diff options
Diffstat (limited to 'site/datasets/final/voc.json')
| -rw-r--r-- | site/datasets/final/voc.json | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/site/datasets/final/voc.json b/site/datasets/final/voc.json index 4f442739..92735af6 100644 --- a/site/datasets/final/voc.json +++ b/site/datasets/final/voc.json @@ -1 +1 @@ -{"id": "abe9f3b91fd26fa1b50cd685c0d20debfb372f73", "paper": {"paper_id": "abe9f3b91fd26fa1b50cd685c0d20debfb372f73", "key": "voc", "title": "The Pascal Visual Object Classes Challenge: A Retrospective", "year": 2014, "pdf": "http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc14.pdf", "address": "", "name": "VOC"}, "address": null, "additional_papers": [], "citations": [{"id": "ed2f711cf9bcd9d7ab039d746af109ed9573421a", "title": "Pixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}, {"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/ed2f/711cf9bcd9d7ab039d746af109ed9573421a.pdf"}, {"id": "a6ac6463b5c89ac9eb013c978f213b309cc6a5c7", "title": "iSPA-Net: Iterative Semantic Pose Alignment Network", "addresses": [{"address": "Indian Institute of Science Bangalore", "lat": "13.02223470", "lng": "77.56718325", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1808.01134.pdf"}, {"id": "aaf4d938f2e66d158d5e635a9c1d279cdc7639c0", "title": "Toward visual understanding of everyday object", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/aaf4/d938f2e66d158d5e635a9c1d279cdc7639c0.pdf"}, {"id": "74dbcc09a3456ddacf5cece640b84045ebdf6be1", "title": "Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation", "addresses": [{"address": "University of Michigan", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu"}, {"address": "Simon Fraser University", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1810.05162.pdf"}, {"id": "dedc7b080b8e13d72f8dc33e248e7637d191fdbf", "title": "Beyond Dataset Bias: Multi-task Unaligned Shared Knowledge Transfer", "addresses": [{"address": "IDIAP Research Institute", "lat": "46.10923700", "lng": "7.08453549", "type": "edu"}, {"address": "University of Cambridge", "lat": "52.17638955", "lng": "0.14308882", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/dedc/7b080b8e13d72f8dc33e248e7637d191fdbf.pdf"}, {"id": "18c57ddc9c0164ee792661f43a5578f7a00d0330", "title": "ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases", "addresses": [{"address": "National Institutes of Health", "lat": "39.00041165", "lng": "-77.10327775", "type": "edu"}], "year": 2017, "pdf": "https://arxiv.org/pdf/1705.02315v2.pdf"}, {"id": "a825680aeb853fc34c65b5844c4c4391148f18c3", "title": "SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again", "addresses": [{"address": "Toyota Research Institute", "lat": "37.40253645", "lng": "-122.11655107", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1711.10006.pdf"}, {"id": "f249c266321d661ae398c26ddb8c7409f6455ba1", "title": "Revisiting Faster R-CNN: A Deeper Look at Region Proposal Network", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/f249/c266321d661ae398c26ddb8c7409f6455ba1.pdf"}, {"id": "7fa5ede4a34dbe604ce317d529eed78db6642bc0", "title": "Soft Proposal Networks for Weakly Supervised Object Localization", "addresses": [{"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}, {"address": "Duke University", "lat": "35.99905220", "lng": "-78.92906290", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1709.01829.pdf"}, {"id": "05fdd29536d55fe3ad00689b6f60ada8bc761e91", "title": "HOGgles: Visualizing Object Detection Features", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2013, "pdf": "http://people.csail.mit.edu/torralba/publications/ihog_iccv.pdf"}, {"id": "394bf41cd8578ec10cd34452c688c3e3de1c16a7", "title": "Multi-view to Novel View: Synthesizing Novel Views With Self-learned Confidence", "addresses": [{"address": "National Tsing Hua University", "lat": "24.79254840", "lng": "120.99511830", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/394b/f41cd8578ec10cd34452c688c3e3de1c16a7.pdf"}, {"id": "2453dd38cde21f3248b55d281405f11d58168fa9", "title": "Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation", "addresses": [{"address": "Chinese University of Hong Kong", "lat": "22.42031295", "lng": "114.20788644", "type": "edu"}], "year": 2016, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.342"}, {"id": "ccb9ffa26b28dffc4f7d613821d1a9f0d60ea3f4", "title": "Online Adaptation of Convolutional Neural Networks for Video Object Segmentation", "addresses": [{"address": "RWTH Aachen University", "lat": "50.77917030", "lng": "6.06728733", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1706.09364.pdf"}, {"id": "d38af10096aa90dfccd7e4cec9757900bf6958bd", "title": "MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network", "addresses": [{"address": "Middle East Technical University", "lat": "39.87549675", "lng": "32.78553506", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.04067.pdf"}, {"id": "8c1e828a4826a1fb3eb47ee432f5333b974fa141", "title": "Spatial Graph for Image Classification", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/8c1e/828a4826a1fb3eb47ee432f5333b974fa141.pdf"}, {"id": "2a31b4bf2a294b6e67956a6cd5ed6d875af548e0", "title": "Learning Affinity via Spatial Propagation Networks", "addresses": [{"address": "Dalian University of Technology", "lat": "38.88140235", "lng": "121.52281098", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1710.01020.pdf"}, {"id": "0790c400bfe6fbefe88ef7791476e1abf1952089", "title": "Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising", "addresses": [{"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": 2016, "pdf": "https://arxiv.org/pdf/1511.04067v1.pdf"}, {"id": "442cf9b24661c9ea5c2a1dcabd4a5b8af1cd89da", "title": "Beyond One-hot Encoding: lower dimensional target embedding", "addresses": [{"address": "University of Barcelona", "lat": "41.38689130", "lng": "2.16352385", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1806.10805.pdf"}, {"id": "04eda7eee3e0282de50e54554f50870dd17defa1", "title": "How Hard Can It Be? Estimating the Difficulty of Visual Search in an Image", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": 2016, "pdf": "https://arxiv.org/pdf/1705.08280v1.pdf"}, {"id": "90a4125974564a5ab6c2ce2ff685fc36e9cf0680", "title": "Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}, {"address": "Beijing Jiaotong University", "lat": "39.94976005", "lng": "116.33629046", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1703.08448.pdf"}, {"id": "c3dd6c1ddbb9cfcc1bed6383ffaa0b1ce4d13625", "title": "TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes", "addresses": [{"address": "Peking University", "lat": "39.99223790", "lng": "116.30393816", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.01544.pdf"}, {"id": "2976605dc3b73377696537291d45f09f1ab1fbf5", "title": "Cross-Stitch Networks for Multi-task Learning", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2016, "pdf": "http://www.ri.cmu.edu/pub_files/2016/6/multi-task.pdf"}, {"id": "25e9a2ec45c34d4610359196dc505a72c3833336", "title": "Benchmarking KAZE and MCM for Multiclass Classification", "addresses": [{"address": "Indian Institute of Technology Delhi", "lat": "28.54632595", "lng": "77.27325504", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/25e9/a2ec45c34d4610359196dc505a72c3833336.pdf"}, {"id": "935e639bebf905af2e35e8b1e7aa0538d7122185", "title": "A Network Structure to Explicitly Reduce Confusion Errors in Semantic Segmentation", "addresses": [{"address": "Beihang University", "lat": "39.98083330", "lng": "116.34101249", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1808.00313.pdf"}, {"id": "211435a4e14d00f4aaed191acfb548185ee800b9", "title": "Visual Saliency Based Multiple Objects Segmentation and its Parallel Implementation for Real-Time Vision Processing", "addresses": [{"address": "Akita Prefectural University", "lat": "39.80114990", "lng": "140.04591160", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/2114/35a4e14d00f4aaed191acfb548185ee800b9.pdf"}, {"id": "9fae24003bbedecdb617f9779215d79d06b90dd8", "title": "Where Are the Blobs: Counting by Localization with Point Supervision", "addresses": [{"address": "University of British Columbia", "lat": "49.25839375", "lng": "-123.24658161", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.09856.pdf"}, {"id": "c45681fa9d9c36a6a196017ef283ac38904f91bb", "title": "Pixel-wise object tracking", "addresses": [{"address": "New York University", "lat": "40.72925325", "lng": "-73.99625394", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1711.07377.pdf"}, {"id": "45f858f9e8d7713f60f52618e54089ba68dfcd6d", "title": "What Actions are Needed for Understanding Human Actions in Videos?", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://openaccess.thecvf.com/content_ICCV_2017/papers/Sigurdsson_What_Actions_Are_ICCV_2017_paper.pdf"}, {"id": "57bd01c042a5f64659b3a9f91c048b8594f762f6", "title": "Advances in fine-grained visual categorization", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/57bd/01c042a5f64659b3a9f91c048b8594f762f6.pdf"}, {"id": "9716416a15e79a36e3481bcdad79cdc905603e6d", "title": "Gaussian Word Embedding with a Wasserstein Distance Loss", "addresses": [{"address": "Fudan University", "lat": "31.30104395", "lng": "121.50045497", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1808.07016.pdf"}, {"id": "97265d64859e06900c11ae5bb5f03f3bd265f858", "title": "Multilabel Image Classification With Regional Latent Semantic Dependencies", "addresses": [{"address": "Nanjing University", "lat": "32.05659570", "lng": "118.77408833", "type": "edu"}, {"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}, {"address": "University of Technology Sydney", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1612.01082.pdf"}, {"id": "a19904e76b5ded44e6aeb9af85997d160de6bb22", "title": "TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/a199/04e76b5ded44e6aeb9af85997d160de6bb22.pdf"}, {"id": "96a9ca7a8366ae0efe6b58a515d15b44776faf6e", "title": "Grid Loss: Detecting Occluded Faces", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1609.00129.pdf"}, {"id": "513b8dc73a9fbc467e1ac130fe8c842b5839ca51", "title": "Dissertation Scalable Visual Navigation for Micro Aerial Vehicles using Geometric Prior Knowledge", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/513b/8dc73a9fbc467e1ac130fe8c842b5839ca51.pdf"}, {"id": "0ee3aa2a78f9680bb65a823bd9195c879572ec1c", "title": "What Makes an Object Memorable?", "addresses": [{"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}, {"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}, {"address": "University of California, Merced", "lat": "37.36566745", "lng": "-120.42158888", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Dubey_What_Makes_an_ICCV_2015_paper.pdf"}, {"id": "a776acc53591c3eb0b53501d9758d984e2e52a97", "title": "Weakly Supervised Instance Segmentation using Class Peak Response", "addresses": [{"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}, {"address": "Duke University", "lat": "35.99905220", "lng": "-78.92906290", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.00880.pdf"}, {"id": "423b941641728a21e37f41359a691815cdd84ceb", "title": "Reversible Recursive Instance-Level Object Segmentation", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/abs/1511.04517"}, {"id": "666939690c564641b864eed0d60a410b31e49f80", "title": "What Visual Attributes Characterize an Object Class?", "addresses": [{"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/6669/39690c564641b864eed0d60a410b31e49f80.pdf"}, {"id": "51e8e8c4cac8260ef21c25f9f2a0a68aedbc6d58", "title": "Deep Generative Adversarial Compression Artifact Removal", "addresses": [{"address": "University of Florence", "lat": "43.77764260", "lng": "11.25976500", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.02518.pdf"}, {"id": "3b01a839d174dad6f2635cff7ebe7e1aaad701a4", "title": "Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/3b01/a839d174dad6f2635cff7ebe7e1aaad701a4.pdf"}, {"id": "d467035d83fb4e86c4a47b2ca87894388deb8c44", "title": "Relief R-CNN : Utilizing Convolutional Feature Interrelationship for Object Detection", "addresses": [{"address": "University of Science and Technology of China", "lat": "31.83907195", "lng": "117.26420748", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/d467/035d83fb4e86c4a47b2ca87894388deb8c44.pdf"}, {"id": "264a2b946fae4af23c646cc08fc56947b5be82cf", "title": "Robust object recognition in RGB-D egocentric videos based on Sparse Affine Hull Kernel", "addresses": [{"address": "University of Texas at Austin", "lat": "30.28415100", "lng": "-97.73195598", "type": "edu"}], "year": 2015, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPRW.2015.7301302"}, {"id": "480888bad59b314236f2d947ebf308ae146c98e4", "title": "Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net", "addresses": [{"address": "University of California, Los Angeles", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1511.06881.pdf"}, {"id": "a1ee55d529e04a80f4eae3b30d0961a985a64fa4", "title": "Enabling low bitrate mobile visual recognition: a performance versus bandwidth evaluation", "addresses": [{"address": "National Taiwan University", "lat": "25.01682835", "lng": "121.53846924", "type": "edu"}], "year": 2013, "pdf": "http://www.cs.utexas.edu/~ycsu/publications/mm029-su.pdf"}, {"id": "0cd736baf31dceea1cc39ac72e00b65587f5fb9e", "title": "Learning Hash Functions Using Column Generation", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/4ad0/b6f189718a7287c6e7b90eb05331e56db334.pdf"}, {"id": "6424574cb92b316928c37232869bfadcb5b4c20f", "title": "C-WSL: Count-Guided Weakly Supervised Localization", "addresses": [{"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1711.05282.pdf"}, {"id": "51eba481dac6b229a7490f650dff7b17ce05df73", "title": "Situation Recognition: Visual Semantic Role Labeling for Image Understanding", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}], "year": 2016, "pdf": "http://grail.cs.washington.edu/wp-content/uploads/2016/09/yatskar2016srv.pdf"}, {"id": "961a5d5750f18e91e28a767b3cb234a77aac8305", "title": "Face