.ee.cuhk.edu.hk/~wlouyang/Papers/tpami15-ouyang_xgWang_xyZeng.pdf", "http://www.ee.cuhk.edu.hk/~xgwang/papers/ouyangZWtpami15.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6994306", "http://doi.ieeecomputersociety.org/10.1109/TPAMI.2014.2377734", "http://doi.org/10.1109/TPAMI.2014.2377734", "https://www.ncbi.nlm.nih.gov/pubmed/26353133"]}, {"id": "2a7007555f71e559c6aa33efbd3bd8b401638d82", "title": "Full interpretation of minimal images", "year": "2018", "pdf": ["https://perso.telecom-paristech.fr/bloch/AIC/articles/BenYosef2017.pdf"], "doi": ["https://www.sciencedirect.com/science/article/pii/S001002771730269X?dgcid=api_sd_search-api-endpoint", "http://doi.org/10.1016/j.cognition.2017.10.006", "https://www.ncbi.nlm.nih.gov/pubmed/29107889"]}, {"id": "08c71fe89af5f168b373e92b44a7cf9d1755fb8c", "title": "The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition", "year": "2013", "pdf": ["http://infoscience.epfl.ch/record/182860/files/2013_ChavarriagaPRLETTERS_preprint.pdf?version=1", "https://www.researchgate.net/profile/Ricardo_Chavarriaga/publication/258031577_The_Opportunity_challenge_A_benchmark_database_for_on-body_sensor-based_activity_recognition/links/02e7e528146aa12213000000.pdf"], "doi": ["https://doi.org/10.1016/j.patrec.2012.12.014"]}, {"id": "8d73906f0a232e8b94200017e512446c1af4dd9d", "title": "Detection of U.S. Traffic Signs", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7116530"]}, {"id": "497857bce6ea1ed4889fb949a2f176072e2509c7", "title": "A Comparison of L_1 Norm and L_2 Norm Multiple Kernel SVMs in Image and Video Classification", "year": "2009", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5137808"]}, {"id": "1d5f704a98d82c34de96ceb80fa06552082effd3", "title": "Dynamic Zoom-in Network for Fast Object Detection in Large Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578822"]}, {"id": "3de71ddc07619c0dd6bbaa3f7b412a9262a0e761", "title": "Discriminatively Trained And-Or Tree Models for Object Detection", "year": "2013", "pdf": ["http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d278.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Song_Discriminatively_Trained_And-Or_2013_CVPR_paper.pdf", "http://www.stat.ucla.edu/~sczhu/papers/Conf_2013/DiscriminativeAOG_cvpr2013.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619265", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.421", "http://doi.org/10.1109/CVPR.2013.421"]}, {"id": "18b4a20ed465972d9d8f3f8d8982d321acf45907", "title": "Mod\u00e9lisation de contextes pour l'annotation s\u00e9mantique de vid\u00e9os. (Context based modeling for video semantic annotation)", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/18b4/a20ed465972d9d8f3f8d8982d321acf45907.pdf"], "doi": []}, {"id": "992a614aa601c52b20729538ea25b62471ffe8bc", "title": "Towards Automatic Construction of Diverse, High-quality Image Dataset", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.06495.pdf"], "doi": []}, {"id": "53822d61e829ef02a95a6c89fea082114fd3e16b", "title": "A General Framework for Tracking Multiple People from a Moving Camera", "year": "2013", "pdf": ["http://www.willowgarage.com/sites/default/files/pami_preprint.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6361406", "http://doi.org/10.1109/TPAMI.2012.248", "https://www.ncbi.nlm.nih.gov/pubmed/23681988", "https://www.wikidata.org/entity/Q48723090"]}, {"id": "323eb410e0d0978901a8baa670f905f280ab19ff", "title": "Inner-Scene Similarities as a Contextual Cue for Object Detection", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.04406.pdf"], "doi": []}, {"id": "7532996c27b199ed89b412a9f0df7483df83ea72", "title": "Committees of deep feedforward networks trained with few data", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.5947.pdf"], "doi": []}, {"id": "bf7238df8b3a7fc0ebf0e8028a417c7e99fca8d8", "title": "An ontology-based framework for the automated analysis and interpretation of comic books' images", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1016/j.ins.2016.10.032", "https://hal.archives-ouvertes.fr/hal-01387033/document"]}, {"id": "c6e042f9db094d3a01c13a9d3120fc6898f40cb8", "title": "Multi-label Classification for Image Annotation via Sparse Similarity Voting", "year": "2010", "pdf": ["http://naosite.lb.nagasaki-u.ac.jp/dspace/bitstream/10069/27087/1/LNCS6469_344.pdf", "https://page-one.springer.com/pdf/preview/10.1007/978-3-642-22819-3_35"], "doi": ["https://doi.org/10.1007/978-3-642-22819-3_35"]}, {"id": "2dd6749ddffa620d2ac40275a436ecd89aa51a45", "title": "Learning Dual Multi-Scale Manifold Ranking for Semantic Segmentation of High-Resolution Images", "year": "2017", "pdf": ["http://www.mdpi.com/2072-4292/9/5/500/pdf"], "doi": ["https://doi.org/10.3390/rs9050500", "https://www.preprints.org/manuscript/201704.0061/v1/download"]}, {"id": "478261574ddc6cf297611000735aa9808f8f0030", "title": "ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.04405.pdf"], "doi": []}, {"id": "c5fcc36768428185c0ec0f04c82c9204c9ba962c", "title": "Deep Material-Aware Cross-Spectral Stereo Matching", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578303"]}, {"id": "e4fc560a78e48bd927c2f6253f5fc489927bb15f", "title": "Detecting objects in internet videos AIMS Project Report", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/e4fc/560a78e48bd927c2f6253f5fc489927bb15f.pdf"], "doi": []}, {"id": "2049db406168f63c46e5efd2d5ceb5941e3fdc7c", "title": "Region detection and matching for object recognition", "year": "2013", "pdf": [], "doi": []}, {"id": "e42b89b6ed1c6d79286a62ded1e4c090f474eb40", "title": "Using image analytics to monitor retail store shelves", "year": "2015", "pdf": [], "doi": ["https://doi.org/10.1147/JRD.2015.2394513"]}, {"id": "64fb6a04a3ec96b2ad266c381c75f4dc16ce3460", "title": "Hole-based traffic sign detection method for traffic signs with red rim", "year": "2013", "pdf": [], "doi": ["https://doi.org/10.1007/s00371-013-0879-0"]}, {"id": "24c20c28871fa923c3f45b745b9b9f2d3d280e81", "title": "Harmony potentials for joint classification and segmentation", "year": "2010", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5540048"]}, {"id": "06f1c079303937f6022e6157e6341c7921fe9428", "title": "Efficient Dense Rigid-Body Motion Segmentation and Estimation in RGB-D Video", "year": "2014", "pdf": ["http://ais.uni-bonn.de/papers/IJCV_2015_Stueckler_Motion_Segmentation.pdf", "http://www.ais.uni-bonn.de/papers/IJCV_2015_Stueckler_Motion_Segmentation.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0796-3"]}, {"id": "333b877ea761c5c1d4ffa39654fc19bd015e245d", "title": "Ontology-Based Semantic Image Segmentation Using Mixture Models and Multiple CRFs", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7450190"]}, {"id": "0ecaabbf846bbc78c91bf7ff71b998b61c0082d8", "title": "Automated Visual Fin Identification of Individual Great White Sharks", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.06323.pdf"], "doi": []}, {"id": "28863c0f3a1aa186bf1c281c73784cf36e2bf361", "title": "Efficient Non-iterative Domain Adaptation of Pedestrian Detectors to Video Scenes", "year": "2014", "pdf": ["http://eprints.whiterose.ac.uk/84865/1/ICPR14.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6976833", "http://doi.org/10.1109/ICPR.2014.123"]}, {"id": "054738ce39920975b8dcc97e01b3b6cc0d0bdf32", "title": "Towards the design of an end-to-end automated system for image and video-based recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1601.07883.pdf"], "doi": []}, {"id": "4446924885545b255164b32e42b8375bac699f23", "title": "Object semantic categorization based on ensemble SVM classifiers", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7867229"]}, {"id": "fc2c39b6439623c00b10e8d9826b1c82e8487805", "title": "Generalized Semantic Preserving Hashing for N-Label Cross-Modal Retrieval", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Mandal_Generalized_Semantic_Preserving_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099765", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.282", "http://doi.org/10.1109/CVPR.2017.282"]}, {"id": "92cd808bba43c3702d8cbddde65ee42bf01676d4", "title": "A MultiPath Network for Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.02135.pdf"], "doi": []}, {"id": "3bccc5621b14f2e6b07a5936acecdf957724c6ff", "title": "Convolutional Fisher Kernels for RGB-D Object Recognition", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7335478", "http://doi.ieeecomputersociety.org/10.1109/3DV.2015.23", "http://doi.org/10.1109/3DV.2015.23"]}, {"id": "0b67879b1d5db9da12490b41b4f52d12626e87bc", "title": "The KIT object models database: An object model database for object recognition, localization and manipulation in service robotics", "year": "2012", "pdf": ["http://ijr.sagepub.com/content/31/8/927.full.pdf"], "doi": ["https://doi.org/10.1177/0278364912445831"]}, {"id": "98b4bf8cf8890f50b12e4fabe78bafd687a598c2", "title": "Semantic Labeling Based Vehicle Detection in Aerial Imagery", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354178"]}, {"id": "e03a2299caf2febcc7b87ee4e61e78ad8cb24e45", "title": "Combined Holistic and Local Patches for Recovering 6D Object Pose", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265469"]}, {"id": "26eadb307d62ab28713931beb8be9ff0f04c6ea0", "title": "Synthetic Viewpoint Prediction", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7801548", "http://doi.ieeecomputersociety.org/10.1109/CRV.2016.58", "http://doi.org/10.1109/CRV.2016.58"]}, {"id": "55d01b7314d78fe3bc5ae03b6e414ecba14188f8", "title": "Cognitive Inspired WOR Framework to Reveal Image Semantics, for Efficient Content Based Image Retrieval", "year": "2015", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2709034"]}, {"id": "05e9e85b5137016c93d042170e82f77bb551a108", "title": "A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation", "year": "2016", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Perazzi_A_Benchmark_Dataset_CVPR_2016_paper.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_poster_cvpr_2016.pdf", "https://graphics.ethz.ch/~perazzif/davis/files/davis_supplementary.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780454", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.85", "http://doi.org/10.1109/CVPR.2016.85"]}, {"id": "64bff565c83c6ce3fac783d8d67191af99803701", "title": "Learning to Co-Generate Object Proposals with a Deep Structured Network", "year": "2016", "pdf": ["http://infoscience.epfl.ch/record/217984/files/HayderHeSalzmannCVPR16.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Hayder_Learning_to_Co-Generate_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780650", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.281", "http://doi.org/10.1109/CVPR.2016.281"]}, {"id": "66dcc6771e35068a1ea2f6e6f4cdb9a40a4df450", "title": "A Linear Approximation to the chi^2 Kernel with Geometric Convergence", "year": "2012", "pdf": ["https://arxiv.org/pdf/1206.4074.pdf"], "doi": []}, {"id": "dbf2d57def648d1dae7717c92a32ff02157e5cb5", "title": "RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.01054.pdf"], "doi": []}, {"id": "2284ba28bd3b1afaf06afb8c2a94638e350b3ecb", "title": "Boosting Object Proposals: From Pascal to COCO", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Pont-Tuset_Boosting_Object_Proposals_ICCV_2015_paper.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01226.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410538", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.181", "http://doi.org/10.1109/ICCV.2015.181"]}, {"id": "174b6d661b96840e27cd9435c2dbb8e538b2c8a6", "title": "Progressive Representation Adaptation for Weakly Supervised Object Localization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1710.04647.pdf"], "doi": []}, {"id": "b95cdaaa0d6c191bcc8169ce555219ad545258fb", "title": "Online streaming feature selection: a minimum redundancy, maximum significance approach", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s10044-018-0690-7"]}, {"id": "0f780a8cb09627bec41000345c2771df2853224a", "title": "Automatic inspection of aeronautic components", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1007/s00138-017-0839-1"]}, {"id": "c1206330ba57a27fd0acc29dd39825bbf2d91060", "title": "A Shape Reconstructability Measure of Object Part Importance with Applications to Object Detection and Localization", "year": "2014", "pdf": ["http://www.stat.ucla.edu/~yuille/Pubs10_12/PartImportance_IJCV2014_online.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0705-9"]}, {"id": "4c500c84e16e5ebb50b33f9bcff36854e5131c16", "title": "All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification", "year": "2016", "pdf": ["https://arxiv.org/pdf/1711.04450.pdf"], "doi": []}, {"id": "02f86370fd467f0d03948a94a346034d8a111ffd", "title": "Semantic Video Retrieval Using High Level Context", "year": "2008", "pdf": ["https://pdfs.semanticscholar.org/02f8/6370fd467f0d03948a94a346034d8a111ffd.pdf"], "doi": []}, {"id": "d111faa1990f80e3351ea1eef0e5fc177d4e44b4", "title": "Iteratively Training Look-Up Tables for Network Quantization", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.05355.pdf"], "doi": []}, {"id": "165c27a4bfb56562c807279bef9d15f1bced5ca0", "title": "Scene parsing using inference Embedded Deep Networks", "year": "2016", "pdf": ["http://www.adv-ci.com/publications/2016_PR_Bu.pdf"], "doi": ["http://doi.org/10.1016/j.patcog.2016.01.027"]}, {"id": "f348d23a88fd81e05585897629f2f230fcfe77c7", "title": "Transfer Learning of Deep Neural Networks for Visual Collaborative Maritime Asset Identification", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8537839"]}, {"id": "87fe38a79ee12531bb618d4006a476b3a5256f3e", "title": "Relative Saliency and Ranking: Models, Metrics, Data, and Benchmarks", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.02426.pdf"], "doi": []}, {"id": "d8b8e165279ca2091d5af1440ed974db4792250f", "title": "Mean Response-Time Minimization of a Soft-Cascade Detector", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/ad73/ff39869e223dba6e0ee94481b6c32766df86.pdf"], "doi": []}, {"id": "0f6a2ea69c325bcbfca85fb05cb5f542873b1bf8", "title": "Food Recognition and Detection with Minimum Supervision", "year": "2016", "pdf": [], "doi": []}, {"id": "df8aee8aef6f0c71f968979318dafcd53da04bdc", "title": "Bending the Curve: Improving the ROC Curve Through Error Redistribution", "year": "2016", "pdf": ["https://arxiv.org/pdf/1605.06652.pdf"], "doi": []}, {"id": "70918453e9f147747b7a37d9159c8c1515a55ae4", "title": "Visual object tracking via the local soft cosine similarity", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1016/j.patrec.2018.03.026"]}, {"id": "1876095a9387a84e594d81675c9c2c17cb10f7cf", "title": "Accurate segmentation of complex document image using digital shearlet transform with neutrosophic set as uncertainty handling tool", "year": "2017", "pdf": ["http://fs.gallup.unm.edu/neut/AccurateSegmentationOfComplex.pdf"], "doi": ["http://doi.org/10.1016/j.asoc.2017.08.005"]}, {"id": "ad52d047a44f20416f9dd6655cef54169d481454", "title": "Perceptual modeling in the problem of active object recognition in visual scenes", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1016/j.patcog.2016.03.007"]}, {"id": "e096b11b3988441c0995c13742ad188a80f2b461", "title": "DeepProposals: Hunting Objects and Actions by Cascading Deep Convolutional Layers", "year": "2017", "pdf": ["https://arxiv.org/pdf/1606.04702.pdf"], "doi": []}, {"id": "56e95fa26fb417776824e5adf6d6d511e5b30110", "title": "Object and Action Classification with Latent Window Parameters", "year": "2013", "pdf": ["http://homepages.inf.ed.ac.uk/hbilen/assets/pdf/Bilen14.pdf", "http://www.cse.iitk.ac.in/users/cs365/2014/_papers/bilen-namboodri-vanGool-13_object-action-classify-latent-windows.pdf", "http://www.cse.iitk.ac.in/users/vinaypn/papers/bilen2013ijcv.pdf"], "doi": ["http://doi.org/10.1007/s11263-013-0646-8"]}, {"id": "e7df750805d6c025d0a1a74a05a83bcf8cc63dd7", "title": "Assessment of crowdsourcing and gamification loss in user-assisted object segmentation", "year": "2015", "pdf": ["http://upcommons.upc.edu/bitstream/handle/2117/81293/asknseek.pdf;jsessionid=469B72384B7C56D4A331D68A53942294?sequence=1"], "doi": ["https://doi.org/10.1007/s11042-015-2897-6"]}, {"id": "85eedee59aca5f2a591265a2173cf3a2799cdc94", "title": "Action and Event Recognition with Fisher Vectors on a Compact Feature Set", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751336"]}, {"id": "3463aeda3a8d33bc88d8383cc4ad451a6775c75a", "title": "Understanding Indoor Scenes Using 3D Geometric Phrases", "year": "2013", "pdf": ["http://courses.cs.washington.edu/courses/cse590v/13au/choi_cvpr13.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989a033.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Choi_Understanding_Indoor_Scenes_2013_CVPR_paper.pdf", "https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/41340.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6618856", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.12", "http://doi.org/10.1109/CVPR.2013.12"]}, {"id": "70b420850e16ec2afe42d5c0006742d9045b3e7f", "title": "If You Can't Beat Them, Join Them: Learning with Noisy Data", "year": "2015", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2806231"]}, {"id": "985b6a10c1bb9c8908d6d299c7ab0bba76df2259", "title": "Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018/papers/Bilinski_Dense_Decoder_Shortcut_CVPR_2018_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578788", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2018.00690", "http://doi.org/10.1109/CVPR.2018.00690"]}, {"id": "82451d0ae2e0154b5f9cd096af199c35319e911a", "title": "Image spam filtering using convolutional neural networks", "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1007/s00779-018-1168-8"]}, {"id": "8ff6294535acf46abf523b879f20685de0692a8c", "title": "Bayes Risk for Large Scale Hierarchical Top-K Image Classification", "year": "2013", "pdf": ["https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/153936/eth-6877-01.pdf?isAllowed=y&sequence=1"], "doi": ["https://doi.org/10.3929/ethz-a-009767867"]}, {"id": "d97224063697392f073e467005e89973d2be7d65", "title": "Recherche de motifs fr\u00e9quents dans une base de cartes combinatoires. (Frequent pattern discovery in combinatorial maps databases)", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/02d1/8e600804a1a6ff354856d8dcb80ceb4c8a43.pdf"], "doi": []}, {"id": "74a1336f1fbc8b7bb3b6e159711af1a91336ce22", "title": "An overview of traffic sign detection methods", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/74a1/336f1fbc8b7bb3b6e159711af1a91336ce22.pdf"], "doi": []}, {"id": "e33bc0cd79d92d6868989a29c3ab06b75f808590", "title": "Deep Nets: What have they ever done for Vision?", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.04025.pdf"], "doi": []}, {"id": "0b4d3e59a0107f0dad22e74054bab1cf1ad9c32e", "title": "Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.07332.pdf"], "doi": []}, {"id": "14d1a458f49e251cbbab34349e379469300a2bae", "title": "Scene Parsing with Object Instances and Occlusion Ordering", "year": "2014", "pdf": ["http://slazebni.cs.illinois.edu/publications/jtighe-cvpr14.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Tighe_Scene_Parsing_with_2014_CVPR_paper.pdf", "http://wwwx.cs.unc.edu/~mn/sites/default/files/jtighe-cvpr14.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909874", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.479", "http://doi.org/10.1109/CVPR.2014.479"]}, {"id": "a6cd743c29667ab5baef9d66d6558247b1cd00b0", "title": "New in-situ training image and one-shot detection model without adaptation GENETIM detection model for synset bottle", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/a6cd/743c29667ab5baef9d66d6558247b1cd00b0.pdf"], "doi": []}, {"id": "9b8746e9480c3bdcaa6efca33096369422c624aa", "title": "Algae Detection Using Computer Vision and Deep Learning", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10847.pdf"], "doi": []}, {"id": "3325860c0c82a93b2eac654f5324dd6a776f609e", "title": "2D Human Pose Estimation: New Benchmark and State of the Art Analysis", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909866"]}, {"id": "896e2776174dcb86d311789ab83a266151d0595b", "title": "A Novel Performance Evaluation Methodology for Single-Target Trackers", "year": "2016", "pdf": ["https://arxiv.org/pdf/1503.01313.pdf"], "doi": []}, {"id": "bf26ccc92bca086195c5f250aef2e409a1c7cd85", "title": "Local Bayes Risk Minimization Based Stopping Strategy for Hierarchical Classification", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8215524", "http://doi.ieeecomputersociety.org/10.1109/ICDM.2017.61", "http://doi.org/10.1109/ICDM.2017.61"]}, {"id": "ff3a9545e73adea5275a1c7c71c5e3fe2e35a9a1", "title": "An Enhanced Feature Extraction Technique for Diagnosis of Pathological Problems in Mango Crop", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/ff3a/9545e73adea5275a1c7c71c5e3fe2e35a9a1.pdf"], "doi": []}, {"id": "21d1225296aad388406824eb113715c4b90ed3da", "title": "Dirichlet-Based Concentric Circle Feature Transform for Breast Mass Classification", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7372146", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2015.50", "http://doi.org/10.1109/ICTAI.2015.50"]}, {"id": "3f0b0ffe315ee111fc028561ec4ecf2c93f94a05", "title": "Pose Normalization Network for Object Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/3f0b/0ffe315ee111fc028561ec4ecf2c93f94a05.pdf"], "doi": []}, {"id": "75b987f86af2bc7f68edc45be240dd30e1ef2699", "title": "Sampling Algorithms to Handle Nuisances in Large-Scale Recognition", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/75b9/87f86af2bc7f68edc45be240dd30e1ef2699.pdf"], "doi": []}, {"id": "6a405e7284ff7e2127a241d60646b4abd3da92f2", "title": "Generate To Adapt : Unsupervised Domain Adaptation using Generative Adversarial Networks", "year": "2017", "pdf": [], "doi": []}, {"id": "c0e551acb063c9cd73dea28ab8963f850b6f1148", "title": "A Comparison of Techniques based on Image Classification and Object Detection to Count Cars and Non-empty Stalls in Parking Spaces", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/c0e5/51acb063c9cd73dea28ab8963f850b6f1148.pdf"], "doi": []}, {"id": "8b45a87f3dfc8eccd745161effbf2457a9097e6a", "title": "WEAKLY SUPERVISED SEMANTIC SEGMENTATION 3 priors can give good pixel labelling results", "year": "2017", "pdf": [], "doi": []}, {"id": "25d75339720787e7003f2f103cf38cee8175972a", "title": "Optimistic and Pessimistic Neural Networks for Scene and Object Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.07982.pdf"], "doi": []}, {"id": "12d9a4233a16ea08fbb1de853b6a97b4f4952c23", "title": "Tractable Structured Prediction using the Permutohedral Lattice", "year": "2017", "pdf": ["https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-01.pdf?isAllowed=y&sequence=1", "https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/130429/eth-50807-02.pdf?isAllowed=y&sequence=2"], "doi": ["https://doi.org/10.3929/ethz-a-010882665"]}, {"id": "33d101fe276fd5e6220c9b40c33e1a1d1389e5bb", "title": "DOC: DEEP OCCLUSION ESTIMATION FROM A SIN-", "year": "2016", "pdf": [], "doi": []}, {"id": "c6c691b772822881c5c52b779100928f0d54fdd7", "title": "Using Visual Saliency to Improve Human Detection with Convolutional Networks", "year": "2018", "pdf": [], "doi": []}, {"id": "11a3084768f035c824662a85a348f02466693d2a", "title": "Lifting Object Detection Datasets into 3D", "year": "2016", "pdf": ["https://arxiv.org/pdf/1503.06465.pdf"], "doi": []}, {"id": "4be10db13a9210e078d78a4a072c569d9bbd9939", "title": "Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.06098.pdf"], "doi": []}, {"id": "18a849b1f336e3c3b7c0ee311c9ccde582d7214f", "title": "Efficiently Scaling Up Crowdsourced Video Annotation A Set of Best Practices for High Quality , Economical Video Labeling", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/18a8/49b1f336e3c3b7c0ee311c9ccde582d7214f.pdf"], "doi": []}, {"id": "13e424d502bf539108ad6f5cc877cfb1255dbee0", "title": "Improving Vision-Based Self-Positioning in Intelligent Transportation Systems via Integrated Lane and Vehicle Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7045914"]}, {"id": "1dbd7653ede6af15d539f64cb2128752ca029e44", "title": "Hollywood 3D: Recognizing Actions in 3D Natural Scenes", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619280"]}, {"id": "f4c45108cb41051010d8a5175b8da23eb246c967", "title": "Improving Image Captioning by Leveraging Knowledge Graphs", "year": "2019", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8658870"]}, {"id": "1b3ee5455956a40c6e9e09ccda0f4fb162838629", "title": "The Recognition of License Plate Restrictions Based on Faster R-CNN", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/1b3e/e5455956a40c6e9e09ccda0f4fb162838629.pdf"], "doi": []}, {"id": "5c45a1abc51fe059987bcfba19b1d5076a8d9afb", "title": "Autonomous Object Category Learning for Service Robots Using Internet Resources", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5c45/a1abc51fe059987bcfba19b1d5076a8d9afb.pdf"], "doi": []}, {"id": "4a31b3fcc346bf3235efe1c0fb310833570cef27", "title": "Learning Intelligent Dialogs for Bounding Box Annotation", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579054"]}, {"id": "ed62a56b81511d7fcf6d247014987163d9668982", "title": "\"What happens if...\" Learning to Predict the Effect of Forces in Images", "year": "2016", "pdf": ["https://arxiv.org/pdf/1603.05600.pdf"], "doi": []}, {"id": "29aa3dc15450e6eb46c34f30f0e224e5ea16615e", "title": "Sketch Me That Shoe", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Yu_Sketch_Me_That_CVPR_2016_paper.pdf", "http://vision.cs.utexas.edu/381V-fall2016/slides/hsiao_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Yu_Sketch_Me_That_CVPR_2016_paper.pdf", "https://www.eecs.qmul.ac.uk/~qian/SketchMeThatShoe.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780462", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.93", "http://doi.org/10.1109/CVPR.2016.93"]}, {"id": "1999d5e0700bf8fa50bb1bab5b981bda1d111a4f", "title": "Monocular Road Terrain Detection by Combining Visual and Spatial Information", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/73b1/10df4809d0a015f90fa6e7a7dce351bcc52e.pdf", "https://www.researchgate.net/profile/Jannik_Fritsch/publication/261073577_Monocular_Road_Terrain_Detection_by_Combining_Visual_and_Spatial_Information/links/5475ef240cf29afed612e5a8.