Detection without Bells and Whistles", "addresses": [{"address": "ETH Z\u00fcrich", "lat": "47.37645340", "lng": "8.54770931", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/961a/5d5750f18e91e28a767b3cb234a77aac8305.pdf"}, {"id": "0c05f60998628884a9ac60116453f1a91bcd9dda", "title": "Optimizing Open-Ended Crowdsourcing: The Next Frontier in Crowdsourced Data Management", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/7b19/80d4ac1730fd0145202a8cb125bf05d96f01.pdf"}, {"id": "efa2aacb0fbee857015fad1dba72767f56be6f39", "title": "Aggregating Crowdsourced Image Segmentations", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}, {"address": "Facebook", "lat": "37.39367170", "lng": "-122.08072620", "type": "company"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/efa2/aacb0fbee857015fad1dba72767f56be6f39.pdf"}, {"id": "17113b0f647ce05b2e50d1d40c856370f94da7de", "title": "Zoom Better to See Clearer: Human Part Segmentation with Auto Zoom Net", "addresses": [{"address": "University of California, Los Angeles", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/1711/3b0f647ce05b2e50d1d40c856370f94da7de.pdf"}, {"id": "549d55a06c5402696e063ce36b411f341a64f8a9", "title": "Learning Deep Structure-Preserving Image-Text Embeddings", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}, {"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1511.06078v1.pdf"}, {"id": "44bfa5311f0921664e9036f63cadd71049a35f35", "title": "Faster R-CNN-Based Glomerular Detection in Multistained Human Whole Slide Images", "addresses": [{"address": "University of Tokyo", "lat": "35.90204480", "lng": "139.93622009", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/44bf/a5311f0921664e9036f63cadd71049a35f35.pdf"}, {"id": "133f1f2679892d408420d8092283539010723359", "title": "What Makes for Effective Detection Proposals?", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1502.05082v3.pdf"}, {"id": "98d04187f091f402a90a6a9a2108393ca5f91563", "title": "ADVIO: An Authentic Dataset for Visual-Inertial Odometry", "addresses": [{"address": "Aalto University", "lat": "60.18558755", "lng": "24.82427330", "type": "edu"}, {"address": "Tampere University of Technology", "lat": "61.44964205", "lng": "23.85877462", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.09828.pdf"}, {"id": "f8015e31d1421f6aee5e17fc3907070b8e0a5e59", "title": "Towards Usable Multimedia Event Detection from Web Videos", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/f801/5e31d1421f6aee5e17fc3907070b8e0a5e59.pdf"}, {"id": "6b9e8acef979c13fa9ecc8fe9b635b312fedbcbe", "title": "Multiple Structured-Instance Learning for Semantic Segmentation with Uncertain Training Data", "addresses": [{"address": "University of Southern California", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu"}], "year": 2014, "pdf": "https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Chang_Multiple_Structured-Instance_Learning_2014_CVPR_paper.pdf"}, {"id": "72fd97d21d6465d4bb407b6f8f3accd4419a2fb4", "title": "Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery", "addresses": [{"address": "University of Bristol", "lat": "51.45848370", "lng": "-2.60977520", "type": "edu"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/384a/ea88ffd79295c99bcb80552f8655dbb87509.pdf"}, {"id": "62b83bf64f200ebb9fa16dfb7108b85e390b2207", "title": "Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}, {"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.11236.pdf"}, {"id": "2577211aeaaa1f2245ddc379564813bee3d46c06", "title": "Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": 2016, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Misra_Seeing_Through_the_CVPR_2016_paper.pdf"}, {"id": "3900fb44902396f94fb070be41199b4beecc9081", "title": "Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1612.02101.pdf"}, {"id": "32c45df9e11e6751bcea1b928f398f6c134d22c6", "title": "Towards Unified Object Detection and Semantic Segmentation", "addresses": [{"address": "University of California, Los Angeles", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/32c4/5df9e11e6751bcea1b928f398f6c134d22c6.pdf"}, {"id": "2bcd59835528c583bb5b310522a5ba6e99c58b15", "title": "Multi-class Open Set Recognition Using Probability of Inclusion", "addresses": [{"address": "Harvard University", "lat": "42.36782045", "lng": "-71.12666653", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/c0ef/596a212d0e40c79c6760673fe122e517b43c.pdf"}, {"id": "3920a205990abc7883c70cc96a0410a2d056c2a8", "title": "Fast Object Segmentation in Unconstrained Video", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": 2013, "pdf": "http://groups.inf.ed.ac.uk/calvin/Publications/papazoglouICCV2013-camera-ready.pdf"}, {"id": "b6810adcfd507b2e019ebc8afe4f44f953faf946", "title": "ML-LocNet: Improving Object Localization with Multi-view Learning Network", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}, {"address": "University of Electronic Science and Technology of China", "lat": "40.01419050", "lng": "-83.03091430", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/b681/0adcfd507b2e019ebc8afe4f44f953faf946.pdf"}, {"id": "0e08cf0b19f0600dadce0f6694420d643ea9828b", "title": "The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}, {"address": "Oregon State University", "lat": "45.51982890", "lng": "-122.67797964", "type": "edu"}], "year": 2015, "pdf": "http://openaccess.thecvf.com/content_iccv_2015/papers/Humayun_The_Middle_Child_ICCV_2015_paper.pdf"}, {"id": "81bf7a4b8b3c21d42cb82f946f762c94031e11b8", "title": "Segmentation of Nerve on Ultrasound Images Using Deep Adversarial Network", "addresses": [{"address": "Zhejiang University", "lat": "30.19331415", "lng": "120.11930822", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/81bf/7a4b8b3c21d42cb82f946f762c94031e11b8.pdf"}, {"id": "30d8fbb9345cdf1096635af7d39a9b04af9b72f9", "title": "Watching plants grow - a position paper on computer vision and Arabidopsis thaliana", "addresses": [{"address": "Aberystwyth University", "lat": "52.41073580", "lng": "-4.05295501", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/30d8/fbb9345cdf1096635af7d39a9b04af9b72f9.pdf"}, {"id": "87204e4e1a96b8f59cb91828199dacd192292231", "title": "Towards Real-Time Detection and Tracking of Basketball Players using Deep Neural Networks", "addresses": [{"address": "University of Toronto", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/8720/4e4e1a96b8f59cb91828199dacd192292231.pdf"}, {"id": "30a4637cbc461838c151073b265fb08e00492ff4", "title": "Weakly Supervised Object Localization with Progressive Domain Adaptation", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}], "year": 2016, "pdf": "http://faculty.ucmerced.edu/mhyang/papers/cvpr16_object_localization.pdf"}, {"id": "606cfdcc43203351dbb944a3bb3719695e557e37", "title": "Ex Paucis Plura : Learning Affordance Segmentation from Very Few Examples", "addresses": [{"address": "University of Bonn", "lat": "50.73381240", "lng": "7.10224650", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/606c/fdcc43203351dbb944a3bb3719695e557e37.pdf"}, {"id": "47b6cd69c0746688f6e17b37d73fa12422826dbc", "title": "Self corrective Perturbations for Semantic Segmentation and Classification", "addresses": [{"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}, {"address": "University of Maryland College Park", "lat": "38.99203005", "lng": "-76.94610290", "type": "edu"}, {"address": "GE Global Research Center", "lat": "42.82982480", "lng": "-73.87719385", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/47b6/cd69c0746688f6e17b37d73fa12422826dbc.pdf"}, {"id": "14421119527aa5882e1552a651fbd2d73bc94637", "title": "Searching for objects driven by context", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}, {"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/9b81/86b6bc1e05d7a473d2afebc8a12698d88691.pdf"}, {"id": "3410a1489d04ec6fcfbb3d76d39055117931ccf0", "title": "Learning Collections of Part Models for Object Recognition", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}], "year": 2013, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.126"}, {"id": "69b647afe6526256a93033eac14ce470204e7bae", "title": "Training Deep Neural Networks via Direct Loss Minimization", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}, {"address": "University of Toronto", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d7dd/4fb9074db71ebf9155d64b439102d4c7b0c5.pdf"}, {"id": "81825711c2aaa1b9d3ead1a300e71c4353a41382", "title": "End-to-end training of object class detectors for mean average precision", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1607.03476.pdf"}, {"id": "2ce073da76e6ed87eda2da08da0e00f4f060f1a6", "title": "Deep Saliency with Encoded Low Level Distance Map and High Level Features", "addresses": [{"address": "SenseTime", "lat": "39.99300800", "lng": "116.32988200", "type": "company"}], "year": 2016, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.78"}, {"id": "2313c827d3cb9a291b6a00d015c29580862bbdcc", "title": "Weakly- and Semi-supervised Panoptic Segmentation", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1808.03575.pdf"}, {"id": "839a2155995acc0a053a326e283be12068b35cb8", "title": "Handcrafted Local Features are Convolutional Neural Networks", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/839a/2155995acc0a053a326e283be12068b35cb8.pdf"}, {"id": "634e02d6107529d672cbbdf5b97990966e289829", "title": "Cost-Effective Training of Deep CNNs with Active Model Adaptation", "addresses": [{"address": "Nanjing University", "lat": "32.05659570", "lng": "118.77408833", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1802.05394.pdf"}, {"id": "d0137881f6c791997337b9cc7f1efbd61977270d", "title": "University of Dundee An automated pattern recognition system for classifying indirect immunofluorescence images for HEp-2 cells and specimens Manivannan,", "addresses": [{"address": "University of Dundee", "lat": "56.45796755", "lng": "-2.98214831", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d013/7881f6c791997337b9cc7f1efbd61977270d.pdf"}, {"id": "ed173a39f4cd980eef319116b6ba39cec1b37c42", "title": "Associative Embedding: End-to-End Learning for Joint Detection and Grouping", "addresses": [{"address": "University of Michigan", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu"}, {"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1611.05424.pdf"}, {"id": "84cf838be40e2ab05732fbefbb93ccb2afb0cb48", "title": "Recognizing Handwritten Characters", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/84cf/838be40e2ab05732fbefbb93ccb2afb0cb48.pdf"}, {"id": "b082f440ee91e2751701401919584203b37e1e1a", "title": "SeedNet : Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation", "addresses": [{"address": "Seoul National University", "lat": "37.26728000", "lng": "126.98411510", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/303c/28f1ba643a7cd88255cc379e79052fb7e7b1.pdf"}, {"id": "6008213e4270e88cb414459de759c961469b92dd", "title": "Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning", "addresses": [{"address": "University of Hong Kong", "lat": "22.20814690", "lng": "114.25964115", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1802.09129.pdf"}, {"id": "90b4470032f2796a347a0080bcd833c2db0e8bf0", "title": "Improving Image Clustering With Multiple Pretrained CNN Feature Extractors", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.07760.pdf"}, {"id": "beecaf2d6e9d102b6b2459ea38e15179a4b55ffd", "title": "Surveillance Video Parsing with Single Frame Supervision", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1611.09587.pdf"}, {"id": "0fb8317a8bf5feaf297af8e9b94c50c5ed0e8277", "title": "Detecting Hands in Egocentric Videos: Towards Action Recognition", "addresses": [{"address": "University of Barcelona", "lat": "41.38689130", "lng": "2.16352385", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/0fb8/317a8bf5feaf297af8e9b94c50c5ed0e8277.pdf"}, {"id": "0e0179eb4b43016691f0f1473a08089dda21f8f0", "title": "The Art of Detection", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/0e01/79eb4b43016691f0f1473a08089dda21f8f0.pdf"}, {"id": "135c957f6a80f250507c7707479e584c288f430f", "title": "Image-Based Synthesis and Re-synthesis of Viewpoints Guided by 3D Models", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": 2014, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.498"}, {"id": "c72b063e23b8b45b57a42ebc2f9714297c539a6f", "title": "TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays", "addresses": [{"address": "National Institutes of Health", "lat": "39.00041165", "lng": "-77.10327775", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1801.04334.pdf"}, {"id": "061ffd3967540424ac4e4066f4a605d8318bab90", "title": "Dirichlet-Based Histogram Feature Transform for Image Classification", "addresses": [{"address": "National Institute of Advanced Industrial Science and Technology", "lat": "36.05238585", "lng": "140.11852361", "type": "edu"}], "year": 2014, "pdf": "https://staff.aist.go.jp/takumi.kobayashi/publication/2014/CVPR2014.pdf"}, {"id": "1a2e9a56e5f71bf95a2f68b6e67e2aaa1c6bf91e", "title": "FPM: Fine Pose Parts-Based Model with 3D CAD Models", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/1a2e/9a56e5f71bf95a2f68b6e67e2aaa1c6bf91e.pdf"}, {"id": "c6f58adf4a5ee8499cbc9b9bc1e6f1c39f1f8eae", "title": "Earn to P Ay a Ttention", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/c6f5/8adf4a5ee8499cbc9b9bc1e6f1c39f1f8eae.pdf"}, {"id": "3c8db2ca155ce4e15ec8a2c4c4b979de654fb296", "title": "Holistically-Nested Edge Detection", "addresses": [{"address": "University of California, San Diego", "lat": "32.87935255", "lng": "-117.23110049", "type": "edu"}], "year": 2015, "pdf": "http://pages.ucsd.edu/~ztu/publication/iccv15_hed.pdf"}, {"id": "8ccd6aaf1ee4b66c13fffbf560e3920f9bdf5f10", "title": "A multitask deep learning model for real-time deployment in embedded systems", "addresses": [{"address": "KTH Royal Institute of