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6766705", "http://doi.org/10.1109/TITS.2014.2303899"]}, {"id": "34072c31c2c778df471c9f0c43ba6198dfd0db32", "title": "Arbitrary Category Classification of Websites Based on Image Content", "year": "2015", "pdf": ["http://users.ics.aalto.fi/juha/papers/ELM2014.pdf", "http://www.engineering.uiowa.edu/sites/default/files/files/newpaper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7083681", "http://doi.org/10.1109/MCI.2015.2405317"]}, {"id": "d23ac99cdab20a9a3eca2784a5b262649c717988", "title": "Rotation Invariant Angular Descriptor Via A Bandlimited Gaussian-like Kernel", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.02753.pdf"], "doi": []}, {"id": "22cf367d14e646914cc959bbcd402df0c20cd0dc", "title": "Towards Automated Melanoma Screening: Proper Computer Vision & Reliable Results", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.04024.pdf"], "doi": []}, {"id": "c9d73438bf5e66bd0c4f512c5a4e53c3e33e721e", "title": "Adding spatial distribution clue to aggregated vector in image retrieval", "year": "2018", "pdf": ["https://jivp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13640-018-0247-0?site=jivp-eurasipjournals.springeropen.com"], "doi": ["http://doi.org/10.1186/s13640-018-0247-0"]}, {"id": "a74b045f28670e8f85173e0e483581520d667f02", "title": "Object tracking using Langevin Monte Carlo particle filter and locality sensitive histogram based likelihood model", "year": "2018", "pdf": [], "doi": ["http://doi.org/10.1016/j.cag.2017.07.023"]}, {"id": "c56da136b8d62125009a131f6dc21fcd0dd6a559", "title": "ICDAR2017 Robust Reading Challenge on Text Extraction from Biomedical Literature Figures (DeTEXT)", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8270166", "http://doi.ieeecomputersociety.org/10.1109/ICDAR.2017.235", "http://doi.org/10.1109/ICDAR.2017.235"]}, {"id": "02e5372e439c09f8a8ce8c4784b044ce116ca11c", "title": "DeepCorrect: Correcting DNN models against Image Distortions", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02406.pdf"], "doi": []}, {"id": "e8b2a98f87b7b2593b4a046464c1ec63bfd13b51", "title": "CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1606.05413.pdf"], "doi": []}, {"id": "5fdbebf417da2427744d2c60f413b5375e68993e", "title": "Discriminative Sub-categorization", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619062"]}, {"id": "32bebe84ffbd4fd81f0e5bb30dbc90774aa3b14b", "title": "Segmentation Results Stimuli Final Saliency Map Ground Truth Constructed Graph CCA", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/32be/be84ffbd4fd81f0e5bb30dbc90774aa3b14b.pdf"], "doi": []}, {"id": "a02e5d8e2a10176dc5e2566e1b492823a0cb6ee2", "title": "A learning framework for higher-order consistency models in multi-class pixel labeling problems", "year": "2014", "pdf": [], "doi": []}, {"id": "383d64b27fb3cdf2beff43f3beb8caac8c21a886", "title": "Detecting activities of daily living in first-person camera views", "year": "2012", "pdf": ["http://people.csail.mit.edu/hpirsiav/papers/adl_cvpr12.pdf", "http://people.csail.mit.edu/hpirsiav/papers/adl_cvpr12_poster.pdf", "http://people.csail.mit.edu/hpirsiav/papers/adl_cvpr12_slides.pdf", "http://vision.ics.uci.edu/papers/PirsiavashR_CVPR_2012_1/PirsiavashR_CVPR_2012_1.pdf", "http://web.cs.hacettepe.edu.tr/~erkut/bil722.f12/w06-cagdas.pdf", "http://www.cs.utexas.edu/~cv-fall2012/slides/dinesh-expt.pdf", "http://www.ics.uci.edu/~dramanan/papers/ADL_2012.pdf", "https://www.cs.cmu.edu/~deva/papers/ADL_2012.pdf", "https://www.csee.umbc.edu/~hpirsiav/papers/adl_cvpr12.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6248010", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2012.6248010", "http://doi.org/10.1109/CVPR.2012.6248010"]}, {"id": "5e0f8c355a37a5a89351c02f174e7a5ddcb98683", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"], "doi": []}, {"id": "64c1158a4061882d610f1cffd5ddb1e8fc9a74b4", "title": "Gated Feedback Refinement Network for Dense Image Labeling", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Islam_Gated_Feedback_Refinement_CVPR_2017_paper.pdf", "http://www.cs.umanitoba.ca/~ywang/papers/cvpr17.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100001", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.518", "http://doi.org/10.1109/CVPR.2017.518"]}, {"id": "284be8be0c6bedc36dfe43229bc84345ab0aedc2", "title": "Faster Training of Mask R-CNN by Focusing on Instance Boundaries", "year": "2018", "pdf": ["https://arxiv.org/pdf/1809.07069.pdf"], "doi": []}, {"id": "be2d326fa588b4ffd1d8d3d4408ae680e1a26277", "title": "JOURNA A Survey on Modern Era \u2019 s Online Object Tracking Algorithms", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/be2d/326fa588b4ffd1d8d3d4408ae680e1a26277.pdf"], "doi": []}, {"id": "2a2232f2972191a0606d588aa4f13c9f27d1972d", "title": "InstanceCut: From Edges to Instances with MultiCut", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.08272.pdf"], "doi": []}, {"id": "029cabb6f3f6a824590e735feb1d8557646db8a6", "title": "One-Bit Object Detection: On learning to localize objects with minimal supervision", "year": "2014", "pdf": ["https://arxiv.org/pdf/1403.1024.pdf"], "doi": []}, {"id": "fd23dda0abe2d6a3ae0c8253c89110364cdecbc9", "title": "Deep Learning for People Detection on Beach Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575616", "http://doi.ieeecomputersociety.org/10.1109/BRACIS.2018.00045", "http://doi.org/10.1109/BRACIS.2018.00045"]}, {"id": "c3c4f0caf1b42b6466306360c4ebe16f66489df0", "title": "Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.11266.pdf"], "doi": []}, {"id": "03fd6774f57aaed9320060e4527121c59e9eca2b", "title": "Intrinsic spatial pyramid matching for deformable 3D shape retrieval", "year": "2013", "pdf": [], "doi": ["https://doi.org/10.1007/s13735-013-0041-9"]}, {"id": "304aa9bfd6bc32d3d87abce6a229d973270bbd73", "title": "Fast Neural Cell Detection Using Light-Weight SSD Neural Network", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w8/papers/Yi_Fast_Neural_Cell_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8014853", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.119", "http://doi.org/10.1109/CVPRW.2017.119"]}, {"id": "c8ba499e8d8daa32637885f03137f41d61023bf9", "title": "Weak supervision for detecting object classes from activities", "year": "2017", "pdf": ["https://ps.is.tue.mpg.de/uploads_file/attachment/attachment/296/weak_supervision_object_detection.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2016.09.006"]}, {"id": "cd1a636c1261208084cb8395c877c7ca22c76df1", "title": "Fast Deep Vehicle Detection in Aerial Images", "year": "2017", "pdf": ["https://www.computer.org/csdl/proceedings/wacv/2017/4822/00/07926624.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7926624", "http://doi.org/10.1109/WACV.2017.41"]}, {"id": "101c7305f141145c4d168dfa40284e0ad86a0d9b", "title": "Active Object Localization with Deep Reinforcement Learning", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410643"]}, {"id": "48922520e6de0954a83f26977b2b50b7fbfdcf61", "title": "A survey of sketch-based image retrieval", "year": "2018", "pdf": [], "doi": ["https://doi.org/10.1007/s00138-018-0953-8"]}, {"id": "c37fe13f94dfc2f3494a35a63336689ce4392135", "title": "MPNET: An End-to-End Deep Neural Network for Object Detection in Surveillance Video", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8365094", "http://doi.org/10.1109/ACCESS.2018.2836921"]}, {"id": "0f8f9253c81fd90fe44d474cc185d4ae2487e5b4", "title": "NYC3DCars: A Dataset of 3D Vehicles in Geographic Context", "year": "2013", "pdf": ["http://nyc3d.cs.cornell.edu/static/paper.pdf", "http://www.cs.cornell.edu/~snavely/publications/papers/nyc3dcars_iccv13.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Matzen_NYC3DCars_A_Dataset_2013_ICCV_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751204", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.99", "http://doi.org/10.1109/ICCV.2013.99"]}, {"id": "e8ffef3d4d74720e766e506e175e533bdc8ee705", "title": "Object Detection Networks on Convolutional Feature Maps", "year": "2017", "pdf": ["https://arxiv.org/pdf/1504.06066.pdf"], "doi": []}, {"id": "1daf971c087f5e21dbae831231377cbe9bb2f188", "title": "Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619272"]}, {"id": "8d74fbd46f9d5d615e350c4593cbc5b5ca63fa8b", "title": "Data driven visual tracking via representation learning and online multi-class LPBoost learning", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1049/iet-cvi.2014.0388"]}, {"id": "7af667b6c1b4b32f513dd70fe3ef36fcf344a741", "title": "A transfer learning based approach for automated grading of Gliomas using deep Residual Networks", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/7af6/67b6c1b4b32f513dd70fe3ef36fcf344a741.pdf"], "doi": []}, {"id": "d9dafc343727db2b6060c868d748f97eff6bac7d", "title": "Improved pedestrian detection using motion segmentation and silhouette orientation", "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1007/s11042-017-4933-1"]}, {"id": "3b304585d5af0afe98a85d6e0559315fbf3a7807", "title": "An Improved Labelling for the INRIA Person Data Set for Pedestrian Detection", "year": "2013", "pdf": ["http://welcome.isr.ist.utl.pt/img/pdfs/2999_2013_IbPRIA_Taiana_Nascimento_Bernardino.pdf", "http://welcome.isr.tecnico.ulisboa.pt/wp-content/uploads/2015/05/2999_2013_IbPRIA_Taiana_Nascimento_Bernardino.pdf"], "doi": ["http://doi.org/10.1007/978-3-642-38628-2_34"]}, {"id": "99df9e95b3f3d187636918a65277baf7c98cbfc5", "title": "An efficient subsequence search for video anomaly detection and localization", "year": "2015", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-015-2453-4", "https://www.wikidata.org/entity/Q56907428"]}, {"id": "832246357de85108cb910e773c203997448c570a", "title": "Recurrently Target-Attending Tracking", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780530"]}, {"id": "74031f12dde0be772a742b96bf5f4c8d9fa41ec7", "title": "Joint Object-Material Category Segmentation from Audio-Visual Cues", "year": "2015", "pdf": ["https://arxiv.org/pdf/1601.02220.pdf"], "doi": []}, {"id": "9452d029f5d140aece06619b6fd8e47b070cacd1", "title": "Urban classification by pixel and object-based approaches for very high resolution imagery", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/9452/d029f5d140aece06619b6fd8e47b070cacd1.pdf"], "doi": []}, {"id": "7268747251a61d1ce3285baade15c372d4c566d6", "title": "Person Attribute Recognition with a Jointly-Trained Holistic CNN Model", "year": "2015", "pdf": ["http://web-info8.informatik.rwth-aachen.de/media/papers/sudowe_spitzer_leibe_ICCV_LaP_2015.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w11/papers/Sudowe_Person_Attribute_Recognition_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7406400", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2015.51", "http://doi.org/10.1109/ICCVW.2015.51"]}, {"id": "81763bb718dc6630be210c056a250b1c2ed57fd7", "title": "3D Semantic Parsing of Large-Scale Indoor Spaces", "year": "2016", "pdf": ["http://buildingparser.stanford.edu/images/CVPR_2016_poster.pdf", "http://buildingparser.stanford.edu/images/supp_mat.pdf", "http://openaccess.thecvf.com/content_cvpr_2016/papers/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780539", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.170", "http://doi.org/10.1109/CVPR.2016.170"]}, {"id": "9d5db7427b44d83bf036ff4cff382c23c6c7b6d8", "title": "Video redaction: a survey and comparison of enabling technologies", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f78d/6d092deaafee550fb58d6ea6e8b559325876.pdf"], "doi": []}, {"id": "a228ba020bd321d29ab24485cb2988a62707fd64", "title": "Using objective ground-truth labels created by multiple annotators for improved video classification: A comparative study", "year": "2013", "pdf": ["https://engineering.purdue.edu/RVL/Publications/Srivastava2013.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2013.06.009"]}, {"id": "037f2e9d2d2aa15c3d476f4aa358da96707b4b44", "title": "Square Localization for Efficient and Accurate Object Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410651"]}, {"id": "bf3aae7293f664d512c0904916d804327af22f52", "title": "STDnet: A ConvNet for Small Target Detection", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/bf3a/ae7293f664d512c0904916d804327af22f52.pdf"], "doi": []}, {"id": "d6b514a68abff3ab14af9fc0152cd5b28bd0192c", "title": "Instance Segmentation by Deep Coloring", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.10007.pdf"], "doi": []}, {"id": "0de46e6768acaa71745406d646573644b975dc62", "title": "Scene-Domain Active Part Models for Object Representation", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410644"]}, {"id": "e24792ec2a6cb8971b2f6befb4b97b9fe2d79952", "title": "Bottom-up Object Detection by Grouping Extreme and Center Points", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08043.pdf"], "doi": []}, {"id": "1d7029a974f950de61f3980704956b43f1a06e7b", "title": "Efficient Optimization for Rank-Based Loss Functions", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578487"]}, {"id": "22a8b7ca2e6449cad31ae4f71bb3587751087e77", "title": "DeepBox: Learning Objectness with Convolutional Networks", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410642"]}, {"id": "9c4365a56fb3cf41b15712657b15f7422ca0dab2", "title": "A Hybrid Supervised-Unsupervised Vocabulary Generation Algorithm for Visual Concept Recognition", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/9c43/65a56fb3cf41b15712657b15f7422ca0dab2.pdf"], "doi": []}, {"id": "37b9ea1bf5b6ce8ecb656628af3933c64c632c2b", "title": "Transfer Learning for 3 D LiDAR-based Human Classification with a Mobile Robot", "year": "2018", "pdf": [], "doi": []}, {"id": "f79c4bf83371627ba139b61eb427463b93cd687b", "title": "Learning from Few Examples for Visual Recognition Problems", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/f79c/4bf83371627ba139b61eb427463b93cd687b.pdf"], "doi": []}, {"id": "084bd219dd239dc4c9a02621a5333d3bc1446566", "title": "DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking", "year": "2015", "pdf": ["https://arxiv.org/pdf/1503.00072.pdf"], "doi": []}, {"id": "1c9da6cef6b1be9c116b26dd52c341c0adcf7db2", "title": "Interactive Perception: Leveraging Action in Perception and Perception in Action", "year": "2017", "pdf": ["https://arxiv.org/pdf/1604.03670.pdf"], "doi": []}, {"id": "549c719c4429812dff4d02753d2db11dd490b2ae", "title": "YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video", "year": "2017", "pdf": ["https://arxiv.org/pdf/1702.00824.pdf"], "doi": []}, {"id": "e430d1ae3a28ec342f767cdfb19aeb76c20a3f21", "title": "Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8592805"]}, {"id": "3b4ad6b789837a6a878f33c0b7ddb1b1fc7daaf8", "title": "Fine-grained recognition of plants from images", "year": "2017", "pdf": ["https://plantmethods.biomedcentral.com/track/pdf/10.1186/s13007-017-0265-4?site=plantmethods.biomedcentral.com"], "doi": ["https://doi.org/10.1186/s13007-017-0265-4", "https://www.ncbi.nlm.nih.gov/pubmed/29299049"]}, {"id": "f92ceb6875f614bbccb25e4b11ca55353773890f", "title": "Saliency Detection via Boundary Prior and Center Prior", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f92c/eb6875f614bbccb25e4b11ca55353773890f.pdf"], "doi": []}, {"id": "828b73e8a4d539eeae82601b5f5a4392818c6430", "title": "Long-Term Tracking by Decision Making", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/828b/73e8a4d539eeae82601b5f5a4392818c6430.pdf"], "doi": []}, {"id": "2114b25727a21275e88e30dad0423752f6047dae", "title": "Generic Visual Recognition on Non-Uniform Distributions Based on AdaBoost Codebooks", "year": "2011", "pdf": ["https://pdfs.semanticscholar.org/cac0/c534e02784a3a873690d213dd8c92b81992f.pdf"], "doi": []}, {"id": "7cb4d30b3bfb0d4b02499c15c7c7a9dfddda8049", "title": "Object Tracking using L 1 / L 2 Sparse Coding and Multi Scale Max Pooling", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/7cb4/d30b3bfb0d4b02499c15c7c7a9dfddda8049.pdf"], "doi": []}, {"id": "b7efecec654acd8831d045e728b54356c697c9c8", "title": "Learning Semantic Segmentation with Diverse Supervision", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354268"]}, {"id": "eacb95e81156c48f4ff7470567ba205225170fa7", "title": "Learning Aerial Image Segmentation From Online Maps", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06879.pdf"], "doi": []}, {"id": "14b311b848b51b7b5345573a289b1cedcbb4d581", "title": "Instance Similarity Deep Hashing for Multi-Label Image Retrieval", "year": "2018", "pdf": ["https://arxiv.org/pdf/1803.02987.pdf"], "doi": []}, {"id": "24ff832171cb774087a614152c21f54589bf7523", "title": "Beat-Event Detection in Action Movie Franchises", "year": "2015", "pdf": ["https://arxiv.org/pdf/1508.03755.pdf"], "doi": []}, {"id": "ffd73d1956163a4160ec2c96b3ab256f79fc92e8", "title": "Attributes as Semantic Units between Natural Language and Visual Recognition", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.03249.pdf"], "doi": []}, {"id": "99c37dba394b100ba8f3d895c0ee0e57d5852347", "title": "Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects", "year": "2014", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2014/papers/Zia_Are_Cars_Just_2014_CVPR_paper.pdf", "http://resources.mpi-inf.mpg.de/publications/D2/2014/zia14cvpr.pdf", "http://www.igp.ethz.ch/photogrammetry/publications/pdf_folder/cvpr2014zz.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909865", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.470", "http://doi.org/10.1109/CVPR.2014.470"]}, {"id": "f6b649023e49a341f042f9a17b2f923db58ccf35", "title": "Feature representation of RGB-D images using joint spatial-depth feature pooling", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1016/j.patrec.2016.04.001"]}, {"id": "f9f86d087e84eaf0e6a09575982aa7b41fa62451", "title": "Image Synthesis for Self-Supervised Visual Representation Learning", "year": "2018", "pdf": [], "doi": ["https://www.base-search.net/Record/6ecfef13a126fd20b941bbb80477b94bd643db70d224a43b1d0b0cb61aa181b1"]}, {"id": "b85c198ce09ffc4037582a544c7ffb6ebaeff198", "title": "Efficient Multiple Instance Metric Learning Using Weakly Supervised Data", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Law_Efficient_Multiple_Instance_CVPR_2017_paper.pdf", "http://www.cs.toronto.edu/~law/publications/CVPR/2017/mimlca_cvpr_2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100113", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.630", "http://doi.org/10.1109/CVPR.2017.630"]}, {"id": "c77c094faf7b1a4e293609a0909c7c50b468675a", "title": "Satyam: Democratizing Groundtruth for Machine Vision", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.03621.pdf"], "doi": []}, {"id": "2a5667702b0f1ff77dde8fb3e2e10d4e05e8de9d", "title": "Scene Parsing through ADE20K Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhou_Scene_Parsing_Through_CVPR_2017_paper.pdf", "http://people.csail.mit.edu/bzhou/publication/scene-parse-camera-ready.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100027", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2017.544", "http://doi.org/10.1109/CVPR.2017.544"]}, {"id": "a422c2bd9030c8a2c89b6db79be2743c4a4609fb", "title": "Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.02886.pdf"], "doi": []}, {"id": "46a1172c784c3741e79781ef2353209b08dbea67", "title": "YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shot Recognition", "year": "2013", "pdf": ["http://www.cs.utexas.edu/users/ml/papers/guadarrama.iccv13.pdf", "http://www.cs.utexas.edu/users/ml/posters/guadarrama.iccv13.pdf", "http://www.eecs.berkeley.edu/~sguada/pdfs/2013-ICCV-YouTube2Text-final.pdf", "https://www.cs.utexas.edu/~vsub/pdf/YouTube2Text_Recognizing_and_2013_ICCV_paper.pdf", "https://www.icsi.berkeley.edu/pubs/vision/youtube2text13.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751448", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.337", "http://doi.org/10.1109/ICCV.2013.337"]}, {"id": "670b10569c5f978ee70d99cf8c14ad9cabb9d454", "title": "Masked face detection via a modified LeNet", "year": "2016", "pdf": [], "doi": ["http://doi.org/10.1016/j.neucom.2016.08.056"]}, {"id": "4acf31294e940d85a4eea56c244205e3a66d8b8e", "title": "Improving Product Classification Using Images", "year": "2011", "pdf": ["http://talukdar.net/papers/ImageText-ICDM2011.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6137235", "http://doi.ieeecomputersociety.org/10.1109/ICDM.2011.79", "http://doi.org/10.1109/ICDM.2011.79"]}, {"id": "057f5ffda59a3412f1e62159e96f84faa352628e", "title": "Tracking with scattering descriptor", "year": "2014", "pdf": [], "doi": ["http://doi.org/10.1049/iet-cvi.2013.0124"]}, {"id": "4404a99e2f6db3e703609168a3595e0fbdeabc38", "title": "Online Video SEEDS for Temporal Window Objectness", "year": "2013", "pdf": ["http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Van_Den_Bergh_Online_Video_SEEDS_2013_ICCV_paper.pdf", "http://www.mvdblive.org/research/videoseeds.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_01056.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751156", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.54", "http://doi.org/10.1109/ICCV.2013.54"]}, {"id": "59ee0f67bcf2d8ea0bbbfcbc71159725fc3a7059", "title": "Object Detection with Appearance-based Mixture Models Anonymous CVPR submission", "year": "2010", "pdf": ["https://pdfs.semanticscholar.org/59ee/0f67bcf2d8ea0bbbfcbc71159725fc3a7059.pdf"], "doi": []}, {"id": "e478c322de923337627487d8a688f5922b45b2ff", "title": "Automatic Garage Door Opening Using License Plate Recognition and Fingerprint Verification", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/e478/c322de923337627487d8a688f5922b45b2ff.pdf"], "doi": []}, {"id": "8a3b481d8e06b4acf6e95d8bc2484016f5862668", "title": "Text Detection in Traffic Informatory Signs Using Synthetic Data", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8270075", "http://doi.ieeecomputersociety.org/10.1109/ICDAR.2017.144", "http://doi.org/10.1109/ICDAR.2017.144"]}, {"id": "7c594c0b9482624745dd95767f3eebde1ee7f043", "title": "Representing Visual Scenes for Robot Control", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/7c59/4c0b9482624745dd95767f3eebde1ee7f043.pdf"], "doi": []}, {"id": "0ceda9dae8b9f322df65ca2ef02caca9758aec6f", "title": "Context-Aware CNNs for Person Head Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410688"]}, {"id": "5f0e9cc18374a670dfea4698424c9d48494f3093", "title": "Online Domain Adaptation for Multi-Object Tracking", "year": "2015", "pdf": ["https://arxiv.org/pdf/1508.00776.pdf"], "doi": []}, {"id": "d47d72afc590f5b96117a5227d45157135da21ad", "title": "Attribute-based knowledge transfer learning for human pose estimation", "year": "2013", "pdf": [], "doi": ["http://doi.org/10.1016/j.neucom.2012.05.032"]}, {"id": "05db46c7745c360fa5938ee204c81efdcc84c1da", "title": "An Empirical Evaluation of Current Convolutional Architectures\u2019 Ability to Manage Nuisance Location and Scale Variability", "year": "2016", "pdf": ["https://arxiv.org/pdf/1505.06795.pdf"], "doi": []}, {"id": "0d4cdadd765c3003b0bd5f762b84bef93408f548", "title": "Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909618"]}, {"id": "5d16ce0c66cd87dd48cb8c53f5b6a7ee73d33abb", "title": "Robust and Real-Time Object Tracking Using Scale-Adaptive Correlation Filters", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7797075", "http://doi.org/10.1109/DICTA.2016.7797075"]}, {"id": "050e5b4043009e54dff9319877fe947885db2d6e", "title": "Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Lai_Saliency_Guided_Dictionary_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Lai_Saliency_Guided_Dictionary_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780764", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.395", "http://doi.org/10.1109/CVPR.2016.395"]}, {"id": "926dd1c4db38356ac5bf87c1a4c6b93625f9a850", "title": "Pulling Actions out of Context: Explicit Separation for Effective Combination", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578834"]}, {"id": "b705ca751a947e3b761e2305b41891051525d9df", "title": "Exploring Context with Deep Structured Models for Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1603.03183.pdf"], "doi": []}, {"id": "be48b5dcd10ab834cd68d5b2a24187180e2b408f", "title": "Constrained Low-Rank Learning Using Least Squares-Based Regularization", "year": "2017", "pdf": ["https://arxiv.org/pdf/1611.04870.pdf"], "doi": []}, {"id": "b2f63863e73a8565895ca3d9d7d6a1e10a7695b1", "title": "Efficient Neural Network Compression via Transfer Learning for Industrial Optical Inspection", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b2f6/3863e73a8565895ca3d9d7d6a1e10a7695b1.pdf"], "doi": []}, {"id": "044ae9738c2445d4fda30fcd6c289eddf8b3add9", "title": "Multiple Instance Learning: A Survey of Problem Characteristics and Applications", "year": "2018", "pdf": ["https://arxiv.org/pdf/1612.03365.pdf"], "doi": []}, {"id": "2ba540ca70c7dee81e13768792aa7571952987f6", "title": "Drivable Road Detection Based on Dilated FPN with Feature Aggregation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8372075", "http://doi.ieeecomputersociety.org/10.1109/ICTAI.2017.00172", "http://doi.org/10.1109/ICTAI.2017.00172"]}, {"id": "6c9f45c76b4f96fe66d8e1d7b31f89b7cc6caa44", "title": "DeNet: Scalable Real-Time Object Detection with Directed Sparse Sampling", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.10295.pdf"], "doi": []}, {"id": "a0ae4ffe252f32514240cf6d82d52538de5fb78c", "title": "AN ALGORITHM FOR PEDESTRIAN DETECTION IN MULTISPECTRAL IMAGE SEQUENCES", "year": "", "pdf": ["https://pdfs.semanticscholar.org/a0ae/4ffe252f32514240cf6d82d52538de5fb78c.pdf"], "doi": []}, {"id": "115e8a4f76a57b893c985ea4f7530b90d071679c", "title": "FSSD: Feature Fusion Single Shot Multibox Detector", "year": "2017", "pdf": ["https://arxiv.org/pdf/1712.00960.pdf"], "doi": []}, {"id": "92f2639dbd9f7c4284b7012809e4d2c407834774", "title": "Point-based Medialness 2 D Shape Description and Identification", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/92f2/639dbd9f7c4284b7012809e4d2c407834774.pdf"], "doi": []}, {"id": "4ace7c8edd9467c7d5bfa00e942531e7b889e650", "title": "Depth-Based Hand Pose Estimation: Data, Methods, and Challenges", "year": "2015", "pdf": ["http://vision.ics.uci.edu/papers/SupancicRYSR_ICCV_2015/SupancicRYSR_ICCV_2015.