Technology, Stockholm", "lat": "59.34986645", "lng": "18.07063213", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/8ccd/6aaf1ee4b66c13fffbf560e3920f9bdf5f10.pdf"}, {"id": "b4f5cf797a1c857f32e5740d53d9990bc925af2b", "title": "Review of Segmentation with Deep Learning and Discover Its Application in Ultrasound Images", "addresses": [{"address": "University of Alberta", "lat": "53.52385720", "lng": "-113.52282665", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/b4f5/cf797a1c857f32e5740d53d9990bc925af2b.pdf"}, {"id": "3bad18554678ab46bbbf9de41d36423bc8083c83", "title": "Weakly Supervised Object Boundaries", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1511.07803v1.pdf"}, {"id": "07191c2047b5b643dd72a0583c1d537ba59f977a", "title": "Interactive Segmentation from 1-Bit Feedback", "addresses": [{"address": "National Tsing Hua University", "lat": "24.79254840", "lng": "120.99511830", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/0719/1c2047b5b643dd72a0583c1d537ba59f977a.pdf"}, {"id": "ae6e8851dfd9c97e37e1cbd61b21cc54d5e2b9c7", "title": "Paraphrasing Complex Network: Network Compression via Factor Transfer", "addresses": [{"address": "Seoul National University", "lat": "37.26728000", "lng": "126.98411510", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1802.04977.pdf"}, {"id": "5375a3344017d9502ebb4170325435de3da1fa16", "title": "Computer Vision \u2013 ACCV 2012", "addresses": [{"address": "Seoul National University", "lat": "37.26728000", "lng": "126.98411510", "type": "edu"}, {"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}, {"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": 2012, "pdf": "https://doi.org/10.1007/978-3-642-37447-0"}, {"id": "fdfd57d4721174eba288e501c0c120ad076cdca8", "title": "An Analysis of Action Recognition Datasets for Language and Vision Tasks", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.07129.pdf"}, {"id": "ec83c63e28ae2a658bc76a6750e078c3a54b9760", "title": "Deep Descriptor Transforming for Image Co-Localization", "addresses": [{"address": "Nanjing University", "lat": "32.05659570", "lng": "118.77408833", "type": "edu"}, {"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1705.02758.pdf"}, {"id": "b1177aad0db8bd6b605ffe0d68addaf97b1f9a6b", "title": "Visual Representations and Models: From Latent SVM to Deep Learning", "addresses": [{"address": "KTH Royal Institute of Technology, Stockholm", "lat": "59.34986645", "lng": "18.07063213", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/5035/733022916db7e5965c565327e169da1e2f39.pdf"}, {"id": "a5ae7d662ed086bc5b0c9a2c1dc54fcb23635000", "title": "Relief R-CNN : Utilizing Convolutional Feature Interrelationship for Fast Object Detection Deployment", "addresses": [{"address": "University of Science and Technology of China", "lat": "31.83907195", "lng": "117.26420748", "type": "edu"}, {"address": "Shenzhen University", "lat": "22.53521465", "lng": "113.93159110", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/a5ae/7d662ed086bc5b0c9a2c1dc54fcb23635000.pdf"}, {"id": "9528e2e8c20517ab916f803c0371abb4f0ed488b", "title": "Shallow and Deep Convolutional Networks for Saliency Prediction", "addresses": [{"address": "Dublin City University", "lat": "53.38522185", "lng": "-6.25740874", "type": "edu"}], "year": 2016, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Pan_Shallow_and_Deep_CVPR_2016_paper.pdf"}, {"id": "e2272f50ffa33b8e41509e4b795ad5a4eb27bb46", "title": "Region-based semantic segmentation with end-to-end training", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1607.07671.pdf"}, {"id": "b8d61dc56a4112e0317c6a7323417ee649476148", "title": "Cross Pixel Optical Flow Similarity for Self-Supervised Learning", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.05636.pdf"}, {"id": "db0a4af734dab1854c2e8dfe499fe0e353226e45", "title": "Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}, {"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/db0a/4af734dab1854c2e8dfe499fe0e353226e45.pdf"}, {"id": "ffe0f43206169deef3a2bf64cec90fe35bb1a8e5", "title": "Automated Processing of Imaging Data through Multi-tiered Classification of Biological Structures Illustrated Using Caenorhabditis elegans\n", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}, {"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/ffe0/f43206169deef3a2bf64cec90fe35bb1a8e5.pdf"}, {"id": "479eb6579194d4d944671dfe5e90b122ca4b58fd", "title": "Structural inference embedded adversarial networks for scene parsing", "addresses": [{"address": "Harbin Engineering University", "lat": "45.77445695", "lng": "126.67684917", "type": "edu"}, {"address": "Northwestern Polytechnical University", "lat": "34.24691520", "lng": "108.91061982", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/479e/b6579194d4d944671dfe5e90b122ca4b58fd.pdf"}, {"id": "d289ce63055c10937e5715e940a4bb9d0af7a8c5", "title": "DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications", "addresses": [{"address": "Singapore Management University", "lat": "1.29500195", "lng": "103.84909214", "type": "edu"}], "year": "2017", "pdf": "http://dl.acm.org/citation.cfm?id=3081360"}, {"id": "061bba574c7c2ef0ba9de91afc4fcab70feddd4f", "title": "Paying Attention to Descriptions Generated by Image Captioning Models", "addresses": [{"address": "Aalto University", "lat": "60.18558755", "lng": "24.82427330", "type": "edu"}, {"address": "University of Central Florida", "lat": "28.59899755", "lng": "-81.19712501", "type": "edu"}], "year": 2017, "pdf": "http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.272"}, {"id": "ee2217f9d22d6a18aaf97f05768035c38305d1fa", "title": "Detection of facial parts via deformable part model using part annotation", "addresses": [{"address": "Kobe University", "lat": "34.72757140", "lng": "135.23710000", "type": "edu"}], "year": 2015, "pdf": "https://doi.org/10.1109/APSIPA.2015.7415501"}, {"id": "18219d85bb14f851fc4714df19cc7f38dff8ddc3", "title": "Online Adaptation of Convolutional Neural Networks for the 2017 DAVIS Challenge on Video Object Segmentation", "addresses": [{"address": "RWTH Aachen University", "lat": "50.77917030", "lng": "6.06728733", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/1821/9d85bb14f851fc4714df19cc7f38dff8ddc3.pdf"}, {"id": "da44881db32c132eb9cdef524618e3c8ed340b47", "title": "Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters", "addresses": [{"address": "Shanghai Jiao Tong University", "lat": "31.20081505", "lng": "121.42840681", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1802.00383.pdf"}, {"id": "cc94b423c298003f0f164e63e63177d443291a77", "title": "Multi-View Semantic Labeling of 3D Point Clouds for Automated Plant Phenotyping", "addresses": [{"address": "University of Bonn", "lat": "50.73381240", "lng": "7.10224650", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.03994.pdf"}, {"id": "83a811fd947415df2413d15386dbc558f07595cb", "title": "Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN", "addresses": [{"address": "Peking University", "lat": "39.99223790", "lng": "116.30393816", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1709.08295.pdf"}, {"id": "3a5f5aca6138abcf22ede1af5572e01eb0f761d1", "title": "Optimizing Multivariate Performance Measures from Multi-View Data", "addresses": [{"address": "University of Technology Sydney", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/3a5f/5aca6138abcf22ede1af5572e01eb0f761d1.pdf"}, {"id": "ce300b006f42c1b64ca0e53d1cf28d11a98ece8f", "title": "Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l 1-Norm Distances", "addresses": [{"address": "Northwestern Polytechnical University", "lat": "34.24691520", "lng": "108.91061982", "type": "edu"}], "year": "", "pdf": "https://pdfs.semanticscholar.org/ce30/0b006f42c1b64ca0e53d1cf28d11a98ece8f.pdf"}, {"id": "71b038958df0b7855fc7b8b8e7dcde8537a7c1ad", "title": "Kernel Methods for Unsupervised Domain Adaptation by Boqing Gong", "addresses": [{"address": "University of Southern California", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/71b0/38958df0b7855fc7b8b8e7dcde8537a7c1ad.pdf"}, {"id": "af7cab9b4a2a2a565a3efe0a226c517f47289077", "title": "Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective", "addresses": [{"address": "Northwestern Polytechnical University", "lat": "34.24691520", "lng": "108.91061982", "type": "edu"}, {"address": "Australian National University", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1803.10910.pdf"}, {"id": "3a6ebdfb6375093885e846153a48139ef1ecfae6", "title": "The treasure beneath convolutional layers: Cross-convolutional-layer pooling for image classification", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": 2015, "pdf": "http://arxiv.org/abs/1411.7466"}, {"id": "a7e9d230bc44dfbe56757f3025d5b4caa49032f3", "title": "Unity in Diversity: Discovering Topics from Words - Information Theoretic Co-clustering for Visual Categorization", "addresses": [{"address": "University of Surrey", "lat": "51.24303255", "lng": "-0.59001382", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/a7e9/d230bc44dfbe56757f3025d5b4caa49032f3.pdf"}, {"id": "50137d663802224e683951c48970496b38b02141", "title": "DETRAC: A New Benchmark and Protocol for Multi-Object Tracking", "addresses": [{"address": "Hanyang University", "lat": "37.55572710", "lng": "127.04366420", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/5013/7d663802224e683951c48970496b38b02141.pdf"}, {"id": "07de8371ad4901356145722aa29abaeafd0986b9", "title": "Towards Usable Multimedia Event Detection", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/07de/8371ad4901356145722aa29abaeafd0986b9.pdf"}, {"id": "af386bb1b5e8c9f65b3ae836198a93aa860d6331", "title": "Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation", "addresses": [{"address": "IBM Thomas J. Watson Research Center", "lat": "41.21002475", "lng": "-73.80407056", "type": "company"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.04574.pdf"}, {"id": "d6b1b0e60e1764982ef95d4ade8fcaa10bfb156a", "title": "A Sketch-based Approach for Multimedia Retrieval", "addresses": [{"address": "International Institute of Information Technology", "lat": "17.44549570", "lng": "78.34854698", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d6b1/b0e60e1764982ef95d4ade8fcaa10bfb156a.pdf"}, {"id": "37b3637dab65b91a5c91bb6a583e69c448823cc1", "title": "Learning a Hierarchical Latent-Variable Model of 3D Shapes", "addresses": [{"address": "Imperial College London", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1705.05994.pdf"}, {"id": "83d16fb8f53156c9e2b28d75abb6532af515440f", "title": "Large-scale Document Labeling using Supervised Sequence Embedding", "addresses": [{"address": "Drexel University", "lat": "39.95740000", "lng": "-75.19026706", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/83d1/6fb8f53156c9e2b28d75abb6532af515440f.pdf"}, {"id": "05e45f61dc7577c50114a382abc6e952ae24cdac", "title": "Object Detection and Recognition in Natural Settings by George William Dittmar A thesis submitted in partial fulfilment of the requirements of the degree Master of Science in Computer Science Thesis Committee: Melanie Mitchell, Chair", "addresses": [{"address": "Portland State University", "lat": "45.51181205", "lng": "-122.68492999", "type": "edu"}], "year": "2012", "pdf": "https://pdfs.semanticscholar.org/05e4/5f61dc7577c50114a382abc6e952ae24cdac.pdf"}, {"id": "192235f5a9e4c9d6a28ec0d333e36f294b32f764", "title": "Reconfiguring the Imaging Pipeline for Computer Vision", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "Cornell University", "lat": "42.45055070", "lng": "-76.47835130", "type": "edu"}], "year": 2017, "pdf": "http://www.andrew.cmu.edu/user/sjayasur/iccv.pdf"}, {"id": "bd4f2e7a196c0d6033a49390ee8836f4f551b7c8", "title": "ICDAR 2015 competition on Robust Reading", "addresses": [{"address": "Czech Technical University", "lat": "50.07642960", "lng": "14.41802312", "type": "edu"}, {"address": "Kyushu University", "lat": "33.59914655", "lng": "130.22359848", "type": "edu"}], "year": 2015, "pdf": "http://rrc.cvc.uab.es/files/Robust-Reading-Competition-Karatzas.pdf"}, {"id": "3d5575e9ba02128d94c20330f4525fc816411ec2", "title": "Learning Video Object Segmentation from Static Images", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1612.02646.pdf"}, {"id": "78f62042bfb3bb49ba10e142d118a9bb058b2a19", "title": "WebSeg: Learning Semantic Segmentation from Web Searches", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/78f6/2042bfb3bb49ba10e142d118a9bb058b2a19.pdf"}, {"id": "0c7aac75ccd17d696cff2e1ce95db0493f5c18a2", "title": "VideoMatch: Matching Based Video Object Segmentation", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1809.01123.pdf"}, {"id": "6c78add400f749c897dc3eb93996eda1c796e91c", "title": "Enhanced Random Forest with Image/Patch-Level Learning for Image Understanding", "addresses": [{"address": "University of Malaya", "lat": "3.12267405", "lng": "101.65356103", "type": "edu"}, {"address": "Imperial College London", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu"}, {"address": "Peking University", "lat": "39.99223790", "lng": "116.30393816", "type": "edu"}], "year": "2014", "pdf": "https://arxiv.org/pdf/1410.3752.pdf"}, {"id": "b61c0b11b1c25958d202b4f7ca772e1d95ee1037", "title": "Bridging Category-level and Instance-level Semantic Image Segmentation", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/b61c/0b11b1c25958d202b4f7ca772e1d95ee1037.pdf"}, {"id": "79894ddf290d3c7a768d634eceb7888564b5cf19", "title": "Query-Guided Regression Network with Context Policy for Phrase Grounding", "addresses": [{"address": "University of Southern California", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.01676.pdf"}, {"id": "fec2a5a06a3aab5efe923a78d208ec747d5e4894", "title": "Generalizing to Unseen Domains via Adversarial Data Augmentation", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.12018.pdf"}, {"id": "5ac63895a7d3371a739d066bb1631fc178d8276a", "title": "Learning Semantic Feature Map for Visual Content Recognition", "addresses": [{"address": "Fudan