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Supancic_Depth-Based_Hand_Pose_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410574", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.217", "http://doi.org/10.1109/ICCV.2015.217"]}, {"id": "4c454fda214e00c9cba4bb759da78949a4130873", "title": "Specialization of a Generic Pedestrian Detector to a Specific Traffic Scene by the Sequential Monte-Carlo Filter and the Faster R-CNN", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/4c45/4fda214e00c9cba4bb759da78949a4130873.pdf"], "doi": []}, {"id": "f541dac9d0d49cadb3cfd018e87b26e03e3f13aa", "title": "Trio Constrained Adaptive Noise Removal ( TCANR ) Mechanism for Salt and Pepper Noise in Image Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/f541/dac9d0d49cadb3cfd018e87b26e03e3f13aa.pdf"], "doi": []}, {"id": "aa2ad3df24d8d8c4a4d2fe85f0d4e635d595f0a2", "title": "PedCut: an iterative framework for pedestrian segmentation combining shape models and multiple data cues", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/c029/edca476ddda4050c3c67748056c6189cd1e3.pdf"], "doi": []}, {"id": "d250e57f6b7e06bb1dac41c8b89700086a85999e", "title": "Self-Supervised Generalisation with Meta Auxiliary Learning", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.08933.pdf"], "doi": []}, {"id": "de35ea60396629b2d1ceb73df56a97ed21012680", "title": "Robust object tracking via multi-scale patch based sparse coding histogram", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1007/s11042-016-3289-2"]}, {"id": "a0e286f3c6a72c857ffd03bd8ab9a9f9b98c4432", "title": "AI Learns to Recognize Bengali Handwritten Digits: Bengali.AI Computer Vision Challenge 2018", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.04452.pdf"], "doi": []}, {"id": "19339e816d8006ad462868b01812b03eb463ead1", "title": "Collective activity localization by spatiality preservation search", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1080/01691864.2016.1172506", "https://www.wikidata.org/entity/Q58025855"]}, {"id": "899e7ff67aa2630edc8776758cc5d65823f099c1", "title": "G-CNN: Object Detection via Grid Convolutional Neural Network", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8097417", "http://doi.org/10.1109/ACCESS.2017.2770178"]}, {"id": "139ab79a0aae5d4346f907b7b29288d09ef373fa", "title": "A Baseline for Multi-Label Image Classification Using Ensemble Deep CNN", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08412.pdf"], "doi": []}, {"id": "94780b00dc2807ec507ae91500b622ec7a8ddb12", "title": "Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.06295.pdf"], "doi": []}, {"id": "fa496716a5b8520e94a0126b5baa4f636623c997", "title": "Revisiting Knowledge Transfer for Training Object Class Detectors", "year": "2018", "pdf": ["https://arxiv.org/pdf/1708.06128.pdf"], "doi": []}, {"id": "c2cb4da617168c76c4560a01de8b5e68b5250749", "title": "FineTag: Multi-attribute Classification at Fine-grained Level in Images", "year": "2018", "pdf": ["https://arxiv.org/pdf/1806.07124.pdf"], "doi": []}, {"id": "87d5b53580ca5f77ccc3ff157337ef3456308943", "title": "Augmented Autoencoders for object orientation estimation trained on synthetic RGB images", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/87d5/b53580ca5f77ccc3ff157337ef3456308943.pdf"], "doi": []}, {"id": "eb2333a759788903848c49111a03c4c00d188e70", "title": "Color-based and Rotation Invariant Self-similarities", "year": "2017", "pdf": ["http://www.scitepress.org/Papers/2017/61075/61075.pdf"], "doi": ["https://doi.org/10.5220/0006107503440351"]}, {"id": "af9cc1767f50f63291d7ca9ab709f6849cd1e46c", "title": "Graph-Driven Diffusion and Random Walk Schemes for Image Segmentation.", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/af9c/c1767f50f63291d7ca9ab709f6849cd1e46c.pdf"], "doi": []}, {"id": "4fe91feab83d947a0d3bd85adcf18ab1b3d9e05f", "title": "Transductive People Tracking in Unconstrained Surveillance", "year": "2016", "pdf": ["http://imagelab.ing.unimore.it/Pubblicazioni/pubblicazioni/2015TCSVT.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7067436", "http://doi.org/10.1109/TCSVT.2015.2416555"]}, {"id": "8eaade06b75dac977574d05ce1058b86df059d47", "title": "Indoor Scene Understanding with RGB-D Images: Bottom-up Segmentation, Object Detection and Semantic Segmentation", "year": "2014", "pdf": ["http://people.eecs.berkeley.edu/~sgupta/pdf/ijcv14a.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0777-6"]}, {"id": "b9b21cfa7de32677151571ab44d27d2d246b7a03", "title": "Towards Explanation of DNN-based Prediction with Guided Feature Inversion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.00506.pdf"], "doi": []}, {"id": "4152d2c8585f7e3f85d3b3d84036171de104cbd7", "title": "Rethinking ImageNet Pre-training", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.08883.pdf"], "doi": []}, {"id": "b31f37fd71b7b45e6fd8978960e271a7db1ee212", "title": "DICTING IMAGE ROTATIONS", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/b31f/37fd71b7b45e6fd8978960e271a7db1ee212.pdf"], "doi": []}, {"id": "149f3cc167b046dc790b1f4f1c48eeb31e898403", "title": "A study of vehicle detector generalization on U.S. highway", "year": "2016", "pdf": ["http://cvrr.ucsd.edu/publications/2016/0669.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7795567", "http://doi.org/10.1109/ITSC.2016.7795567"]}, {"id": "1a1654456decd116f4ca84c98006dfda0a8a3134", "title": "INTEGRATED VISUAL INFORMATION FOR MARITIME SURVEILLANCE", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1a16/54456decd116f4ca84c98006dfda0a8a3134.pdf"], "doi": []}, {"id": "3e00dd86c084d8680409c65c1a48f1b3aa864eb7", "title": "Deep Crisp Boundaries: From Boundaries to Higher-Level Tasks", "year": "2019", "pdf": ["https://arxiv.org/pdf/1801.02439.pdf"], "doi": []}, {"id": "1e5edbd39b4c61f785515e117a74e2d280aefbe7", "title": "The urrent tate and TRL ssessment of eople racking echnology for ideo urveillance pplications", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/1e5e/dbd39b4c61f785515e117a74e2d280aefbe7.pdf"], "doi": []}, {"id": "2e1f0b522014c942197e51b556eeb48b6ad66cda", "title": "Automatic object classification using motion blob based local feature fusion for traffic scene surveillance", "year": "2012", "pdf": [], "doi": ["http://doi.org/10.1007/s11704-012-1296-7"]}, {"id": "25858dc59faf2630bf0eefe23297ce262370cff0", "title": "Monitoring Giraffe Behavior in Thermal Video", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7046812"]}, {"id": "e545f1c06799bfd2bd5f7eaed085fd60a388202f", "title": "A top-down manner-based DCNN architecture for semantic image segmentation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/e545/f1c06799bfd2bd5f7eaed085fd60a388202f.pdf"], "doi": []}, {"id": "7b3a63d030d03e536ddcbc217bc8d6fd630e3b53", "title": "xView: Objects in Context in Overhead Imagery", "year": "2018", "pdf": ["https://arxiv.org/pdf/1802.07856.pdf"], "doi": []}, {"id": "4a6049e1926cc8e574301cfb229599cdc0a64e62", "title": "Characterizing the performance of an image-based recognizer for planar mechanical linkages in textbook graphics and hand-drawn sketches", "year": "2015", "pdf": ["http://vdel.me.cmu.edu/publications/2015cag/paper.pdf"], "doi": ["http://doi.org/10.1016/j.cag.2015.06.002"]}, {"id": "ec6f1a4b9367675833f0111c44a22ba217fcbd23", "title": "Visual Tracking via Constrained Incremental Non-negative Matrix Factorization", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7045563", "http://doi.org/10.1109/LSP.2015.2404856"]}, {"id": "5950512e21114236208b9eaeebc9a09735e367a6", "title": "Master research Internship Internship report Segmentation and recognition of symbols for printed and handwritten music scores", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/5950/512e21114236208b9eaeebc9a09735e367a6.pdf"], "doi": []}, {"id": "c7780cff11068fecb322a43e459c56267a88aee7", "title": "DeepVoting: An Explainable Framework for Semantic Part Detection under Partial Occlusion", "year": "2017", "pdf": [], "doi": []}, {"id": "98bf42055160845e6f8f3c022298e3b8e4e55f80", "title": "Vision Meets Drones: A Challenge", "year": "2018", "pdf": ["https://arxiv.org/pdf/1804.07437.pdf"], "doi": []}, {"id": "19b6b0649cc669791c799c52fc56bdc556f06916", "title": "Efficient Model Evaluation with Bilinear Separation Model", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7045964"]}, {"id": "cf58f90e14b49ce35548d89c7339b7fc4db9ba4f", "title": "Generating Diverse Image Datasets with Limited Labeling", "year": "2016", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=2967285"]}, {"id": "4ff486644be5e451784d6ae83f8073c8320fa974", "title": "Visual Tracking with Convolutional Neural Network", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7379494", "http://doi.org/10.1109/SMC.2015.362"]}, {"id": "a43f460f6c1abbe8eb0097594df6eafc0f651d49", "title": "Saliency-based object recognition in video", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/a43f/460f6c1abbe8eb0097594df6eafc0f651d49.pdf"], "doi": []}, {"id": "b4df58f1fd8a3bd0815e7fb957f7f07fddd77338", "title": "Rethinking the sGLOH Descriptor", "year": "2018", "pdf": ["http://cvg.dsi.unifi.it/colombo_now/CC/Public/sGLOH2_TPAMI_2017.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7911291", "http://doi.org/10.1109/TPAMI.2017.2697849", "https://www.ncbi.nlm.nih.gov/pubmed/28459683", "https://www.wikidata.org/entity/Q38811217"]}, {"id": "ceee9ba72a021ae5604db04a93fdcff421d60216", "title": "Encoder Based Lifelong Learning", "year": "2017", "pdf": ["https://arxiv.org/pdf/1704.01920.pdf"], "doi": []}, {"id": "c4a0e89793961dc486964802df55ae73fbba60ee", "title": "Soccer: Who Has the Ball? Generating Visual Analytics and Player Statistics", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w34/Theagarajan_Soccer_Who_Has_CVPR_2018_paper.pdf", "http://vislab.ucr.edu/PUBLICATIONS/pubs/Journal%20and%20Conference%20Papers/after10-1-1997/Conference/2018/FINAL-published-soccer-ball-generating.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8575390", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2018.00227", "http://doi.org/10.1109/CVPRW.2018.00227"]}, {"id": "2622d2467f19bc60427f8ea495515e7da82316c9", "title": "Tell Me Where to Look: Guided Attention Inference Network", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579058"]}, {"id": "ccee8af5667d1d3bccf30baf2c6f049f031bb5ad", "title": "Mixing Hierarchical Contexts for Object Recognition", "year": "2011", "pdf": ["http://web.ing.puc.cl/~asoto/papers/Peralta-2011.pdf"], "doi": ["https://doi.org/10.1007/978-3-642-25085-9_27"]}, {"id": "c96f012f4915398259e7e223810c57898b5e1a76", "title": "Fast LIDAR-based Road Detection Using Convolutional Neural Networks", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/c96f/012f4915398259e7e223810c57898b5e1a76.pdf"], "doi": []}, {"id": "7142e659d6466717cdb8a242d8e34fce176b3f4a", "title": "Improved scene identification and object detection on egocentric vision of daily activities", "year": "2017", "pdf": ["http://crcv.ucf.edu/news&info/DefenseBooklet_FA17.pdf", "http://crcv.ucf.edu/papers/cviu2016-gonzalo.pdf", "http://vision.eecs.ucf.edu/papers/cviu2016-gonzalo.pdf"], "doi": ["http://doi.org/10.1016/j.cviu.2016.10.016"]}, {"id": "3b483c986b973856e016f761ec312c1a339766a5", "title": "DOTA: A Large-Scale Dataset for Object Detection in Aerial Images", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578516"]}, {"id": "1281e443d2cf1c1dd71ed3b7b0376d408d0958af", "title": "SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks", "year": "2015", "pdf": ["http://www.cs.cornell.edu/~xhuang/publications/salicon_poster.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Huang_SALICON_Reducing_the_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410395", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.38", "http://doi.org/10.1109/ICCV.2015.38"]}, {"id": "71f7be73a575f3689b0137446289d02462e1c5b0", "title": "Adaptive Multi-Scale Information Flow for Object Detection.", "year": "2018", "pdf": ["http://bmvc2018.org/contents/papers/0266.pdf"], "doi": []}, {"id": "581fb0f0405c7f0e60610d88ceaceb9af44d8569", "title": "Final Report : Smart Trash Net : Waste Localization and Classification", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/581f/b0f0405c7f0e60610d88ceaceb9af44d8569.pdf"], "doi": []}, {"id": "eaa7c6293c9d858bd4c9897a5dfc7c670f2a8671", "title": "Distant Vehicle Detection Using Radar and Vision", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.10951.pdf"], "doi": []}, {"id": "2cea306754ed83eaf1d0433abbfb05b5a4c4cf48", "title": "BIG-OH: BInarization of gradient orientation histograms", "year": "2014", "pdf": ["http://vgl-ait.org/mdailey/uploads/publication_file/filename/110/Baber-BIG-OH.pdf"], "doi": ["http://doi.org/10.1016/j.imavis.2014.08.006"]}, {"id": "eb2ab9caa61b021c1cd7aff6d08163768faba99e", "title": "Cleaning Up Multiple Detections Caused by Sliding Window Based Object Detectors", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/eb2a/b9caa61b021c1cd7aff6d08163768faba99e.pdf"], "doi": []}, {"id": "5a364ecb2d10b637c63b885d27eb372390232277", "title": "Unsupervised Robust Feature-Based Partition Ensembling to Discover Categories", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7789641"]}, {"id": "1114c2aba97a5782a48341817811df2438d0fdbf", "title": "Robust Visual Tracking using Multi-Frame Multi-Feature Joint Modeling", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07498.pdf"], "doi": []}, {"id": "367008b91eb57c5ea64ef7520dfcabc0c5c85532", "title": "Person Re-identification: Past, Present and Future", "year": "2016", "pdf": ["https://arxiv.org/pdf/1610.02984.pdf"], "doi": []}, {"id": "8211c974ec152e79235cb57a03ba2971e913508f", "title": "Multimodal Image Retrieval", "year": "2012", "pdf": [], "doi": ["https://doi.org/10.1007/s13735-012-0006-4"]}, {"id": "eb69f89588e9538194750f12bf8c8df6d5301f3b", "title": "Object Tracking by a Combination of Discriminative Global and Generative Multi-Scale Local Models", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/eb69/f89588e9538194750f12bf8c8df6d5301f3b.pdf"], "doi": []}, {"id": "d6bdc70d259b38bbeb3a78db064232b4b4acc88f", "title": "Video-Based Face Association and Identification", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7961735", "http://doi.ieeecomputersociety.org/10.1109/FG.2017.27", "http://doi.org/10.1109/FG.2017.27"]}, {"id": "d2e8efaa0d095c22455fe4eab260f94994bfb116", "title": "Stand-alone quality estimation of background subtraction algorithms", "year": "2017", "pdf": [], "doi": ["http://doi.org/10.1016/j.cviu.2017.08.005"]}, {"id": "abe9f3b91fd26fa1b50cd685c0d20debfb372f73", "title": "The Pascal Visual Object Classes Challenge: A Retrospective", "year": "2014", "pdf": ["http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc14.pdf", "http://www.robots.ox.ac.uk/~vgg/publications/2015/Everingham15/everingham15.pdf", "https://www.research.ed.ac.uk/portal/files/20017166/ijcv_voc14.pdf"], "doi": ["http://doi.org/10.1007/s11263-014-0733-5"]}, {"id": "10d3f77225eca1d576268ba84ed83f230a5e47c4", "title": "Crafting a multi-task CNN for viewpoint estimation", "year": "2016", "pdf": ["https://arxiv.org/pdf/1609.03894.pdf"], "doi": []}, {"id": "a01c7eec51fa901b2526325f563480c152c58ee5", "title": "Contour Box: Rejecting Object Proposals without Explicit Closed Contours", "year": "2015", "pdf": ["http://openaccess.thecvf.com/content_iccv_2015/papers/Lu_Contour_Box_Rejecting_ICCV_2015_paper.pdf", "http://www.cse.cuhk.edu.hk/leojia/papers/contour_iccv15.