University", "lat": "31.30104395", "lng": "121.50045497", "type": "edu"}, {"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": 2017, "pdf": "http://doi.acm.org/10.1145/3123266.3123379"}, {"id": "4e559f23bcf502c752f2938ad7f0182047b8d1e4", "title": "A Fast Approximate AIB Algorithm for Distributional Word Clustering", "addresses": [{"address": "University of Wollongong", "lat": "-34.40505545", "lng": "150.87834655", "type": "edu"}], "year": 2013, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Wang_A_Fast_Approximate_2013_CVPR_paper.pdf"}, {"id": "7536b6a9f3cb4ae810e2ef6d0219134b4e546dd0", "title": "Semi-Automatic Image Labelling Using Depth Information", "addresses": [{"address": "Australian National University", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/7536/b6a9f3cb4ae810e2ef6d0219134b4e546dd0.pdf"}, {"id": "11b89011298e193d9e6a1d99302221c1d8645bda", "title": "Structured Feature Selection", "addresses": [{"address": "Rensselaer Polytechnic Institute", "lat": "42.72984590", "lng": "-73.67950216", "type": "edu"}], "year": 2015, "pdf": "http://openaccess.thecvf.com/content_iccv_2015/papers/Gao_Structured_Feature_Selection_ICCV_2015_paper.pdf"}, {"id": "de3245c795bc50ebdb5d929c8da664341238264a", "title": "Generative Model With Coordinate Metric Learning for Object Recognition Based on 3D Models", "addresses": [{"address": "Beijing University of Posts and Telecommunications", "lat": "39.96014880", "lng": "116.35193921", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1705.08590.pdf"}, {"id": "cc2eaa182f33defbb33d69e9547630aab7ed9c9c", "title": "Surpassing Humans and Computers with JELLYBEAN: Crowd-Vision-Hybrid Counting Algorithms", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}, {"address": "Ohio State University", "lat": "40.00471095", "lng": "-83.02859368", "type": "edu"}, {"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/ce2e/e807a63bbdffa530c80915b04d11a7f29a21.pdf"}, {"id": "9c71e6f4e27b3a6f0f872ec683b0f6dfe0966c05", "title": "Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey", "addresses": [{"address": "Nanjing University", "lat": "32.05659570", "lng": "118.77408833", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/9c71/e6f4e27b3a6f0f872ec683b0f6dfe0966c05.pdf"}, {"id": "b88b83d2ffd30bf3bc3be3fb7492fd88f633b2fe", "title": "Subcategory-Aware Object Classification", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": 2013, "pdf": "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989a827.pdf"}, {"id": "b6a3802075d460093977f8566c451f950edf7a47", "title": "Facilitating and Exploring Planar Homogeneous Texture for Indoor Scene Understanding", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/0999/e5baf505eed0df8e2661c29354f3757b3399.pdf"}, {"id": "cd6cab9357f333ad9966abc76f830c190a1b7911", "title": "Recognition, reorganisation, reconstruction and reinteraction for scene understanding", "addresses": [{"address": "Oxford Brookes University", "lat": "51.75552050", "lng": "-1.22615970", "type": "edu"}], "year": "2014", "pdf": "https://pdfs.semanticscholar.org/cd6c/ab9357f333ad9966abc76f830c190a1b7911.pdf"}, {"id": "0fe8b5503681128da84a8454a4cc94470adc09ea", "title": "Sparsity Potentials for Detecting Objects with the Hough Transform", "addresses": [{"address": "ETH Z\u00fcrich", "lat": "47.37645340", "lng": "8.54770931", "type": "edu"}, {"address": "Sharif University of Technology", "lat": "35.70362270", "lng": "51.35125097", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/b96a/0ccae1d15cffe3b479b2c56d9132b05cd846.pdf"}, {"id": "9bbc952adb3e3c6091d45d800e806d3373a52bac", "title": "Learning Visual Classifiers using Human-centric Annotations", "addresses": [{"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/9bbc/952adb3e3c6091d45d800e806d3373a52bac.pdf"}, {"id": "6e209d7d33c0be8afae863f4e4e9c3e86826711f", "title": "Weakly-supervised segmentation by combining CNN feature maps and object saliency maps", "addresses": [{"address": "University of Electro-Communications", "lat": "35.65729570", "lng": "139.54255868", "type": "edu"}], "year": 2016, "pdf": "http://img.cs.uec.ac.jp/pub/conf16/161204shimok_1_ppt.pdf"}, {"id": "46d85e1dc7057bef62647bd9241601e9896a1b02", "title": "Improving object proposals with multi-thresholding straddling expansion", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2A_040_ext.pdf"}, {"id": "67e3fac91c699c085d47774990572d8ccdc36f15", "title": "Multiple Skip Connections and Dilated Convolutions for Semantic Segmentation", "addresses": [{"address": "Chubu University", "lat": "35.27426550", "lng": "137.01327841", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/67e3/fac91c699c085d47774990572d8ccdc36f15.pdf"}, {"id": "a4f29217d2120ed1490aea7e1c5b78c3b76e972f", "title": "Enhanced object detection via fusion with prior beliefs from image classification", "addresses": [{"address": "University of Southern California", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1610.06907.pdf"}, {"id": "f2d07a77711a8d74bbfa48a0436dae18a698b05a", "title": "Composite Statistical Learning and Inference for Semantic Segmentation", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}, {"address": "University of Coimbra", "lat": "40.20759510", "lng": "-8.42566148", "type": "edu"}, {"address": "Lund University", "lat": "55.70395710", "lng": "13.19020110", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/f2d0/7a77711a8d74bbfa48a0436dae18a698b05a.pdf"}, {"id": "ff11cb09e409996020a2dc3a8afc3b535e6b2482", "title": "Faster Bounding Box Annotation for Object Detection in Indoor Scenes", "addresses": [{"address": "Tampere University of Technology", "lat": "61.44964205", "lng": "23.85877462", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.03142.pdf"}, {"id": "e103fa24d7fa297cd206b22b3bf670bfda6c65c4", "title": "Object Detection in Very High-Resolution Aerial Images Using One-Stage Densely Connected Feature Pyramid Network", "addresses": [{"address": "Chonbuk National University", "lat": "35.84658875", "lng": "127.13501330", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/e103/fa24d7fa297cd206b22b3bf670bfda6c65c4.pdf"}, {"id": "9a781a01b5a9c210dd2d27db8b73b7d62bc64837", "title": "An Attempt to Build Object Detection Models by Reusing Parts", "addresses": [{"address": "Brown University", "lat": "41.82686820", "lng": "-71.40123146", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/9a78/1a01b5a9c210dd2d27db8b73b7d62bc64837.pdf"}, {"id": "ac559888f996923c06b1cf90db6b57b12e582289", "title": "Benchmarking neuromorphic vision: lessons learnt from computer vision", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}, {"address": "ETH Z\u00fcrich", "lat": "47.37645340", "lng": "8.54770931", "type": "edu"}, {"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/ac55/9888f996923c06b1cf90db6b57b12e582289.pdf"}, {"id": "2a4fc35acaf09517e9c63821cadd428a84832416", "title": "Learning object class detectors from weakly annotated video", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": 2012, "pdf": "http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_00905.pdf"}, {"id": "cd4850de71e4e858be5f5e6ef7f48d5bf7decea6", "title": "Distribution Entropy Boosted VLAD for Image Retrieval", "addresses": [{"address": "Jilin University", "lat": "22.05356500", "lng": "113.39913285", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/cd48/50de71e4e858be5f5e6ef7f48d5bf7decea6.pdf"}, {"id": "34b925a111ba29f73f5c0d1b363f357958d563c1", "title": "SAPPHIRE: An always-on context-aware computer vision system for portable devices", "addresses": [{"address": "Purdue University", "lat": "40.43197220", "lng": "-86.92389368", "type": "edu"}, {"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": 2015, "pdf": "https://www.microsoft.com/en-us/research/wp-content/uploads/2015/03/Shoaib_DATE_2015.pdf"}, {"id": "c76b611a986a2e09df22603d93b2d9125aaff369", "title": "Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation", "addresses": [{"address": "National Tsing Hua University", "lat": "24.79254840", "lng": "120.99511830", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1810.07050.pdf"}, {"id": "1927d01b6b9acf865401b544e25b62a7ddbac5fa", "title": "An Enhanced Region Proposal Network for object detection using deep learning method", "addresses": [{"address": "Jilin University", "lat": "22.05356500", "lng": "113.39913285", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/1927/d01b6b9acf865401b544e25b62a7ddbac5fa.pdf"}, {"id": "1ecd20f7fc34344e396825d27bc5a9871ab0d0c2", "title": "SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation", "addresses": [{"address": "University of Technology Sydney", "lat": "-33.88096510", "lng": "151.20107299", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1810.09091.pdf"}, {"id": "26aa0aff1ea1baf848a521363cc455044690e090", "title": "A 2D + 3D Rich Data Approach to Scene Understanding", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/26aa/0aff1ea1baf848a521363cc455044690e090.pdf"}, {"id": "3548cb9ee54bd4c8b3421f1edd393da9038da293", "title": "(Unseen) event recognition via semantic compositionality", "addresses": [{"address": "University of Trento", "lat": "46.06588360", "lng": "11.11598940", "type": "edu"}], "year": 2012, "pdf": "http://www.huppelen.nl/publications/2012cvprUnseenEventCompositionality.pdf"}, {"id": "25ee08db14dca641d085584909b551042618b8bf", "title": "Learning to Segment Instances in Videos with Spatial Propagation Network", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}, {"address": "University of California, Merced", "lat": "37.36566745", "lng": "-120.42158888", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/25ee/08db14dca641d085584909b551042618b8bf.pdf"}, {"id": "d0f81c31e11af1783644704321903a3d2bd83fd6", "title": "3D Fa\u00e7ade Labeling over Complex Scenarios: A Case Study Using Convolutional Neural Network and Structure-From-Motion", "addresses": [{"address": "University of Stuttgart", "lat": "48.90953380", "lng": "9.18318920", "type": "edu"}, {"address": "University of Exeter", "lat": "50.73693020", "lng": "-3.53647672", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/d0f8/1c31e11af1783644704321903a3d2bd83fd6.pdf"}, {"id": "a996f22a2d0c685f7e4972df9f45e99efc3cbb76", "title": "Towards the Success Rate of One: Real-Time Unconstrained Salient Object Detection", "addresses": [{"address": "University of Maryland College Park", "lat": "38.99203005", "lng": "-76.94610290", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1708.00079.pdf"}, {"id": "4da5f0c1d07725a06c6b4a2646e31ea3a5f14435", "title": "End-to-End Training of Hybrid CNN-CRF Models for Semantic Segmentation using Structured Learning", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/4da5/f0c1d07725a06c6b4a2646e31ea3a5f14435.pdf"}, {"id": "26c58e24687ccbe9737e41837aab74e4a499d259", "title": "Codemaps - Segment, Classify and Search Objects Locally", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2013, "pdf": "http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Li_Codemaps_-_Segment_2013_ICCV_paper.pdf"}, {"id": "299b65d5d3914dad9aae2f936165dcebcf78db88", "title": "Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation", "addresses": [{"address": "Google", "lat": "37.42199990", "lng": "-122.08405750", "type": "company"}], "year": 2015, "pdf": "http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.203"}, {"id": "cb5dcd048b0eaa78a887a014be26a8a7b1325d36", "title": "Joint Learning of Set Cardinality and State Distribution", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1709.04093.pdf"}, {"id": "63660c50e2669a5115c2379e622549d8ed79be00", "title": "Deep Salient Object Detection by Integrating Multi-level Cues", "addresses": [{"address": "Northwestern Polytechnical University", "lat": "34.24691520", "lng": "108.91061982", "type": "edu"}, {"address": "Australian National University", "lat": "-35.27769990", "lng": "149.11852700", "type": "edu"}], "year": 2017, "pdf": "http://porikli.com/mysite/pdfs/porikli%202017%20-%20Deep%20salient%20object%20detection%20by%20integrating%20multi-level%20cues.pdf"}, {"id": "472541ccd941b9b4c52e1f088cc1152de9b3430f", "title": "Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses", "addresses": [{"address": "Technical University Munich", "lat": "48.14955455", "lng": "11.56775314", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1612.00197.pdf"}, {"id": "9184b0c04013bfdfd82f4f271b5f017396c2f085", "title": "Semantic Segmentation for Line Drawing Vectorization Using Neural Networks", "addresses": [{"address": "ETH Z\u00fcrich", "lat": "47.37645340", "lng": "8.54770931", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/9184/b0c04013bfdfd82f4f271b5f017396c2f085.pdf"}, {"id": "57488aa24092fa7118aa5374c90b282a32473cf9", "title": "A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "University of Pennsylvania", "lat": "39.94923440", "lng": "-75.19198985", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.01257.pdf"}, {"id": "7771807cd05f78a4591f2d0b094ddd3e0bd5339a", "title": "Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors", "addresses": [{"address": "Nanjing University", "lat": "32.05659570", "lng": "118.77408833", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1707.06399.pdf"}, {"id": "4558338873556d01fd290de6ddc55721c633a1ad", "title": "Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation", "addresses": [{"address": "Cambridge University", "lat": "50.79440260", "lng": "-1.09717480", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/4558/338873556d01fd290de6ddc55721c633a1ad.pdf"}, {"id": "85957b49896246bb416c0a182e52b355a8fa40b4", "title": "Feature Pyramid Network for Multi-Class Land Segmentation", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1806.03510.pdf"}, {"id": "f5eb411217f729ad7ae84bfd4aeb3dedb850206a", "title": "Tackling Low Resolution for Better Scene Understanding", "addresses": [{"address": "International Institute of Information Technology", "lat": "17.44549570", "lng": "78.34854698", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/f5eb/411217f729ad7ae84bfd4aeb3dedb850206a.pdf"}, {"id": "7fb8d9c36c23f274f2dd84945dd32ec2cc143de1", "title": "Semantic