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Lu_Contour_Box_Rejecting_ICCV_2015_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410591", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.234", "http://doi.org/10.1109/ICCV.2015.234"]}, {"id": "3db4bdee7bc03239ef25d23cf8dc14ce5a5300e2", "title": "Sparse Coding for Object Recognition", "year": "2013", "pdf": [], "doi": []}, {"id": "32cde90437ab5a70cf003ea36f66f2de0e24b3ab", "title": "The Cityscapes Dataset for Semantic Urban Scene Understanding", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.01685.pdf"], "doi": []}, {"id": "04e1c7618e4ef3e16159b27c522ddf94068c4f99", "title": "Reconstructing PASCAL VOC", "year": "2014", "pdf": ["http://home.isr.uc.pt/~joaoluis/papers/cvpr14_reconstruct_pascal_slides.pdf", "http://home.isr.uc.pt/~joaoluis/papers/cvpr2014_1.pdf", "http://people.eecs.berkeley.edu/~carreira/papers/cvpr14_reconstruct_pascal_slides.pdf", "http://people.eecs.berkeley.edu/~carreira/papers/cvpr2014_1.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Vicente_Reconstructing_PASCAL_VOC_2014_CVPR_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909407", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.13", "http://doi.org/10.1109/CVPR.2014.13"]}, {"id": "ec187cedb69b389d06da26b17d889020e36ba6f6", "title": "ModaNet: A Large-scale Street Fashion Dataset with Polygon Annotations", "year": "2018", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3240652"]}, {"id": "729f20fa5928514768f4e0d848e74e5eecc33174", "title": "Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8270088"]}, {"id": "8ecf9e6428edd33986e8c6a143870e57142fd5a1", "title": "DOTA: A Large-Scale Dataset for Object Detection in Aerial Images", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578516"]}, {"id": "8bb4e1ddfec4c5868c31685b6dfe8673df1d3e38", "title": "What is a Salient Object? A Dataset and a Baseline Model for Salient Object Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6990522"]}, {"id": "1fef45786e707e6b9b8517b0403e596ecbdea6a5", "title": "Sketch-based manga retrieval using manga109 dataset", "year": "2016", "pdf": ["https://arxiv.org/pdf/1510.04389.pdf"], "doi": []}, {"id": "12660f0defc6580e566c0fa2ac909971d6c6883b", "title": "The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes", "year": "2016", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780721", "http://doi.org/10.1109/CVPR.2016.352", "https://www.wikidata.org/entity/Q57840870"]}, {"id": "dc7a6156c90b5e9b0ff3e95413e9139024c460a5", "title": "Semantic Understanding of Scenes Through the ADE20K Dataset", "year": "2016", "pdf": ["http://arxiv.org/pdf/1608.05442", "http://arxiv.org/pdf/1608.05442v1.pdf", "http://bzhou.ie.cuhk.edu.hk/publication/ADE20K_IJCV.pdf", "https://arxiv.org/pdf/1608.05442.pdf", "https://export.arxiv.org/pdf/1608.05442"], "doi": ["https://doi.org/10.1007/s11263-018-1140-0"]}, {"id": "b7ff61c0807d50266fdd3a9770a7d66399b5f087", "title": "Drishti-GS: Retinal image dataset for optic nerve head(ONH) segmentation", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6867807"]}, {"id": "58a6eb3584b2f5df2f25d39a218904d510cae516", "title": "The UAVid Dataset for Video Semantic Segmentation", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.10438.pdf"], "doi": []}, {"id": "2f4df08d9072fc2ac181b7fced6a245315ce05c8", "title": "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909475"]}, {"id": "dcb6f06631021811091ce691592b12a237c12907", "title": "SeaShips: A Large-Scale Precisely Annotated Dataset for Ship Detection", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8438999", "http://doi.org/10.1109/TMM.2018.2865686"]}, {"id": "127316fbe268c78c519ceb23d41100e86639418a", "title": "CNN Features Off-the-Shelf: An Astounding Baseline for Recognition", "year": "2014", "pdf": ["https://arxiv.org/pdf/1403.6382.pdf"], "doi": []}, {"id": "e74f9b7f8eec6ba4704c206b93bc8079af3da4bd", "title": "ImageNet Large Scale Visual Recognition Challenge", "year": "2014", "pdf": ["https://dspace.mit.edu/bitstream/1721.1/104944/1/11263_2015_Article_816.pdf", "http://arxiv.org/pdf/1409.0575v1.pdf", "http://dspace.mit.edu/bitstream/handle/1721.1/104944/11263_2015_Article_816.pdf;jsessionid=7277F2E4B792AF15009A8777BCC84DD1?sequence=1", "http://hci.stanford.edu/publications/2015/scenegraphs/imagenet-challenge.pdf", "https://arxiv.org/pdf/1409.0575.pdf", "https://dspace.mit.edu/bitstream/handle/1721.1/104944/11263_2015_Article_816.pdf;jsessionid=D47A767FE49C452E89782919F8DCDCE6?sequence=1"], "doi": ["https://doi.org/10.1007/s11263-015-0816-y", "http://dspace.mit.edu/openaccess-disseminate/1721.1/104944", "https://www.wikidata.org/entity/Q56594393"]}, {"id": "39978ba7c83333475d6825d0ff897692933895fc", "title": "Conditional Random Fields as Recurrent Neural Networks", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410536"]}, {"id": "aa4cc6506e837390486e5b836fb3dac8d15daafa", "title": "ThermalGAN: Multimodal Color-to-Thermal Image Translation for Person Re-identification in Multispectral Dataset", "year": "2018", "pdf": ["http://openaccess.thecvf.com/content_ECCVW_2018/papers/11134/Kniaz_ThermalGAN_Multimodal_Color-to-Thermal_Image_Translation_for_Person_Re-Identification_in_Multispectral_ECCVW_2018_paper.pdf"], "doi": ["https://doi.org/10.1007/978-3-030-11024-6_46"]}, {"id": "562463fafacca4bbe5256e318eb628bf915f4114", "title": "SLNSW-UTS: A Historical Image Dataset for Image Multi-Labeling and Retrieval", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7797084"]}, {"id": "2c0b510ebf995ef172cb64ed7ce24aa7903dced8", "title": "Learning Rich Features from RGB-D Images for Object Detection and Segmentation", "year": "2014", "pdf": ["https://arxiv.org/pdf/1407.5736.pdf"], "doi": []}, {"id": "21a1654b856cf0c64e60e58258669b374cb05539", "title": "You Only Look Once: Unified, Real-Time Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1506.02640.pdf"], "doi": []}, {"id": "38b6540ddd5beebffd05047c78183f7575559fb2", "title": "Selective Search for Object Recognition", "year": "2013", "pdf": ["https://pure.uva.nl/ws/files/19494140/UijlingsIJCV2013.pdf", "http://graphics.cs.cmu.edu/courses/16-824/2016_spring/slides/seg_3.pdf", "http://koen.me/research/pub/uijlings-ijcv2013-draft.pdf", "http://www.cs.cornell.edu/courses/cs7670/2014sp/slides/VisionSeminar14.pdf", "http://www.tpbin.com/Uploads/Subjects/de55b048-461f-4962-b851-fd020c47c982.pdf", "https://staff.fnwi.uva.nl/th.gevers/pub/GeversIJCV2013.pdf", "https://webcourse.cs.technion.ac.il/236815/Spring2016/ho/WCFiles/01_object_proposals_6pp.pdf"], "doi": ["https://doi.org/10.1007/s11263-013-0620-5"]}, {"id": "616b246e332573af1f4859aa91440280774c183a", "title": "The Pascal Visual Object Classes Challenge: A Retrospective", "year": "2014", "pdf": ["https://www.pure.ed.ac.uk/ws/files/20017166/ijcv_voc14.pdf", "http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc14.pdf", "http://www.robots.ox.ac.uk/~vgg/publications/2015/Everingham15/everingham15.pdf", "https://www.research.ed.ac.uk/portal/files/20017166/ijcv_voc14.pdf"], "doi": ["https://doi.org/10.1007/s11263-014-0733-5"]}, {"id": "abe80983d7773b51f1e30c02c50bcbe774c15a12", "title": "PLS/OPLS models in metabolomics: the impact of permutation of dataset rows on the K-fold cross-validation quality parameters.", "year": "2015", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/25382277", "https://doi.org/10.1039/c4mb00414k"]}, {"id": "784da2a7b53a16d2243f747e14946cc5e3476af0", "title": "VQA: Visual Question Answering", "year": "2015", "pdf": ["http://arxiv.org/pdf/1505.00468"], "doi": ["https://doi.org/10.1109/iccv.2015.279", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.279"]}, {"id": "4cef5476f9da50c1a8fefdcb7114863966f61d67", "title": "Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780717"]}, {"id": "7d39d69b23424446f0400ef603b2e3e22d0309d6", "title": "YOLO9000: Better, Faster, Stronger", "year": "2017", "pdf": ["https://arxiv.org/pdf/1612.08242.pdf"], "doi": []}, {"id": "20a78d3145279dcd799cd7a856ae2714f4863a16", "title": "SSD: Single Shot MultiBox Detector", "year": "2016", "pdf": ["https://arxiv.org/pdf/1512.02325.pdf"], "doi": []}, {"id": "28fa525ca1e101335e877bb1f6999b6ccf476959", "title": "Semantic Segmentation with Second-Order Pooling", "year": "2012", "pdf": ["http://home.isr.uc.pt/~joaoluis/papers/eccv2012.pdf", "http://videolectures.net/site/normal_dl/tag=725540/eccv2012_carreira_semantic_01.pdf", "http://www.eecs.berkeley.edu/~carreira/papers/eccv2012.pdf"], "doi": ["https://doi.org/10.1007/978-3-642-33786-4_32"]}, {"id": "1e9b1f6061ef779e3ad0819c2832a29168eaeb9d", "title": "Instance-Aware Semantic Segmentation via Multi-task Network Cascades", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780712"]}, {"id": "28ef938aaa312d76df988f636e248a6b267b6352", "title": "Unsupervised Visual Domain Adaptation Using Subspace Alignment", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751479"]}, {"id": "cab372bc3824780cce20d9dd1c22d4df39ed081a", "title": "DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs", "year": "2018", "pdf": ["https://arxiv.org/pdf/1606.00915.pdf"], "doi": []}, {"id": "851a884a89a95968c2edcad9787994ccaa8b51a8", "title": "BING: Binarized normed gradients for objectness estimation at 300fps", "year": "2018", "pdf": ["http://mmcheng.net/mftp/Papers/ObjectnessBING.pdf", "http://vision.ia.ac.cn/zh/senimar/reports/2014.5.6PPT.pdf"], "doi": ["https://doi.org/10.1007/s41095-018-0120-1"]}, {"id": "94c5ced03a6f896a4b3bc5a98b8b2baf349d8852", "title": "Fully Convolutional Instance-Aware Semantic Segmentation", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099955"]}, {"id": "cbba352a37426a21b020d1ba8f61e5bca9ca20ae", "title": "Fully convolutional networks for semantic segmentation", "year": "2015", "pdf": ["http://arxiv.org/pdf/1411.4038"], "doi": ["https://doi.org/10.1109/cvpr.2015.7298965", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2015.7298965"]}, {"id": "79cfb51a51fc093f66aac8e858afe2e14d4a1f20", "title": "Focal Loss for Dense Object Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237586"]}, {"id": "74cd38f585cfc48b7e01d95e127204d36b3c02c0", "title": "Anthropogenic VOC in Abidjan, southern West Africa: from source quantification to atmospheric impacts", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/74cd/38f585cfc48b7e01d95e127204d36b3c02c0.pdf"], "doi": []}, {"id": "71b7178df5d2b112d07e45038cb5637208659ff7", "title": "Microsoft COCO: Common Objects in Context", "year": "2014", "pdf": ["https://arxiv.org/pdf/1405.0312.pdf"], "doi": []}, {"id": "a971fb267c150834ba823156841eca8845ae1c7f", "title": "Hierarchical Saliency Detection", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6618997"]}, {"id": "83d1118c2b2995a3e0cf9b6159e4c59e85cabb7e", "title": "Multiscale Combinatorial Grouping", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909443"]}, {"id": "f251d1d8eb5f3e5b8cf2b4c4550f25ef4c832b5e", "title": "Regionlets for Generic Object Detection", "year": "2013", "pdf": [], "doi": ["https://doi.org/10.1109/iccv.2013.10", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.10"]}, {"id": "2c03df8b48bf3fa39054345bafabfeff15bfd11d", "title": "Deep Residual Learning for Image Recognition", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780459"]}, {"id": "1a2a770d23b4a171fa81de62a78a3deb0588f238", "title": "Visualizing and Understanding Convolutional Networks", "year": "2013", "pdf": ["https://arxiv.org/pdf/1311.2901.pdf"], "doi": []}, {"id": "3dd2f70f48588e9bb89f1e5eec7f0d8750dd920a", "title": "Fast R-CNN", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410526"]}, {"id": "c1994ba5946456fc70948c549daf62363f13fa2d", "title": "Indoor Segmentation and Support Inference from RGBD Images", "year": "2012", "pdf": ["http://cs.nyu.edu/~silberman/papers/indoor_seg_support.pdf", "http://cs.nyu.edu/~silberman/papers/indoor_seg_support_supplementary.pdf", "http://videolectures.net/site/normal_dl/tag=725527/eccv2012_silberman_images_01.pdf", "http://web.engr.illinois.edu/~dhoiem/publications/eccv2012_indoorkinect_nathan.pdf"], "doi": ["https://doi.org/10.1007/978-3-642-33715-4_54"]}, {"id": "abd1c342495432171beb7ca8fd9551ef13cbd0ff", "title": "ImageNet Classification with Deep Convolutional Neural Networks", "year": "2012", "pdf": [], "doi": ["http://dl.acm.org/citation.cfm?id=3065386"]}, {"id": "6de2b1058c5b717878cce4e7e50d3a372cc4aaa6", "title": "Generative Adversarial Nets", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/6de2/b1058c5b717878cce4e7e50d3a372cc4aaa6.pdf"], "doi": []}, {"id": "16fc1065c296840cb0f8ca62601aa17b7f0a02bf", "title": "Object Detection with Discriminatively Trained Part-Based Models", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/16fc/1065c296840cb0f8ca62601aa17b7f0a02bf.pdf"], "doi": []}, {"id": "3a0130cfab8192a397d79fc1c7c398470157cf48", "title": "Mask R-CNN.", "year": "2018", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/29994331", "https://doi.org/10.1109/tpami.2018.2844175"]}, {"id": "0023582fde36430c7e3ae81611a14e558c8f4bae", "title": "The Algorithmic Foundations of Differential Privacy", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/7f7e/9fd30ff0d1937f83ed0705de49cb9a7e7719.pdf"], "doi": []}, {"id": "2640a376c2b51f83420526646613e85d730eab37", "title": "Saliency Detection via Graph-Based Manifold Ranking", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619251"]}, {"id": "4a3fd686ce675659f238c46c629b055cd58651a0", "title": "Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099834"]}, {"id": "2f56b1ac5b9faac9527b6814778925e9242cf5fd", "title": "Training