Segmentation with Second-Order Pooling", "addresses": [{"address": "Institute of Systems and Robotics", "lat": "53.83383710", "lng": "10.70359390", "type": "edu"}, {"address": "University of Bonn", "lat": "50.73381240", "lng": "7.10224650", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/8e44/ba779d7cdc23d597c2c6e4420129834e7e21.pdf"}, {"id": "b5e3beb791cc17cdaf131d5cca6ceb796226d832", "title": "Novel Dataset for Fine-Grained Image Categorization: Stanford Dogs", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/b5e3/beb791cc17cdaf131d5cca6ceb796226d832.pdf"}, {"id": "b5968e7bb23f5f03213178c22fd2e47af3afa04c", "title": "Multiple-Human Parsing in the Wild", "addresses": [{"address": "Beijing Jiaotong University", "lat": "39.94976005", "lng": "116.33629046", "type": "edu"}, {"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1705.07206.pdf"}, {"id": "532c089b43983935e1001c5e35aa35440263beaf", "title": "G-Distillation: Reducing Overconfident Errors on Novel Samples", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.03166.pdf"}, {"id": "35fc0b28d0d674b28dd625d170bc641a36b17318", "title": "CSI: Composite Statistical Inference Techniques for Semantic Segmentation", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}, {"address": "Lund University", "lat": "55.70395710", "lng": "13.19020110", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/35fc/0b28d0d674b28dd625d170bc641a36b17318.pdf"}, {"id": "e4cb27d2a3e1153cb517d97d61de48ff0483c988", "title": "Viktoria Plemakova Vehicle Detection Based on Convolutional Neural Networks", "addresses": [{"address": "University of Tartu", "lat": "58.38131405", "lng": "26.72078081", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/e4cb/27d2a3e1153cb517d97d61de48ff0483c988.pdf"}, {"id": "3d0660e18c17db305b9764bb86b21a429241309e", "title": "Counting Everyday Objects in Everyday Scenes", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1604.03505.pdf"}, {"id": "a67da2dd79c01e8cc4029ecc5a05b97967403862", "title": "On Selecting Helpful Unlabeled Data for Improving Semi-Supervised Support Vector Machines", "addresses": [{"address": "Myongji University", "lat": "37.23810230", "lng": "127.19034310", "type": "edu"}], "year": "2014", "pdf": "https://pdfs.semanticscholar.org/a67d/a2dd79c01e8cc4029ecc5a05b97967403862.pdf"}, {"id": "4ab69672e1116427d685bf7c1edb5b1fd0573b5e", "title": "Spatial pooling of heterogeneous features for image applications", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}], "year": 2012, "pdf": "http://bigml.cs.tsinghua.edu.cn/~lingxi/PDFs/Xie_ACMMM12_EdgeGPP.pdf"}, {"id": "989c7cdafa9b90ab2ea0a9d8fa60634cc698f174", "title": "YoloFlow Real - time Object Tracking in Video CS 229 Course Project", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/989c/7cdafa9b90ab2ea0a9d8fa60634cc698f174.pdf"}, {"id": "85af6c005df806b57b306a732dcb98e096d15bfb", "title": "Getting to Know Low-light Images with The Exclusively Dark Dataset", "addresses": [{"address": "University of Malaya", "lat": "3.12267405", "lng": "101.65356103", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.11227.pdf"}, {"id": "cdb293381ff396d6e9c0f5e9578d411e759347fd", "title": "3 DR 2 N 2 : A Unified Approach for Single and Multiview 3 D Object Reconstruction", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/022e/eae0edc09deb228da26d5390874f781ace0f.pdf"}, {"id": "0e67717484684d90ae9d4e1bb9cdceb74b194910", "title": "Mining Pixels: Weakly Supervised Semantic Segmentation Using Image Labels", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/0e67/717484684d90ae9d4e1bb9cdceb74b194910.pdf"}, {"id": "5b4b84ce3518c8a14f57f5f95a1d07fb60e58223", "title": "Diagnosing Error in Object Detectors", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}], "year": "2012", "pdf": "https://pdfs.semanticscholar.org/9f92/05a60ddf1135929e0747db34363b3a8c6bc8.pdf"}, {"id": "47203943c86e4d9355ffd99cd3d75f37211fd805", "title": "Semi-Crowdsourced Clustering: Generalizing Crowd Labeling by Robust Distance Metric Learning", "addresses": [{"address": "Michigan State University", "lat": "42.71856800", "lng": "-84.47791571", "type": "edu"}, {"address": "GE Global Research Center", "lat": "42.82982480", "lng": "-73.87719385", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/be18/9c7066c4d99d617d137c975139c594ad09af.pdf"}, {"id": "45ff38add61df32a027048624f58952a67a7c5f5", "title": "Deep Context Convolutional Neural Networks for Semantic Segmentation", "addresses": [{"address": "Temple University", "lat": "39.95472495", "lng": "-75.15346905", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/45ff/38add61df32a027048624f58952a67a7c5f5.pdf"}, {"id": "0a789733ccb300d0dd9df6174faaa7e8c64e0409", "title": "High-Resolution Multispectral Dataset for Semantic Segmentation", "addresses": [{"address": "Rochester Institute of Technology", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/0a78/9733ccb300d0dd9df6174faaa7e8c64e0409.pdf"}, {"id": "9d3a6e459e0cecda20a8afd69d182877ff0224cf", "title": "A Framework for Articulated Hand Pose Estimation and Evaluation", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/9d3a/6e459e0cecda20a8afd69d182877ff0224cf.pdf"}, {"id": "943a1e218b917172199e524944006aa349f58968", "title": "Joint Learning of Intrinsic Images and Semantic Segmentation", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.11857.pdf"}, {"id": "5f68e2131d9275d56092e9fca05bcfc65abea0d8", "title": "Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}], "year": 2015, "pdf": "http://doi.acm.org/10.1145/2806416.2806469"}, {"id": "f989a20fbcc2d576c0c4514a0e5085c741580778", "title": "Co-localization with Category-Consistent Features and Geodesic Distance Propagation", "addresses": [{"address": "Stony Brook University", "lat": "40.91531960", "lng": "-73.12706260", "type": "edu"}, {"address": "Harvard University", "lat": "42.36782045", "lng": "-71.12666653", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1612.03236.pdf"}, {"id": "cf94200a476dc15d6da95db809349db4cfd8e92c", "title": "Leveraging Motion Priors in Videos for Improving Human Segmentation", "addresses": [{"address": "National Tsing Hua University", "lat": "24.79254840", "lng": "120.99511830", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.11436.pdf"}, {"id": "25dba68e4db0ce361032126b91f734f9252cae7c", "title": "DeepSetNet: Predicting Sets with Deep Neural Networks", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1611.08998.pdf"}, {"id": "883767948f535ea2bf8a0c03047ca9064e1b078f", "title": "A Combination of Object Recognition and Localisation for an Autonomous Racecar", "addresses": [{"address": "KTH Royal Institute of Technology, Stockholm", "lat": "59.34986645", "lng": "18.07063213", "type": "edu"}], "year": "", "pdf": "https://pdfs.semanticscholar.org/8837/67948f535ea2bf8a0c03047ca9064e1b078f.pdf"}, {"id": "18095a530b532a70f3b615fef2f59e6fdacb2d84", "title": "Deep Structured Scene Parsing by Learning with Image Descriptions", "addresses": [{"address": "Sun Yat-Sen University", "lat": "23.09461185", "lng": "113.28788994", "type": "edu"}, {"address": "Harbin Institute of Technology", "lat": "45.74139210", "lng": "126.62552755", "type": "edu"}], "year": 2016, "pdf": "https://arxiv.org/pdf/1604.02271v3.pdf"}, {"id": "9397e7acd062245d37350f5c05faf56e9cfae0d6", "title": "DeepFruits: A Fruit Detection System Using Deep Neural Networks", "addresses": [{"address": "Queensland University of Technology", "lat": "-27.47715625", "lng": "153.02841004", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/9397/e7acd062245d37350f5c05faf56e9cfae0d6.pdf"}, {"id": "03a24d15533dae78de78fd9d5f6c9050fb97f186", "title": "Pedestrian detection aided by scale-discriminative network", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}], "year": 2016, "pdf": "https://doi.org/10.1109/SSCI.2016.7850112"}, {"id": "17d4fd92352baf6f0039ec64d43ca572c8252384", "title": "MoE-SPNet: A mixture-of-experts scene parsing network", "addresses": [{"address": "University of Sydney", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1806.07049.pdf"}, {"id": "30a29f6c407749e97bc7c2db5674a62773af9d27", "title": "Tracking and Visual Quality Inspection in Harsh Environments (print-version)", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/30a2/9f6c407749e97bc7c2db5674a62773af9d27.pdf"}, {"id": "280d632ef3234c5ab06018c6eaccead75bc173b3", "title": "Efficient Image and Video Co-localization with Frank-Wolfe Algorithm", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/6b1a/c8e438041ac02cc8fab5762ca069c386f473.pdf"}, {"id": "0f945f796a9343b51a3dc69941c0fa1a98c0f448", "title": "Local Hypersphere Coding Based on Edges between Visual Words", "addresses": [{"address": "University of Science and Technology of China", "lat": "31.83907195", "lng": "117.26420748", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/a7ef/979ce52b9e4bcbd6ee5524dfd4e92baf6292.pdf"}, {"id": "0db6a58927a671c01089c53248b0e1c36bdc3231", "title": "Efficient Point Process Inference for Large-Scale Object Detection", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": 2016, "pdf": "http://openaccess.thecvf.com/content_cvpr_2016/papers/Pham_Efficient_Point_Process_CVPR_2016_paper.pdf"}, {"id": "14d0afea52c4e9b7a488f6398e4a92bd4f4b93c7", "title": "Rethinking the Faster R-CNN Architecture for Temporal Action Localization", "addresses": [{"address": "University of Michigan", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.07667.pdf"}, {"id": "8da1b0834688edb311a803532e33939e9ecf8292", "title": "CornerNet: Detecting Objects as Paired Keypoints", "addresses": [{"address": "University of Michigan", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1808.01244.pdf"}, {"id": "f42d3225afd9e463ddb7a355f64b54af8bd14227", "title": "Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation", "addresses": [{"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.10343.pdf"}, {"id": "a1dd88f44d045b360569a9a8721f728afbd951c3", "title": "Relief Impression Image Detection : Unsupervised Extracting Objects Directly From Feature Arrangements of Deep CNN", "addresses": [{"address": "University of Science and Technology of China", "lat": "31.83907195", "lng": "117.26420748", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/a1dd/88f44d045b360569a9a8721f728afbd951c3.pdf"}, {"id": "fc027fccb19512a439fc17181c34ee1c3aad51b5", "title": "Joint Multi-person Pose Estimation and Semantic Part Segmentation", "addresses": [{"address": "University of California, Los Angeles", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.03383.pdf"}, {"id": "377f2b65e6a9300448bdccf678cde59449ecd337", "title": "Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results", "addresses": [{"address": "Johns Hopkins University", "lat": "39.32905300", "lng": "-76.61942500", "type": "edu"}, {"address": "Rutgers University", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.10275.pdf"}, {"id": "451eed7fd8ae281d1cc76ca8cdecbaf47816e55a", "title": "Close Yet Distinctive Domain Adaptation", "addresses": [{"address": "Shanghai Jiao Tong University", "lat": "31.20081505", "lng": "121.42840681", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/451e/ed7fd8ae281d1cc76ca8cdecbaf47816e55a.pdf"}, {"id": "992b93ab9d016640551a8cebcaf4757288154f32", "title": "Nested Pictorial Structures", "addresses": [{"address": "Duke University", "lat": "35.99905220", "lng": "-78.92906290", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/e38c/f96363aaf1f17c487c484ad27d3175ca4b31.pdf"}, {"id": "7489990ea3d6ab4c1c86c9ed9f049399961dfaef", "title": "Normalized cutswith soft must-link constraints for image segmentation and clustering", "addresses": [{"address": "Rochester Institute of Technology", "lat": "43.08250655", "lng": "-77.67121663", "type": "edu"}], "year": 2014, "pdf": "https://people.rit.edu/ndcsma/pubs/WNYISPW_Nov_2014_Chew.pdf"}, {"id": "41199678ad9370ff8ca7e9e3c2617b62a297fac3", "title": "Multitask Deep Learning models for real-time deployment in embedded systems", "addresses": [{"address": "KTH Royal Institute of Technology, Stockholm", "lat": "59.34986645", "lng": "18.07063213", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/4119/9678ad9370ff8ca7e9e3c2617b62a297fac3.pdf"}, {"id": "7fb74f5abab4830e3cdaf477230e5571d9e3ca57", "title": "Polyhedral Conic Classifiers for Visual Object Detection and Classification", "addresses": [{"address": "Eskisehir Osmangazi University", "lat": "39.74875160", "lng": "30.47653071", "type": "edu"}], "year": 2017, "pdf": "http://openaccess.thecvf.com/content_cvpr_2017/papers/Cevikalp_Polyhedral_Conic_Classifiers_CVPR_2017_paper.pdf"}, {"id": "10793d1475607929fedc6d9a677911ad16843e58", "title": "Unsupervised Learning of Edges", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": 2016, "pdf": "http://openaccess.thecvf.com/content_cvpr_2016/papers/Li_Unsupervised_Learning_of_CVPR_2016_paper.pdf"}, {"id": "c94fd258a8f1e8f4033a7fe491f1372dcf7d3cd6", "title": "TS ^2 2 C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection", "addresses": [{"address": "Fudan University", "lat": "31.30104395", "lng": "121.50045497", "type": "edu"}, {"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.04897.pdf"}, {"id": "2581a12189eb1a0b5b27a7fd1c2cbe44c88fcc20", "title": "Analyzing Classifiers: Fisher Vectors and Deep Neural Networks", "addresses": [{"address": "TU Berlin", "lat": "52.51806410", "lng": "13.32504250", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1512.00172v1.pdf"}, {"id": "96416b1b44fb05302c6e9a8ab1b74d9204995e73", "title": "Learning Effective Binary Visual Representations with Deep Networks", "addresses": [{"address": "Nanjing University", "lat": "32.05659570", "lng": "118.77408833", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/9641/6b1b44fb05302c6e9a8ab1b74d9204995e73.pdf"}, {"id": "aa2ddae22760249729ac2c2c4e24c8b665bcd40e", "title": "Interpretable Basis Decomposition for Visual Explanation", "addresses": [{"address": "MIT CSAIL", "lat": "42.36194070", "lng": "-71.09043780", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/8c47/635ae7f1641c2bdd45026ad7dbff70c24398.pdf"}, {"id": "60542b1a857024c79db8b5b03db6e79f74ec8f9f", "title": "Learning to Detect Human-Object Interactions", "addresses": [{"address": "University of Michigan", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1702.05448.pdf"}, {"id": "bd8a85acaa45d4068fca584e8d9e3bd3bb4eea4d", "title": "Toward Scene Recognition by Discovering Semantic Structures and Parts", "addresses": [{"address": "Shandong University", "lat": "36.36934730", "lng": "120.67381800", "type": "edu"}, {"address": "Simon Fraser University", "lat": "49.27674540", "lng": "-122.91777375", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/bd8a/85acaa45d4068fca584e8d9e3bd3bb4eea4d.pdf"}, {"id": "456abee9c8d31f004b2f0a3b47222043e20f5042", "title": "Unsupervised Visual Sense Disambiguation for Verbs using Multimodal Embeddings", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1603.09188.pdf"}, {"id": "7c2f6424b0bb2c28f282fbc0b4e98bf85d5584eb", "title": "Relief R-CNN: Utilizing Convolutional Feature Interrelationship for Fast Object Detection Deployment", "addresses": [{"address": "University of Science and Technology of China", "lat": "31.83907195", "lng": "117.26420748", "type": "edu"}, {"address": "Shenzhen University", "lat": "22.53521465", "lng": "113.93159110", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/a5ae/7d662ed086bc5b0c9a2c1dc54fcb23635000.pdf"}, {"id": "59e9934720baf3c5df3a0e1e988202856e1f83ce", "title": "UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking", "addresses": [{"address": "Hanyang University", "lat": "37.55572710", "lng": "127.04366420", "type": "edu"}], "year": "2015", "pdf": "https://arxiv.org/pdf/1511.04136.pdf"}, {"id": "d58c44bd9b464d9ac1db1344445c31364925f75a", "title": "TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights", "addresses": [{"address": "University of Electronic Science and Technology of China", "lat": "40.01419050", "lng": "-83.03091430", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/d58c/44bd9b464d9ac1db1344445c31364925f75a.pdf"}, {"id": "81ba5202424906f64b77f68afca063658139fbb2", "title": "Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}, {"address": "IDIAP Research Institute", "lat": "46.10923700", "lng": "7.08453549", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1611.09078.pdf"}, {"id": "0b6f64c78c44dc043e2972fa7bfe2a5753768609", "title": "A future for learning semantic models of man-made environments", "addresses": [{"address": "University of Bonn", "lat": "50.73381240", "lng": "7.10224650", "type": "edu"}], "year": 2016, "pdf": "https://doi.org/10.1109/ICPR.2016.7900008"}, {"id": "016eb7b32d1fdec0899151fb03799378bf59bbe5", "title": "Point Linking Network for Object Detection", "addresses": [{"address": "Huazhong University of Science and Technology", "lat": "30.50975370", "lng": "114.40628810", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/016e/b7b32d1fdec0899151fb03799378bf59bbe5.pdf"}, {"id": "cd9d654c6a4250e0cf8bcfddc2afab9e70ee6cae", "title": "Object Detection with Mask-based Feature Encoding", "addresses": [{"address": "University of South Carolina", "lat": "33.99282980", "lng": "-81.02685168", "type": "edu"}, {"address": "Tianjin University", "lat": "36.20304395", "lng": "117.05842113", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/cd9d/654c6a4250e0cf8bcfddc2afab9e70ee6cae.pdf"}, {"id": "28737575297a20d431dd2b777a79a8be2c9c2bbd", "title": "Object Ranking on Deformable Part Models with Bagged LambdaMART", "addresses": [{"address": "Beijing University of Posts and Telecommunications", "lat": "39.96014880", "lng": "116.35193921", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/2873/7575297a20d431dd2b777a79a8be2c9c2bbd.pdf"}, {"id": "46702e0127e16a4d6a1feda3ffc5f0f123957e87", "title": "Revisit Multinomial Logistic Regression in Deep Learning: Data Dependent Model Initialization for Image Recognition", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1809.06131.pdf"}, {"id": "d2b2cb1d5cc1aa30cf5be7bcb0494198934caabb", "title": "A Restricted Visual Turing Test for Deep Scene and Event Understanding", "addresses": [{"address": "University of California, Los Angeles", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/d2b2/cb1d5cc1aa30cf5be7bcb0494198934caabb.pdf"}, {"id": "446fbff6a2a7c9989b0a0465f960e236d9a5e886", "title": "Context Encoders: Feature Learning by Inpainting", "addresses": [{"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": 2016, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Pathak_Context_Encoders_Feature_CVPR_2016_paper.pdf"}, {"id": "291e5377df2eec4835b5c6889896941831a11c69", "title": "Recovering 6D Object Pose: Multi-modal Analyses on Challenges", "addresses": [{"address": "Imperial College London", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/291e/5377df2eec4835b5c6889896941831a11c69.pdf"}, {"id": "b69fbf046faf685655b5fa52fef07fb77e75eff4", "title": "Modeling guidance and recognition in categorical search: bridging human and computer object detection.", "addresses": [{"address": "Stony Brook University", "lat": "40.91531960", "lng": "-73.12706260", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/b69f/bf046faf685655b5fa52fef07fb77e75eff4.pdf"}, {"id": "13bda03fc8984d5943ed8d02e49a779d27c84114", "title": "Efficient object detection using cascades of nearest convex model classifiers", "addresses": [{"address": "Eskisehir Osmangazi University", "lat": "39.74875160", "lng": "30.47653071", "type": "edu"}], "year": 2012, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2012.6248047"}, {"id": "87a66ccc68374ffb704ee6fb9fa7df369718095c", "title": "Multi-person Pose Estimation with Local Joint-to-Person Associations", "addresses": [{"address": "University of Bonn", "lat": "50.73381240", "lng": "7.10224650", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/ea90/16fb585ba6449d3d6f98bf85fa0bcd1f4621.pdf"}, {"id": "4960ab1cef23e5ccd60173725ea280f462164a0e", "title": "Video Object Segmentation by Learning Location-Sensitive Embeddings", "addresses": [{"address": "Peking University", "lat": "39.99223790", "lng": "116.30393816", "type": "edu"}, {"address": "Microsoft Research Asia", "lat": "39.97721700", "lng": "116.33763200", "type": "company"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/4960/ab1cef23e5ccd60173725ea280f462164a0e.pdf"}, {"id": "8856fbf333b2aba7b9f1f746e16a2b7f083ee5b8", "title": "Analyzing animal behavior via classifying each video frame using convolutional neural networks", "addresses": [{"address": "Duke University", "lat": "35.99905220", "lng": "-78.92906290", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/8856/fbf333b2aba7b9f1f746e16a2b7f083ee5b8.pdf"}, {"id": "f9f01af981f8d25f0c96ea06d88be62dabb79256", "title": "Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network", "addresses": [{"address": "Xidian University", "lat": "34.12358250", "lng": "108.83546000", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/f9f0/1af981f8d25f0c96ea06d88be62dabb79256.pdf"}, {"id": "09066d7d0bb6273bf996c8538d7b34c38ea6a500", "title": "Yes, IoU loss is submodular - as a function of the mispredictions", "addresses": [{"address": "Yonsei University", "lat": "37.56004060", "lng": "126.93692480", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1809.01845.pdf"}, {"id": "4aeebd1c9b4b936ed2e4d988d8d28e27f129e6f1", "title": "See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Chiu_See_the_Difference_ICCV_2015_paper.pdf"}, {"id": "232ff2dab49cb5a1dae1012fd7ba53382909ec18", "title": "Semantic Video Segmentation from Occlusion Relations within a Convex Optimization Framework", "addresses": [{"address": "University of California, Los Angeles", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/232f/f2dab49cb5a1dae1012fd7ba53382909ec18.pdf"}, {"id": "465c34c3334f29de28f973b7702a235509649429", "title": "Stereopsis via deep learning", "addresses": [{"address": "University of Frankfurt", "lat": "50.13053055", "lng": "8.69234224", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/465c/34c3334f29de28f973b7702a235509649429.pdf"}, {"id": "caa2ded6d8d5de97c824d29b0c7a18d220c596c8", "title": "Learning to Segment Breast Biopsy Whole Slide Images", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}, {"address": "University of Vermont", "lat": "44.48116865", "lng": "-73.20021790", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1709.02554.pdf"}, {"id": "289d833a35c2156b7e332e67d1cb099fd0683025", "title": "HICO: A Benchmark for Recognizing Human-Object Interactions in Images", "addresses": [{"address": "University of Michigan", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Chao_HICO_A_Benchmark_ICCV_2015_paper.pdf"}, {"id": "0fbdd4b8eb9e4c4cfbe5b76ab29ab8b0219fbdc0", "title": "Constrained Convolutional Neural Networks for Weakly Supervised Segmentation", "addresses": [{"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": 2015, "pdf": "https://people.eecs.berkeley.edu/~pathak/papers/iccv15.pdf"}, {"id": "f94f79168c1cfaebb8eab5151e01d56478ab0b73", "title": "Optimizing Region Selection for Weakly Supervised Object Detection", "addresses": [{"address": "Beijing University of Posts and Telecommunications", "lat": "39.96014880", "lng": "116.35193921", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/f94f/79168c1cfaebb8eab5151e01d56478ab0b73.pdf"}, {"id": "6bb51f431f348b2b3e1db859827e80f97a576c30", "title": "Irregular Convolutional Neural Networks", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/6bb5/1f431f348b2b3e1db859827e80f97a576c30.pdf"}, {"id": "b78e611c32dc0daf762cfa93044558cdb545d857", "title": "Temporal Action Detection with Structured Segment Networks Supplementary Materials", "addresses": [{"address": "Chinese University of Hong Kong", "lat": "22.42031295", "lng": "114.20788644", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/b78e/611c32dc0daf762cfa93044558cdb545d857.pdf"}, {"id": "bc12715a1ddf1a540dab06bf3ac4f3a32a26b135", "title": "Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking", "addresses": [{"address": "Technical University Munich", "lat": "48.14955455", "lng": "11.56775314", "type": "edu"}, {"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/bc12/715a1ddf1a540dab06bf3ac4f3a32a26b135.pdf"}, {"id": "4d1757aacbc49c74a5d4e53259c92ab0e47544da", "title": "Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer", "addresses": [{"address": "Shanghai Jiao Tong University", "lat": "31.20081505", "lng": "121.42840681", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.04310.pdf"}, {"id": "d392098688a999c70589c995bd4427c212eff69d", "title": "Object Repositioning Based on the Perspective in a Single Image", "addresses": [{"address": "University of Tsukuba", "lat": "36.11120580", "lng": "140.10551760", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/d392/098688a999c70589c995bd4427c212eff69d.pdf"}, {"id": "1c1f21bf136fe2eec412e5f70fd918c27c5ccb0a", "title": "Object Detection and Viewpoint Estimation with Auto-masking Neural Network", "addresses": [{"address": "Chinese University of Hong Kong", "lat": "22.42031295", "lng": "114.20788644", "type": "edu"}, {"address": "Shenzhen Institutes of Advanced Technology", "lat": "22.59805605", "lng": "113.98533784", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/1c1f/21bf136fe2eec412e5f70fd918c27c5ccb0a.pdf"}, {"id": "72e9acdd64e71fc2084acaf177aafaa2e075bd8c", "title": "The 2017 Hands in the Million Challenge on 3D Hand Pose Estimation", "addresses": [{"address": "Imperial College London", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/72e9/acdd64e71fc2084acaf177aafaa2e075bd8c.pdf"}, {"id": "0209389b8369aaa2a08830ac3b2036d4901ba1f1", "title": "DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild", "addresses": [{"address": "Imperial College London", "lat": "51.49887085", "lng": "-0.17560797", "type": "edu"}, {"address": "University College London", "lat": "51.52316070", "lng": "-0.12820370", "type": "edu"}], "year": 2017, "pdf": "https://arxiv.org/pdf/1612.01202v2.pdf"}, {"id": "07b8a9a225b738c4074a50cf80ee5fe516878421", "title": "Convolutional Simplex Projection Network for Weakly Supervised Semantic Segmentation", "addresses": [{"address": "University of Bonn", "lat": "50.73381240", "lng": "7.10224650", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.09169.pdf"}, {"id": "1bd1645a629f1b612960ab9bba276afd4cf7c666", "title": "End-to-End People Detection in Crowded Scenes", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}, {"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1506.04878.pdf"}, {"id": "1bbe0371ca22c2fdb6e0d098049bbf6430324bdb", "title": "Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval", "addresses": [{"address": "University of Florence", "lat": "43.77764260", "lng": "11.25976500", "type": "edu"}, {"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2016, "pdf": "http://doi.acm.org/10.1145/2906152"}, {"id": "9954f7ee5288724184f9420e39cca9165efa6822", "title": "Estimation of object functions using deformable part model", "addresses": [{"address": "Kobe University", "lat": "34.72757140", "lng": "135.23710000", "type": "edu"}], "year": 2015, "pdf": "http://www.me.cs.scitec.kobe-u.ac.jp/~takigu/pdf/2015/Th5_4.pdf"}, {"id": "e212b2bc41645fe467a73d004067fcf1ca77d87f", "title": "Deep Active Contours", "addresses": [{"address": "Technical University Munich", "lat": "48.14955455", "lng": "11.56775314", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/e212/b2bc41645fe467a73d004067fcf1ca77d87f.pdf"}, {"id": "51c4ecf4539f56c4b1035b890f743b3a91dd758b", "title": "Situational object boundary detection", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": 2015, "pdf": "http://arxiv.org/abs/1504.06434"}, {"id": "007e86cb55f0ba0415a7764a1e9f9566c1e8784b", "title": "Adversarial Feature Learning", "addresses": [{"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/2677/3023b17ba560bad6a679930710a9049abca5.pdf"}, {"id": "54d97ea9a5f92761dddd148fb0e602c2293e7c16", "title": "Associating Inter-image Salient