Region-Based Object Detectors with Online Hard Example Mining", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780458"]}, {"id": "272216c1f097706721096669d85b2843c23fa77d", "title": "Adam: A Method for Stochastic Optimization", "year": "2015", "pdf": ["https://arxiv.org/pdf/1412.6980.pdf"], "doi": []}, {"id": "2a94c84383ee3de5e6211d43d16e7de387f68878", "title": "Feature Pyramid Networks for Object Detection", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8099589"]}, {"id": "3cdb1364c3e66443e1c2182474d44b2fb01cd584", "title": "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1511.00561.pdf"], "doi": []}, {"id": "33da83b54410af11d0cd18fd07c74e1a99f67e84", "title": "DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition", "year": "2014", "pdf": ["https://arxiv.org/pdf/1310.1531.pdf"], "doi": []}, {"id": "8ac2736683dac9a467602ee19f5a290096259148", "title": "HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection", "year": "2016", "pdf": ["https://arxiv.org/pdf/1604.00600.pdf"], "doi": []}, {"id": "0da75bded3ae15e255f5bd376960cfeffa173b4e", "title": "The Role of Context for Object Detection and Semantic Segmentation in the Wild", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909514"]}, {"id": "522fab628aab972f39835521e31564b4b6c64fe5", "title": "Vehicle Classification on Low-resolution and Occluded images : A low-cost labeled dataset for augmentation", "year": "2017", "pdf": ["https://pdfs.semanticscholar.org/522f/ab628aab972f39835521e31564b4b6c64fe5.pdf"], "doi": []}, {"id": "f78db8e59ba354258c3eb4fff2ec67564975436f", "title": "Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories", "year": "2018", "pdf": ["https://arxiv.org/pdf/1810.09263.pdf"], "doi": []}, {"id": "3aa681914a7da79f7d7293f51a058eefe61c8bb7", "title": "MVTec AD -- A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/0222/42d33927ef415754e116df1a122961edb6e9.pdf"], "doi": []}, {"id": "7df435390fa21d623d066d76c53c8cd6b8211891", "title": "What Makes a Patch Distinct?", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6618995"]}, {"id": "e3ea1c7a3c6cc15590ab5e62a171536fe01b9b1c", "title": "Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410492"]}, {"id": "2b7c2e4e888f4ca6bc8def17497504ea4012aa0f", "title": "Articulated Pose Estimation Using Discriminative Armlet Classifiers", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619273"]}, {"id": "5f5c075e8675d00a2e12bf12a99dafeba444e199", "title": "Semantic Segmentation with Reverse Attention", "year": "2017", "pdf": ["https://arxiv.org/pdf/1707.06426.pdf"], "doi": []}, {"id": "2bcf46c0b52d8e9535ab3dcfdfb793a3da2a6271", "title": "Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7781017"]}, {"id": "c88c233c50f49b4b85a8702d5ee384d96fca8c23", "title": "Object-Proposal Evaluation Protocol is \u2018Gameable\u2019", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780466"]}, {"id": "09e15bb266da86d0a9525d2a94ac0b38f0b53b88", "title": "Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.2031.pdf"], "doi": []}, {"id": "6a1b76f1ef876061ec479ab9bc13fcd517eb4188", "title": "Large Kernel Matters \u2014 Improve Semantic Segmentation by Global Convolutional Network", "year": "2017", "pdf": ["https://arxiv.org/pdf/1703.02719.pdf"], "doi": []}, {"id": "f0550daaf6b173759aa5a2e39a3a9d874d65e858", "title": "Improvements to Context Based Self-Supervised Learning", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579071"]}, {"id": "1779b6a17ee68afafb6801477b165f19901689b2", "title": "Object Contour Detection with a Fully Convolutional Encoder-Decoder Network", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780397"]}, {"id": "cdfe4e46d949b68c682e554c402d16679fd7247c", "title": "Stacked Deconvolutional Network for Semantic Segmentation", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.04943.pdf"], "doi": []}, {"id": "b9c830332608afbbf452a20afeff38ca5aac2e27", "title": "Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410477"]}, {"id": "b92a1ed9622b8268ae3ac9090e25789fc41cc9b8", "title": "Pooling in image representation: The visual codeword point of view", "year": "2013", "pdf": ["http://cedric.cnam.fr/~thomen/papers/avila_CVIU2012_final.pdf", "http://webia.lip6.fr/~thomen/papers/avila_CVIU2012_accepted.pdf"], "doi": ["https://doi.org/10.1016/j.cviu.2012.09.007"]}, {"id": "031055c241b92d66b6984643eb9e05fd605f24e2", "title": "Multi-fold MIL Training for Weakly Supervised Object Localization", "year": "2014", "pdf": ["http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Cinbis_Multi-fold_MIL_Training_2014_CVPR_paper.pdf", "https://hal.inria.fr/hal-00975746/PDF/paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909705", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.309", "http://doi.org/10.1109/CVPR.2014.309"]}, {"id": "2a1f38e4451e826e01c9874954ba7c6f32ff79f4", "title": "Boosting Self-Supervised Learning via Knowledge Transfer", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8579073"]}, {"id": "f2666a91f6844d7815f758ec1afbac18caf392f8", "title": "Single-Shot Object Detection with Enriched Semantics", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578707"]}, {"id": "57bfbd06e94c5def35c1dde901bb4f1c839dbcdf", "title": "Deep patch learning for weakly supervised object classification and discovery", "year": "2017", "pdf": ["https://arxiv.org/pdf/1705.02429.pdf"], "doi": []}, {"id": "1cf25786f1e473fdbfcd817cfa37b0ad12806e72", "title": "Co-segmentation by Composition", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751271"]}, {"id": "ab9d87a03ce3538ff42b6c26d87e676107cc392c", "title": "Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619260"]}, {"id": "3bde1aae1db3577938ffe910a9de5a1f187840e9", "title": "RIFD-CNN: Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780684"]}, {"id": "647c6ac5e0bfee0241d583650f18c6314f28aaee", "title": "Segmentation Driven Object Detection with Fisher Vectors", "year": "2013", "pdf": ["http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Cinbis_Segmentation_Driven_Object_2013_ICCV_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751480", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2013.369", "http://doi.org/10.1109/ICCV.2013.369"]}, {"id": "67490b6f34c827f107b046adeef0f5476132d4f8", "title": "How good are detection proposals, really?", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.6962.pdf"], "doi": []}, {"id": "636cea485f77373ae18e32ac8e1c4e37555db5bd", "title": "BING: Binarized Normed Gradients for Objectness Estimation at 300fps", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909816"]}, {"id": "3fd90098551bf88c7509521adf1c0ba9b5dfeb57", "title": "Attribute-Based Classification for Zero-Shot Visual Object Categorization", "year": "2014", "pdf": ["http://pub.ist.ac.at/~chl/papers/lampert-pami2013.pdf", "https://staff.fnwi.uva.nl/t.e.j.mensink/zsl2016/zslpubs/lampert13pami.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6571196", "http://doi.org/10.1109/TPAMI.2013.140", "https://www.ncbi.nlm.nih.gov/pubmed/24457503", "https://www.wikidata.org/entity/Q38437353"]}, {"id": "15e024d8f5625ec03c8ac592fbc093687cfb5f02", "title": "The Visual Object Tracking VOT2015 Challenge Results", "year": "2015", "pdf": ["http://cell.missouri.edu/media/publications/Matej-KristanRengarajan_VOT2015-challenge-results_ICCVW-2015.pdf", "http://cmp.felk.cvut.cz/~vojirtom/publications/Kristan2013The.pdf", "http://data.votchallenge.net/vot2015/presentations/vot_2015_paper.pdf", "http://liris.cnrs.fr/Documents/Liris-6875.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015_workshops/w14/papers/Kristan_The_Visual_Object_ICCV_2015_paper.pdf", "http://www.epics-project.eu/publications/2013_kristan_iccvw.pdf", "http://www.epics-project.eu/publications/2014_kristan_iccvw.pdf", "https://hal.archives-ouvertes.fr/hal-01336773/file/Kristan2015The.pdf", "https://repositorio.uam.es/bitstream/handle/10486/674992/visual_kristan_ICCVW_2015_ps.pdf?isAllowed=y&sequence=1"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7406428", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2015.79", "http://doi.org/10.1109/ICCVW.2015.79", "https://hal.archives-ouvertes.fr/hal-01336773/document"]}, {"id": "a1bcdb820f6f0dde108996a18eefb239ef0e9566", "title": "Visual Tracking: An Experimental Survey.", "year": "2014", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/26353314", "https://doi.org/10.1109/TPAMI.2013.230"]}, {"id": "1af794673d64112edf60f071ca24066e6a227d2b", "title": "Online Object Tracking: A Benchmark", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619156"]}, {"id": "d082f64b8a0a07d105207eb822be58ffb61b353a", "title": "EMOTIC: Emotions in Context Dataset", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_cvpr_2017_workshops/w41/papers/Lapedriza_EMOTIC_Emotions_in_CVPR_2017_paper.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8015019", "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2017.285", "http://doi.org/10.1109/CVPRW.2017.285"]}, {"id": "2822a883d149956934a20614d6934c6ddaac6857", "title": "A survey of appearance models in visual object tracking", "year": "2013", "pdf": ["https://arxiv.org/pdf/1303.4803.pdf"], "doi": []}, {"id": "f727837e03a039d9bcec6d02cd87256f5a5854a4", "title": "Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.03409.pdf"], "doi": []}, {"id": "ebe5a4c2dc3ca55a5aeedcd25a98ca6e446ce9cc", "title": "Hippocampal Activity Patterns Carry Information about Objects in Temporal Context", "year": "2014", "pdf": ["http://cogns.northwestern.edu/cbmg/pdfs/2.Hsieh_2014.pdf", "http://dml.ucdavis.edu/uploads/6/1/9/7/61974117/hseih_2014_hippocampal.pdf", "http://orca.cf.ac.uk/96034/7/Hsieh_NEURON-D-13-01629.1.pdf"], "doi": ["https://www.sciencedirect.com/science/article/pii/S0896627314000208", "https://doi.org/10.1016/j.neuron.2014.01.015", "https://www.ncbi.nlm.nih.gov/pubmed/24607234"]}, {"id": "b7d540cd0de72e984cdec44afa4a4d039cfd5eea", "title": "Object Tracking Benchmark", "year": "2015", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/pami15_tracking_benchmark.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7001050", "http://doi.org/10.1109/TPAMI.2014.2388226", "https://www.ncbi.nlm.nih.gov/pubmed/26353130", "https://www.wikidata.org/entity/Q35768210"]}, {"id": "aa23d33983b1abd2d8a677040eb875e93c478a7f", "title": "Measuring the Objectness of Image Windows", "year": "2012", "pdf": ["http://groups.inf.ed.ac.uk/calvin/Publications/alexe11-techreport.pdf", "http://groups.inf.ed.ac.uk/calvin/Publications/alexe12pami.pdf", "http://www.vision.ee.ethz.ch/en/publications/papers/techreports/eth_biwi_00882.pdf", "https://www.research.ed.ac.uk/portal/files/17686204/Alexe_et_al_2010_Measuring_the_objectnessi.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6133291", "http://doi.org/10.1109/TPAMI.2012.28", "https://www.ncbi.nlm.nih.gov/pubmed/22248633", "https://www.wikidata.org/entity/Q50666022"]}, {"id": "149e5e5eeea5a9015ab5ae755f62c45ef70fa79b", "title": "Hierarchical Convolutional Features for Visual Tracking", "year": "2015", "pdf": ["http://faculty.ucmerced.edu/mhyang/papers/iccv15_tracking.pdf", "http://openaccess.thecvf.com/content_iccv_2015/papers/Ma_Hierarchical_Convolutional_Features_ICCV_2015_paper.pdf", "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Ma_Hierarchical_Convolutional_Features_ICCV_2015_paper.pdf", "https://filebox.ece.vt.edu/~jbhuang/poster/ICCV_2015_HCF_Poster.pdf", "https://filebox.ece.vt.edu/~jbhuang/slides/ICCV_2015_HCF_Slides.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410709", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.352", "http://doi.org/10.1109/ICCV.2015.352"]}, {"id": "05375a7489f0a84d47a316bacb4d86e8a7bda0df", "title": "Analysis of Scores, Datasets, and Models in Visual Saliency Prediction", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751224"]}, {"id": "58e6eaacaab3fbf9b307a8aec1c614027ff501ce", "title": "Dynamic Eye Movement Datasets and Learnt Saliency Models for Visual Action Recognition", "year": "2012", "pdf": ["http://109.101.234.42/documente/publications/19-62.pdf", "http://sminchisescu.ins.uni-bonn.de/papers/ms12eccv.pdf", "http://web.cs.hacettepe.edu.tr/~erkut/bil722.f12/w09-levent.pdf"], "doi": ["https://doi.org/10.1007/978-3-642-33709-3_60"]}, {"id": "36c91b1342c1357877e89b4c43f8eadb39755c0b", "title": "Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses", "year": "2012", "pdf": ["http://cs.stanford.edu/groups/vision/documents/YaoFei-Fei_PAMI2012.pdf", "http://cs.stanford.edu/groups/vision/pdf/yaopami12.pdf", "http://vision.stanford.edu/pdf/yaopami12.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6165303", "http://doi.org/10.1109/TPAMI.2012.67", "https://www.ncbi.nlm.nih.gov/pubmed/22392710", "https://www.wikidata.org/entity/Q34185448"]}, {"id": "f0ee079a1f40736e5b7760b38781f090744f37fc", "title": "Contextualizing Object Detection and Classification", "year": "2015", "pdf": [], "doi": ["https://www.ncbi.nlm.nih.gov/pubmed/26353205", "https://doi.org/10.1109/TPAMI.2014.2343217", "https://www.wikidata.org/entity/Q40558547"]}, {"id": "5b130e2a1fc3f71b7638cc5dde72481cf33264cc", "title": "Scene Recognition with CNNs: Objects, Scales and Dataset Bias", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780437"]}, {"id": "bfa6ad4d71008505729274d008a9b4a7d92b2985", "title": "Semantic Understanding of Scenes Through the ADE20K Dataset", "year": "2018", "pdf": ["https://arxiv.org/pdf/1608.05442.pdf"], "doi": []}, {"id": "1883116d33a3e0321d2fe96e0a8a62546aca4ee9", "title": "Visual Question Answering: Datasets, Algorithms, and Future Challenges", "year": "2017", "pdf": ["https://arxiv.org/pdf/1610.01465.pdf"], "doi": []}, {"id": "88c307c51594c6d802080a0780d0d654e2e2891f", "title": "Visual Question Answering: A Survey of Methods and Datasets", "year": "2017", "pdf": ["https://arxiv.org/pdf/1607.05910.pdf"], "doi": []}, {"id": "3cfbb77e5a0e24772cfdb2eb3d4f35dead54b118", "title": "Don't count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/2353/17b7ce64b4b3aefe57c1304e8157a4832d2c.pdf"], "doi": []}, {"id": "18e39b6f8f5c538d639bc0b46136ed93b5e3ef35", "title": "A Large Dataset of Object Scans", "year": "2016", "pdf": ["https://arxiv.org/pdf/1602.02481.pdf"], "doi": []}, {"id": "b31d6f201340ecec35bbe0f477710436f860605e", "title": "Learning Video Object Segmentation with Visual Memory", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237742"]}, {"id": "4a19f6545473363b16d4a10ed13fef29b38856d3", "title": "What is a Salient Object? A Dataset and a Baseline Model for Salient Object Detection", "year": "2015", "pdf": ["https://arxiv.org/pdf/1412.5027.pdf"], "doi": []}, {"id": "0558c94a094158ecd64f0d5014d3d9668054fb97", "title": "Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/528d/141aba97074977a332bb2d96364b716f246c.pdf"], "doi": []}, {"id": "09a503095db2d68b439e48d67481399198ed0e5b", "title": "Recurrent Models of Visual Attention", "year": "2014", "pdf": ["https://arxiv.org/pdf/1406.6247.pdf"], "doi": []}, {"id": "350d507f5d899e4d7293b1aa951aa0f81b9fd30a", "title": "The Visual Object Tracking VOT2017 Challenge Results", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017_workshops/papers/w28/Kristan_The_Visual_Object_ICCV_2017_paper.pdf", "https://hal.archives-ouvertes.fr/hal-01336773/file/Kristan2015The.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8265440", "http://doi.ieeecomputersociety.org/10.1109/ICCVW.2017.230", "http://doi.org/10.1109/ICCVW.2017.230"]}, {"id": "7e232313a59d735ef7c8a9f4cc7bc980a29deb5e", "title": "Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering", "year": "2017", "pdf": [], "doi": ["https://doi.org/10.1007/s11263-018-1116-0"]}, {"id": "b4ee2a6b5fdf66f57e94a998cff2acef4af7d256", "title": "Monocular Visual Scene Understanding: Understanding Multi-Object Traffic Scenes", "year": "2013", "pdf": ["https://www.d2.mpi-inf.mpg.de/sites/default/files/wojek2013pami.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6265058", "http://doi.org/10.1109/TPAMI.2012.174", "https://www.ncbi.nlm.nih.gov/pubmed/22889818", "https://www.wikidata.org/entity/Q45823527"]}, {"id": "2ce63d77eecc35faef85a3b752a314c93a077ac9", "title": "Learning Multi-domain Convolutional Neural Networks for Visual Tracking", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780834"]}, {"id": "1c66fa1f3f189ca25bd657f53d77fde64c75f3da", "title": "Adaptive Color Attributes for Real-Time Visual Tracking", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909539"]}, {"id": "eb66303192a89c314ce4acae640ba700fa3293a3", "title": "Unsupervised Object Annotation through Context Analysis", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/eb66/303192a89c314ce4acae640ba700fa3293a3.pdf"], "doi": []}, {"id": "51a4d658c93c5169eef7568d3d1cf53e8e495087", "title": "Unsupervised Visual Domain Adaptation Using Subspace Alignment", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751479"]}, {"id": "079ed21601974d0604544a6d816c2f51b5c039b8", "title": "Enriching Visual Knowledge Bases via Object Discovery and Segmentation", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909658"]}, {"id": "7574b7e5a75fdd338c27af5aeb77ab79460c4437", "title": "Learning Dynamic Siamese Network for Visual Object Tracking", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237458"]}, {"id": "38a169b6e67ef7768f91fa208c9b5544f6f57f16", "title": "Object Bank: An Object-Level Image Representation for High-Level Visual Recognition", "year": "2013", "pdf": ["http://cs.stanford.edu/groups/vision/pdf/li_ijcv2013.pdf", "http://vision.stanford.edu/pdf/li_ijcv2013.pdf", "http://www.tpbin.com/Uploads/Subjects/79181d36-c45c-4f6c-821f-b7f9fcac3881.pdf"], "doi": ["http://doi.org/10.1007/s11263-013-0660-x"]}, {"id": "5527dd901b836e2f164c9fa3e62f57cd70c21745", "title": "3D object retrieval via range image queries in a bag-of-visual-words context", "year": "2013", "pdf": ["http://graphics.di.uoa.gr/Downloads/papers/journals/p43.pdf", "http://www.idi.ntnu.no/grupper/vis/wp-content/uploads/2013/09/Range3DRetrievalTVCfinal.pdf"], "doi": ["https://doi.org/10.1007/s00371-013-0876-3"]}, {"id": "5ea8a9ae2bf40c4722e618b732f769744ab57dfe", "title": "Context Driven Scene Parsing with Attention to Rare Classes", "year": "2014", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6909817"]}, {"id": "2d84f49572c2b29b6c9e1818eb57e7f12bc4236e", "title": "Query-Adaptive Asymmetrical Dissimilarities for Visual Object Retrieval", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6751322"]}, {"id": "00319cd17cebae5e1095a248260bd7be15781362", "title": "A Dataset for Improved RGBD-Based Object Detection and Pose Estimation for Warehouse Pick-and-Place", "year": "2016", "pdf": ["https://arxiv.org/pdf/1509.01277.pdf"], "doi": []}, {"id": "0f060f011fe3093a24bf2cde96a4a833f58ec5a5", "title": "Object-based visual query suggestion", "year": "2012", "pdf": ["https://www.researchgate.net/profile/Pierre_Letessier/publication/257627352_Object-based_visual_query_suggestion/links/00b7d5260034959679000000.pdf"], "doi": ["https://doi.org/10.1007/s11042-012-1340-5"]}, {"id": "33baa52f583fb049f473a53d8e0ca5ac8e7abbf2", "title": "Reinforcement Learning for Visual Object Detection", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780685"]}, {"id": "1631bc8b8fe853278b8e54bd3e9fff1445fa9f91", "title": "Visual Distance Measures for Object Retrieval", "year": "2012", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6411668"]}, {"id": "4a8e9e179b58d3e10448f5e4680b66f34c8bc573", "title": "Learning to segment moving objects in videos", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7299035"]}, {"id": "0f6a8e9139cdd15fd0a8a292204aed21a8b51c5a", "title": "ReferItGame: Referring to Objects in Photographs of Natural Scenes", "year": "2014", "pdf": ["https://pdfs.semanticscholar.org/0f6a/8e9139cdd15fd0a8a292204aed21a8b51c5a.pdf"], "doi": []}, {"id": "1ced31e02234bc3d1092ffb2c7442ffbd51cb309", "title": "A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation", "year": "2016", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7780807"]}, {"id": "5ac18d505ed6d10e8692cbb7d33f6852e6782692", "title": "The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.00982.pdf"], "doi": []}, {"id": "efa08283656714911acff2d5022f26904e451113", "title": "Active Object Localization in Visual Situations", "year": "2016", "pdf": ["https://arxiv.org/pdf/1607.00548.pdf"], "doi": []}, {"id": "1f7127b9ae86d7fac305c6b824801e455e82f511", "title": "Visual relationship detection with object spatial distribution", "year": "2017", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8019448", "http://doi.ieeecomputersociety.org/10.1109/ICME.2017.8019448", "http://doi.org/10.1109/ICME.2017.8019448"]}, {"id": "051830b0ea58d1568f19ec3297e301d9789c9a76", "title": "Bringing Semantics into Focus Using Visual Abstraction", "year": "2013", "pdf": ["http://courses.cs.washington.edu/courses/cse590v/13au/cse590v_au13_wk5_abstract_scenes.pdf", "http://courses.cs.washington.edu/courses/cse590v/13au/cse590v_au13_wk5_abstract_scenes_rob.pdf", "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989d009.pdf", "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Zitnick_Bringing_Semantics_into_2013_CVPR_paper.pdf", "https://filebox.ece.vt.edu/~parikh/Publications/ZitnickParikh_CVPR_2013_clipart.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619231", "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.387", "http://doi.org/10.1109/CVPR.2013.387"]}, {"id": "64c4019f1ea9b54b1848418ac53c4e2584dc62d4", "title": "ActionNet-VE Dataset: A Dataset for Describing Visual Events by Extending VIRAT Ground 2.0", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7433003"]}, {"id": "9a8e61cc9a95efe9e35df4d4230c7b8a655b7392", "title": "Unsupervised Joint Object Discovery and Segmentation in Internet Images", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6619097"]}, {"id": "022027ce7475029f78fb3cdb758d947a8978ab5c", "title": "Invariant visual object recognition: biologically plausible approaches", "year": "2015", "pdf": ["http://wrap.warwick.ac.uk/77413/1/WRAP_422_2015_Article_658.pdf", "http://www.oxcns.org/papers/554%20Robinson%20Rolls%202015%20Invariant%20visual%20object%20recognition%20Biologically%20plausible%20models.pdf"], "doi": ["https://doi.org/10.1007/s00422-015-0658-2", "https://www.ncbi.nlm.nih.gov/pubmed/26335743", "https://www.wikidata.org/entity/Q43248757"]}, {"id": "e8e662e45e39249756d2b0090782434a5cf1f4aa", "title": "VegFru: A Domain-Specific Dataset for Fine-Grained Visual Categorization", "year": "2017", "pdf": ["http://openaccess.thecvf.com/content_ICCV_2017/papers/Hou_VegFru_A_Domain-Specific_ICCV_2017_paper.pdf", "http://openaccess.thecvf.com/content_ICCV_2017/supplemental/Hou_VegFru_A_Domain-Specific_ICCV_2017_supplemental.pdf"], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237328", "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.66", "http://doi.org/10.1109/ICCV.2017.66"]}, {"id": "54c7c3909c7e1e827befdbe8d2595a3b196ba1b8", "title": "AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578731"]}, {"id": "ac6c28cd866bccbbca54da8b7bd5b2e0d5e9d0b4", "title": "Cross-Dataset Learning of Visual Concepts", "year": "2012", "pdf": ["https://hpi.de/fileadmin/user_upload/fachgebiete/meinel/Semantic-Technologies/paper/amr2012.pdf"], "doi": ["https://doi.org/10.1007/978-3-319-12093-5_4"]}, {"id": "bbe7f4217a9bd9c6d3826b5b62d59d183e729383", "title": "Discriminative Hough context model for object detection", "year": "2013", "pdf": [], "doi": ["https://doi.org/10.1007/s00371-013-0780-x"]}, {"id": "55ca9fe4ae98904bfe026d22dcf1420ff9c0dd86", "title": "Dataset for Visual Reasoning", "year": "2017", "pdf": [], "doi": []}, {"id": "20f9a09defe5b02b98c464ca6df36b3b6358f60b", "title": "The State-of-the-Art in Visual Object Tracking", "year": "2012", "pdf": ["https://pdfs.semanticscholar.org/cd46/4a309fa1736e1373f0bb06baf75e3d0abcac.pdf"], "doi": []}, {"id": "d86fabd4498c8feaed80ec342d254fb877fb92f5", "title": "Region-Object Relevance-Guided Visual Relationship Detection", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/d86f/abd4498c8feaed80ec342d254fb877fb92f5.pdf"], "doi": []}, {"id": "4405b44b5597787c42abeca6d0b3172175557b7b", "title": "Object discovery in 3D scenes via shape analysis", "year": "2013", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6630857"]}, {"id": "8da0771e47c32405c4877cedce3ff84ac7390646", "title": "A survey of datasets for visual tracking", "year": "2015", "pdf": ["http://www.isir.upmc.fr/files/2015ACLI3545.pdf"], "doi": ["https://doi.org/10.1007/s00138-015-0713-y", "http://hal.upmc.fr/hal-01217152/document"]}, {"id": "4a75c3441cef2069458fe61a01196c2c8b32ee92", "title": "Single-trial classification of EEG in a visual object task using ICA and machine learning", "year": "2014", "pdf": ["https://www.research.ed.ac.uk/portal/files/14632594/Stewart.JNeurosciMeth.228.2014.pdf"], "doi": ["https://www.sciencedirect.com/science/article/pii/S0165027014000752", "https://doi.org/10.1016/j.jneumeth.2014.02.014", "https://www.ncbi.nlm.nih.gov/pubmed/24613798"]}, {"id": "1456f147381bf7c385225d854c2fb48c19eca285", "title": "LCAV-31: a dataset for light field object recognition", "year": "2014", "pdf": ["http://infoscience.epfl.ch/record/197737/files/902014.pdf"], "doi": ["http://doi.org/10.1117/12.2041097"]}, {"id": "d7ed761cfe1b71aa7e4d08c355fcab131558f8c8", "title": "Learning Object Models on a Robot using Visual Context and Appearance Cues", "year": "2013", "pdf": ["https://pdfs.semanticscholar.org/d7ed/761cfe1b71aa7e4d08c355fcab131558f8c8.pdf"], "doi": []}, {"id": "d53c79cce46820642f2d4e0f0dac9b31d1201f24", "title": "Visual object trapping", "year": "2016", "pdf": [], "doi": ["https://doi.org/10.1016/j.cviu.2016.07.007"]}, {"id": "5ffd74d2873b7cba2cbc5fd295cc7fbdedca22a2", "title": "The Cityscapes Dataset", "year": "2015", "pdf": [], "doi": []}, {"id": "14ca963b4e0b87fc7213b8e3a3e2371cee7ffad6", "title": "Exploring Causal Relationships in Visual Object Tracking", "year": "2015", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7410708"]}, {"id": "f9c602cc436a9ea2f9e7db48c77d924e09ce3c32", "title": "Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms", "year": "2017", "pdf": ["https://arxiv.org/pdf/1708.07747.pdf"], "doi": []}, {"id": "3ecb007d46614d5e5566b0ad7c96c0c4c8ac0d14", "title": "Enhancing Object Recognition With Dynamic Cognitive Context", "year": "2016", "pdf": ["https://pdfs.semanticscholar.org/3ecb/007d46614d5e5566b0ad7c96c0c4c8ac0d14.pdf"], "doi": []}, {"id": "c8018f3dc6121d92da37f1756e7bd11a128aa55c", "title": "Region Filling and Object Removal by Exemplar based Image Inpainting", "year": "2015", "pdf": ["https://pdfs.semanticscholar.org/c801/8f3dc6121d92da37f1756e7bd11a128aa55c.pdf"], "doi": []}, {"id": "051d8bbf12877c46ae9a598a386c5b72d1b103ac", "title": "Object Detection using Geometrical Context Feedback", "year": "2012", "pdf": ["http://cvgl.stanford.edu/papers/Sun_IJCV_2012.pdf"], "doi": ["http://doi.org/10.1007/s11263-012-0547-2"]}, {"id": "b0cd469a06fb2eae3a5cc0c860aa592f71b13f6d", "title": "IQA: Visual Question Answering in Interactive Environments", "year": "2018", "pdf": [], "doi": ["http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8578528"]}]}
\ No newline at end of file