Instances for Weakly Supervised Semantic Segmentation", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}, {"address": "Cardiff University", "lat": "51.48799610", "lng": "-3.17969747", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/54d9/7ea9a5f92761dddd148fb0e602c2293e7c16.pdf"}, {"id": "0e923b74fd41f73f57e22f66397feeea67e834f0", "title": "Invariant encoding schemes for visual recognition", "addresses": [{"address": "University College London", "lat": "51.52316070", "lng": "-0.12820370", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/0e92/3b74fd41f73f57e22f66397feeea67e834f0.pdf"}, {"id": "93cba94ff0ff96f865ce24ea01e9c006369d75ff", "title": "Knowledge Aided Consistency for Weakly Supervised Phrase Grounding", "addresses": [{"address": "University of Southern California", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1803.03879.pdf"}, {"id": "24fc311970e097efc317c0f98d2df37b828bfbad", "title": "Semi-supervised hierarchical semantic object parsing", "addresses": [{"address": "Amirkabir University of Technology", "lat": "35.70451400", "lng": "51.40972058", "type": "edu"}], "year": 2017, "pdf": "https://arxiv.org/pdf/1709.08019v2.pdf"}, {"id": "5c4d4fd37e8c80ae95c00973531f34a6d810ea3a", "title": "The Open World of Micro-Videos", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1603.09439.pdf"}, {"id": "71b973c87965e4086e75fd2379dd1bd8e3f8231e", "title": "Progressive Attention Networks for Visual Attribute Prediction", "addresses": [{"address": "Seoul National University", "lat": "37.26728000", "lng": "126.98411510", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1606.02393.pdf"}, {"id": "20c02e98602f6adf1cebaba075d45cef50de089f", "title": "Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1808.07507.pdf"}, {"id": "c17ed26650a67e80151f5312fa15b5c423acc797", "title": "Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}, {"address": "Institute of Industrial Science", "lat": "36.05238585", "lng": "140.11852361", "type": "edu"}, {"address": "University of Tokyo", "lat": "35.90204480", "lng": "139.93622009", "type": "edu"}, {"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/c17e/d26650a67e80151f5312fa15b5c423acc797.pdf"}, {"id": "0ce08f1cc6684495d12c2da157a056c7b88ffcd9", "title": "Multi-Modality Feature Transform: An Interactive Image Segmentation Approach", "addresses": [{"address": "Alexandria University", "lat": "31.21051105", "lng": "29.91314562", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/0ce0/8f1cc6684495d12c2da157a056c7b88ffcd9.pdf"}, {"id": "567078a51ea63b70396dca5dabb50a10a736d991", "title": "Conditional Generative Adversarial Network for Structured Domain Adaptation", "addresses": [{"address": "Nanyang Technological University", "lat": "1.34841040", "lng": "103.68297965", "type": "edu"}, {"address": "University at Buffalo", "lat": "43.00080930", "lng": "-78.78896970", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/1b5a/3bdb174df1ff36c1c101739d6daaec07760d.pdf"}, {"id": "6e4e5ef25f657de8fb383c8dfeb8e229eea28bb9", "title": "RON: Reverse Connection with Objectness Prior Networks for Object Detection", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1707.01691.pdf"}, {"id": "cf528f9fe6588b71efa94c219979ce111fc9c1c9", "title": "On Evaluation of 6D Object Pose Estimation", "addresses": [{"address": "Czech Technical University", "lat": "50.07642960", "lng": "14.41802312", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/cf52/8f9fe6588b71efa94c219979ce111fc9c1c9.pdf"}, {"id": "3b67645cd512898806aaf1df1811035f2d957f6b", "title": "SCNet: Learning Semantic Correspondence", "addresses": [{"address": "University of Hong Kong", "lat": "22.20814690", "lng": "114.25964115", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1705.04043.pdf"}, {"id": "ef2e36daf429899bb48d80ce6804731c3f99bb85", "title": "Debnath, Banerjee, Namboodiri: Adapting Ransac-svm to Detect Outliers for Robust Classification", "addresses": [{"address": "Indian Institute of Technology Kanpur", "lat": "26.51318800", "lng": "80.23651945", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/f7bd/b4df0fb5b3ff9fa0ebfe7c2a9ddc34c09a5c.pdf"}, {"id": "79a3a07661b8c6a36070fd767344e15c847a30ef", "title": "Contextual Pooling in Image Classification", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/79a3/a07661b8c6a36070fd767344e15c847a30ef.pdf"}, {"id": "5aa7f33cdc00787284b609aa63f5eb5c0a3212f6", "title": "Multiplicative mixing of object identity and image attributes in single inferior temporal neurons", "addresses": [{"address": "Indian Institute of Science Bangalore", "lat": "13.02223470", "lng": "77.56718325", "type": "edu"}], "year": 2018, "pdf": "http://pdfs.semanticscholar.org/5aa7/f33cdc00787284b609aa63f5eb5c0a3212f6.pdf"}, {"id": "38f88655debf4bf32978a7b39fbd56aea6ee5752", "title": "Class Rectification Hard Mining for Imbalanced Deep Learning", "addresses": [{"address": "Queen Mary University of London", "lat": "51.52472720", "lng": "-0.03931035", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1712.03162.pdf"}, {"id": "7b3b2912c1d7a70839bc71a150e33f8634d0fff3", "title": "Convolutional Neural Network-Based Embarrassing Situation Detection under Camera for Social Robot in Smart Homes", "addresses": [{"address": "Oklahoma State University", "lat": "36.12447560", "lng": "-97.05004383", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/7b3b/2912c1d7a70839bc71a150e33f8634d0fff3.pdf"}, {"id": "acdc333f7b32d987e65ce15f21db64e850ca9471", "title": "Direct Loss Minimization for Training Deep Neural Nets", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}, {"address": "University of Toronto", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/acdc/333f7b32d987e65ce15f21db64e850ca9471.pdf"}, {"id": "da4137396f26bf3e76d04eeed0c94e11b7824aa6", "title": "Transferable Semi-Supervised Semantic Segmentation", "addresses": [{"address": "National University of Defense Technology, China", "lat": "28.22902090", "lng": "112.99483204", "type": "edu"}, {"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}, {"address": "Beckman Institute", "lat": "40.11571585", "lng": "-88.22750772", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1711.06828.pdf"}, {"id": "5240941af3b263609acaa168f96e1decdb0b3fe4", "title": "Action classification in still images using human eye movements", "addresses": [{"address": "Stony Brook University", "lat": "40.91531960", "lng": "-73.12706260", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_workshops_2015/W06/papers/Ge_Action_Classification_in_2015_CVPR_paper.pdf"}, {"id": "126250d6077a6a68ae06277352eb42c4fa4c8b10", "title": "Learning Patch-based Structural Element Models with Hierarchical Palettes Abstract Learning Patch-based Structural Element Models with Hierarchical Palettes", "addresses": [{"address": "University of Toronto", "lat": "43.66333345", "lng": "-79.39769975", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/1262/50d6077a6a68ae06277352eb42c4fa4c8b10.pdf"}, {"id": "0cbbbfac2fe925479c6b34712e056f840a10fa4d", "title": "Quality Evaluation Methods for Crowdsourced Image Segmentation", "addresses": [{"address": "University of Illinois, Urbana-Champaign", "lat": "40.11116745", "lng": "-88.22587665", "type": "edu"}, {"address": "Facebook", "lat": "37.39367170", "lng": "-122.08072620", "type": "company"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/0cbb/bfac2fe925479c6b34712e056f840a10fa4d.pdf"}, {"id": "28df3f11894ce0c48dd8aee65a6ec76d9009cbbd", "title": "Recurrent Flow-Guided Semantic Forecasting", "addresses": [{"address": "Michigan State University", "lat": "42.71856800", "lng": "-84.47791571", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1809.08318.pdf"}, {"id": "535ed3850e79ccd51922601546ef0fc48c5fb468", "title": "A feature embedding strategy for high-level CNN representations from multiple convnets", "addresses": [{"address": "University of Windsor", "lat": "42.30791465", "lng": "-83.07176915", "type": "edu"}, {"address": "Zhejiang University", "lat": "30.19331415", "lng": "120.11930822", "type": "edu"}], "year": 2017, "pdf": "http://arxiv.org/abs/1705.04301"}, {"id": "247ca98c5a46616044cf6ae32b0d5b4140a7a161", "title": "High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/247c/a98c5a46616044cf6ae32b0d5b4140a7a161.pdf"}, {"id": "5f771fed91c8e4b666489ba2384d0705bcf75030", "title": "Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing", "addresses": [{"address": "National University of Defense Technology, China", "lat": "28.22902090", "lng": "112.99483204", "type": "edu"}, {"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1804.03287.pdf"}, {"id": "d115c4a66d765fef596b0b171febca334cea15b5", "title": "Combining Stacked Denoising Autoencoders and Random Forests for Face Detection", "addresses": [{"address": "Swansea University", "lat": "51.60915780", "lng": "-3.97934429", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d115/c4a66d765fef596b0b171febca334cea15b5.pdf"}, {"id": "e20ab84ac7fa0a5d36d4cf2266b7065c60e1c804", "title": "Stacked U-Nets for Ground Material Segmentation in Remote Sensing Imagery", "addresses": [{"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": "", "pdf": "https://pdfs.semanticscholar.org/e20a/b84ac7fa0a5d36d4cf2266b7065c60e1c804.pdf"}, {"id": "a1fdf45e6649b0020eb533c70d6062b9183561ff", "title": "Where's YOUR focus: Personalized Attention", "addresses": [{"address": "Hong Kong University of Science and Technology", "lat": "22.33863040", "lng": "114.26203370", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1802.07931.pdf"}, {"id": "775c51b965e8ff37646a265aab64136b4a620526", "title": "Three viewpoints toward exemplar SVM", "addresses": [{"address": "National Institute of Advanced Industrial Science and Technology", "lat": "36.05238585", "lng": "140.11852361", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2A_059_ext.pdf"}, {"id": "0688c0568f3ab418719260d443cc0d86c3af2914", "title": "Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes", "addresses": [{"address": "University of Central Florida", "lat": "28.59899755", "lng": "-81.19712501", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1707.09465.pdf"}, {"id": "5d92531e74c4c2cdce91fdcd3c7ff090c8c29504", "title": "Synthesizing Scenes for Instance Detection", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/5d92/531e74c4c2cdce91fdcd3c7ff090c8c29504.pdf"}, {"id": "c919a9f61656cdcd3a26076057ee006c48e8f609", "title": "High-Value Target Detection", "addresses": [{"address": "University of Tartu", "lat": "58.38131405", "lng": "26.72078081", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/c919/a9f61656cdcd3a26076057ee006c48e8f609.pdf"}, {"id": "c6ce8eb37dafed09e1c55735fd1f1e9dc9c6bfe2", "title": "Joint background reconstruction and foreground segmentation via a two-stage convolutional neural network", "addresses": [{"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}, {"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1707.07584.pdf"}, {"id": "c0006a2268d299644e9f1b455601bcbe89ddc2b5", "title": "Semantic Video Segmentation by Gated Recurrent Flow Propagation", "addresses": [{"address": "Lund University", "lat": "55.70395710", "lng": "13.19020110", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1612.08871.pdf"}, {"id": "273b9b7c63ac9196fb12734b49b74d0523ca4df4", "title": "The Secrets of Salient Object Segmentation", "addresses": [{"address": "California Institute of Technology", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu"}, {"address": "University of California, Los Angeles", "lat": "34.06877880", "lng": "-118.44500940", "type": "edu"}], "year": 2014, "pdf": "https://arxiv.org/pdf/1406.2807v2.pdf"}, {"id": "e771661fa441f008c111ea786eb275153919da6e", "title": "Globally Optimal Object Tracking with Fully Convolutional Networks", "addresses": [{"address": "Kyushu University", "lat": "33.59914655", "lng": "130.22359848", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/e771/661fa441f008c111ea786eb275153919da6e.pdf"}, {"id": "5feacd9dd73827fb438a6bf6c8b406f4f11aa2fa", "title": "Slanted Stixels: Representing San Francisco's Steepest Streets", "addresses": [{"address": "Universitat Aut\u00f2noma de Barcelona", "lat": "41.50078110", "lng": "2.11143663", "type": "edu"}, {"address": "ETH Z\u00fcrich", "lat": "47.37645340", "lng": "8.54770931", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/5fea/cd9dd73827fb438a6bf6c8b406f4f11aa2fa.pdf"}]}
\ No newline at end of file +{"id": "0ee1916a0cb2dc7d3add086b5f1092c3d4beb38a", "paper": {"paper_id": "0ee1916a0cb2dc7d3add086b5f1092c3d4beb38a", "key": "voc", "title": "The Pascal Visual Object Classes (VOC) Challenge", "year": 2009, "pdf": "https://doi.org/10.1007/s11263-009-0275-4", "address": "", "name": "VOC"}, "address": null, "additional_papers": [], "citations": [{"id": "9f4078773c8ea3f37951bf617dbce1d4b3795839", "title": "Leveraging Inexpensive Supervision Signals for Visual Learning", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/9f40/78773c8ea3f37951bf617dbce1d4b3795839.pdf"}, {"id": "0e2af97f07625cb3cf5e30f1c9d807124cbbc850", "title": "From Large Scale Image Categorization to Entry-Level Categories", "addresses": [{"address": "University of North Carolina at Chapel Hill", "lat": "35.91139710", "lng": "-79.05045290", "type": "edu"}], "year": 2013, "pdf": "http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Ordonez_From_Large_Scale_2013_ICCV_paper.pdf"}, {"id": "131e9edbe4b0322a467b7e8c35f6b0c0ca750e21", "title": "Contextual Action Recognition with R*CNN", "addresses": [{"address": "Microsoft", "lat": "47.64233180", "lng": "-122.13693020", "type": "company"}], "year": 2015, "pdf": "http://openaccess.thecvf.com/content_iccv_2015/papers/Gkioxari_Contextual_Action_Recognition_ICCV_2015_paper.pdf"}, {"id": "396aacab076a3607429f58ce442d5d57b5aaa794", "title": "Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer", "addresses": [{"address": "University of Washington", "lat": "47.65432380", "lng": "-122.30800894", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1511.03240v2.pdf"}, {"id": "ef8de1bd92e9ee9d0d2dee73095d4d348dc54a98", "title": "Fine-grained Activity Recognition with Holistic and Pose based Features", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}, {"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2014", "pdf": "https://arxiv.org/pdf/1406.1881.pdf"}, {"id": "86c158ef6caaf247d5d14e07c5edded0147df8b7", "title": "Spatial Memory for Context Reasoning in Object Detection", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.04224.pdf"}, {"id": "18fe63c013983bea53be7d559ef36a1f385ca6ea", "title": "Supervision Beyond Human Annotations for Learning Visual Representations", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/18fe/63c013983bea53be7d559ef36a1f385ca6ea.pdf"}, {"id": "663cca096b98c8f0444608b188e464028ee34368", "title": "CASENet: Deep Category-Aware Semantic Edge Detection", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1705.09759.pdf"}, {"id": "f9d171019bfeb71733fe36f7fae14f342ca9e51c", "title": "Hough Forests Revisited: An Approach to Multiple Instance Tracking from Multiple Cameras", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/f9d1/71019bfeb71733fe36f7fae14f342ca9e51c.pdf"}, {"id": "f832fdf1fac092b4140bf81d38e6bc6af5c1ea65", "title": "Instance-Level Human Parsing via Part Grouping Network", "addresses": [{"address": "Sun Yat-Sen University", "lat": "23.09461185", "lng": "113.28788994", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1808.00157.pdf"}, {"id": "41be021880a916305c82199ddc2298eb271f6590", "title": "Benchmarks for Image Classification and Other High-dimensional Pattern Recognition Problems", "addresses": [{"address": "Purdue University", "lat": "40.43197220", "lng": "-86.92389368", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1806.05272.pdf"}, {"id": "fdcc1e66697a724bd2d0d2da368de04a7eaf9209", "title": "The Devil is in the Decoder", "addresses": [{"address": "University College London", "lat": "51.52316070", "lng": "-0.12820370", "type": "edu"}, {"address": "Google", "lat": "37.42199990", "lng": "-122.08405750", "type": "company"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1707.05847.pdf"}, {"id": "6e7a9779dee831658e973ee26ac8bfed2d6da033", "title": "Human Pose Estimation for Multiple Frames", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/6e7a/9779dee831658e973ee26ac8bfed2d6da033.pdf"}, {"id": "29b3be93a60bbc5fe842826030853f99753b08bd", "title": "Hierarchical Scene Annotation", "addresses": [{"address": "California Institute of Technology", "lat": "34.13710185", "lng": "-118.12527487", "type": "edu"}], "year": "2013", "pdf": "https://pdfs.semanticscholar.org/6a94/c929f02e2ebd2477ca96d14334b311e9b829.pdf"}, {"id": "b88b83d2ffd30bf3bc3be3fb7492fd88f633b2fe", "title": "Subcategory-Aware Object Classification", "addresses": [{"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": 2013, "pdf": "http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989a827.pdf"}, {"id": "241b86d3c71d14b8cc6044a425b047a0724cfdc9", "title": "Following Gaze in Video", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2017, "pdf": "http://people.csail.mit.edu/recasens/docs/videogazefollow.pdf"}, {"id": "0d746111135c2e7f91443869003d05cde3044beb", "title": "Partial face detection for continuous authentication", "addresses": [{"address": "State University of New Jersey", "lat": "40.51865195", "lng": "-74.44099801", "type": "edu"}, {"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": 2016, "pdf": "https://doi.org/10.1109/ICIP.2016.7532908"}, {"id": "420c46d7cafcb841309f02ad04cf51cb1f190a48", "title": "Multi-Scale Context Aggregation by Dilated Convolutions", "addresses": [{"address": "Princeton University", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/b2a5/e98409c7a6a5e005348c023ccad23f5cb5a9.pdf"}, {"id": "076fd6fd85b93858155a1c775f1897f83d52b4c2", "title": "Improving an Object Detector and Extracting Regions Using Superpixels", "addresses": [{"address": "University of Central Florida", "lat": "28.59899755", "lng": "-81.19712501", "type": "edu"}], "year": 2013, "pdf": "http://www.crcv.ucf.edu/papers/cvpr2013/CVPR13_final_guang.pdf"}, {"id": "ccd3dcbccae7d903608530bddf6381db8e723a7d", "title": "Unsupervised Domain Adaptation for Semantic Segmentation with GANs", "addresses": [{"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}, {"address": "GE Global Research Center", "lat": "42.82982480", "lng": "-73.87719385", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/ccd3/dcbccae7d903608530bddf6381db8e723a7d.pdf"}, {"id": "b2cd92d930ed9b8d3f9dfcfff733f8384aa93de8", "title": "HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition", "addresses": [{"address": "University of Maryland College Park", "lat": "38.99203005", "lng": "-76.94610290", "type": "edu"}, {"address": "University of Maryland", "lat": "39.28996850", "lng": "-76.62196103", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/b2cd/92d930ed9b8d3f9dfcfff733f8384aa93de8.pdf"}, {"id": "08eaa845a72a2b78e08e58592d8785942fced649", "title": "What's in a Question: Using Visual Questions as a Form of Supervision", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2017, "pdf": "http://arxiv.org/abs/1704.03895"}, {"id": "d0ac9913a3b1784f94446db2f1fb4cf3afda151f", "title": "Exploiting Multi-modal Curriculum in Noisy Web Data for Large-scale Concept Learning", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d0ac/9913a3b1784f94446db2f1fb4cf3afda151f.pdf"}, {"id": "3a3a4408432408b62e2dc22de7820a5a2f7bbe9e", "title": "No Spare Parts: Sharing Part Detectors for Image Categorization", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}, {"address": "Delft University of Technology", "lat": "51.99882735", "lng": "4.37396037", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1510.04908.pdf"}, {"id": "d4f1eb008eb80595bcfdac368e23ae9754e1e745", "title": "Unconstrained Face Detection and Open-Set Face Recognition Challenge", "addresses": [{"address": "University of Colorado, Colorado Springs", "lat": "38.89207560", "lng": "-104.79716389", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.02337.pdf"}, {"id": "33ba256d59aefe27735a30b51caf0554e5e3a1df", "title": "Early Active Learning via Robust Representation and Structured Sparsity", "addresses": [{"address": "University of Texas at Arlington", "lat": "32.72836830", "lng": "-97.11201835", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/33ba/256d59aefe27735a30b51caf0554e5e3a1df.pdf"}, {"id": "b7407b2ea67b8c82246f013f4966c4cac1507e60", "title": "Object Detection via End-to-End Integration of Aspect Ratio and Context Aware Part-based Models and Fully Convolutional Networks", "addresses": [{"address": "Jilin University", "lat": "22.05356500", "lng": "113.39913285", "type": "edu"}, {"address": "North Carolina State University", "lat": "35.77184965", "lng": "-78.67408695", "type": "edu"}], "year": "2016", "pdf": "https://pdfs.semanticscholar.org/b740/7b2ea67b8c82246f013f4966c4cac1507e60.pdf"}, {"id": "3af130e2fd41143d5fc49503830bbd7bafd01f8b", "title": "How Do We Evaluate the Quality of Computational Editing Systems?", "addresses": [{"address": "University of Wisconsin Madison", "lat": "43.07982815", "lng": "-89.43066425", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/db76/002794c12e5febc30510de58b54bb9344ea9.pdf"}, {"id": "732e4016225280b485c557a119ec50cffb8fee98", "title": "Are all training examples equally valuable?", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/732e/4016225280b485c557a119ec50cffb8fee98.pdf"}, {"id": "6341274aca0c2977c3e1575378f4f2126aa9b050", "title": "A multi-scale cascade fully convolutional network face detector", "addresses": [{"address": "University of Southern California", "lat": "34.02241490", "lng": "-118.28634407", "type": "edu"}], "year": 2016, "pdf": "http://arxiv.org/pdf/1609.03536v1.pdf"}, {"id": "9bd9050c53d90dfa86cb22501812afe6fc897406", "title": "Fine-Grained and Layered Object Recognition", "addresses": [{"address": "Xi'an Jiaotong University", "lat": "34.24749490", "lng": "108.97898751", "type": "edu"}, {"address": "Kyoto University", "lat": "35.02749960", "lng": "135.78154513", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/9bd9/050c53d90dfa86cb22501812afe6fc897406.pdf"}, {"id": "3e0a1884448bfd7f416c6a45dfcdfc9f2e617268", "title": "Understanding and Controlling User Linkability in Decentralized Learning", "addresses": [{"address": "Max Planck Institute for Informatics", "lat": "49.25795660", "lng": "7.04577417", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1805.05838.pdf"}, {"id": "108961c7366e36825ffed94ac9eab603e05b6bc6", "title": "Deep Visual-Semantic Alignments for Generating Image Descriptions", "addresses": [{"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": 2015, "pdf": "http://arxiv.org/abs/1412.2306"}, {"id": "282cee05661a690aa525f21b47c6ee39fb26a7c2", "title": "Build a Robust Learning Feature Descriptor by Using a New Image Visualization Method for Indoor Scenario Recognition", "addresses": [{"address": "Beijing University of Posts and Telecommunications", "lat": "39.96014880", "lng": "116.35193921", "type": "edu"}], "year": 2017, "pdf": "http://pdfs.semanticscholar.org/282c/ee05661a690aa525f21b47c6ee39fb26a7c2.pdf"}, {"id": "121503705689f46546cade78ff62963574b4750b", "title": "We Don\u2019t Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1602.08405.pdf"}, {"id": "df0e280cae018cebd5b16ad701ad101265c369fa", "title": "Deep Attributes from Context-Aware Regional Neural Codes", "addresses": [{"address": "Columbia University", "lat": "40.84198360", "lng": "-73.94368971", "type": "edu"}, {"address": "Beihang University", "lat": "39.98083330", "lng": "116.34101249", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/df0e/280cae018cebd5b16ad701ad101265c369fa.pdf"}, {"id": "30654fd93360a339e271d4b194b7f7463b2c5dac", "title": "COSTA: Co-Occurrence Statistics for Zero-Shot Classification", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2014, "pdf": "https://ivi.fnwi.uva.nl/isis/publications/2014/MensinkCVPR2014/MensinkCVPR2014.pdf"}, {"id": "02ae77f4c289426f18e83ce6e295d39538fb0fcc", "title": "Dependency Modeling for Information Fusion with Applications in Visual Recognition", "addresses": [{"address": "Hong Kong Baptist University", "lat": "22.38742010", "lng": "114.20822220", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/02ae/77f4c289426f18e83ce6e295d39538fb0fcc.pdf"}, {"id": "23a84a4a77b6662d553c9252331e6b7920053125", "title": "Latent Model Ensemble with Auto-localization", "addresses": [{"address": "Electrical and Computer Engineering", "lat": "33.58667840", "lng": "-101.87539204", "type": "edu"}, {"address": "University of Missouri", "lat": "38.92676100", "lng": "-92.29193783", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/ad28/34a42fccfe965f2039591e2ac26453273405.pdf"}, {"id": "b7c5f885114186284c51e863b58292583047a8b4", "title": "GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms", "addresses": [{"address": "American University in Cairo", "lat": "30.04287695", "lng": "31.23664139", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/b7c5/f885114186284c51e863b58292583047a8b4.pdf"}, {"id": "009678c2034cf4a9924a78d533d2ec81303a946e", "title": "Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.10437.pdf"}, {"id": "0ae80aa149764e91544bbe45b80bb50434e7bda9", "title": "Ambient Sound Provides Supervision for Visual Learning", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/714c/21c575d2c02a51f2dd5250164f1269be44ca.pdf"}, {"id": "16161051ee13dd3d836a39a280df822bf6442c84", "title": "Learning Efficient Object Detection Models with Knowledge Distillation", "addresses": [{"address": "University of California, San Diego", "lat": "32.87935255", "lng": "-117.23110049", "type": "edu"}, {"address": "University of Missouri", "lat": "38.92676100", "lng": "-92.29193783", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/4bd3/f187f3e09483b1f0f92150a4a77409691b0f.pdf"}, {"id": "d6b1b0e60e1764982ef95d4ade8fcaa10bfb156a", "title": "A Sketch-based Approach for Multimedia Retrieval", "addresses": [{"address": "International Institute of Information Technology", "lat": "17.44549570", "lng": "78.34854698", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/d6b1/b0e60e1764982ef95d4ade8fcaa10bfb156a.pdf"}, {"id": "079e20d0d870a5bade46cc9b4338a3d637399654", "title": "Semantic Segmentation , Urban Navigation , and Research Directions", "addresses": [{"address": "Princeton University", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/079e/20d0d870a5bade46cc9b4338a3d637399654.pdf"}, {"id": "9035e87ce49b67b751838c7346d36fe481260217", "title": "An Introduction to Random Forests for Multi-class Object Detection", "addresses": [{"address": "Katholieke Universiteit Leuven", "lat": "50.88306860", "lng": "4.70195030", "type": "edu"}], "year": 2011, "pdf": "http://pdfs.semanticscholar.org/9035/e87ce49b67b751838c7346d36fe481260217.pdf"}, {"id": "24065d385bae5579be07607a1f63eb79cebf8773", "title": "Incremental Learning of NCM Forests for Large-Scale Image Classification", "addresses": [{"address": "University of Bonn", "lat": "50.73381240", "lng": "7.10224650", "type": "edu"}], "year": 2014, "pdf": "http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.467"}, {"id": "7fbf1885f27fb72d5e553c4a2147375f928465ee", "title": "Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade", "addresses": [{"address": "Chinese University of Hong Kong", "lat": "22.42031295", "lng": "114.20788644", "type": "edu"}, {"address": "Shenzhen Institutes of Advanced Technology", "lat": "22.59805605", "lng": "113.98533784", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.01344.pdf"}, {"id": "a89e1fc2681a9a399cc5008ea34b5ec3fe7ca845", "title": "Improving Fast Segmentation With Teacher-Student Learning", "addresses": [{"address": "Sun Yat-Sen University", "lat": "23.09461185", "lng": "113.28788994", "type": "edu"}, {"address": "Nanyang Technological University", "lat": "1.34841040", "lng": "103.68297965", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1810.08476.pdf"}, {"id": "3434ba5677e5c98e82ee17a1f2d0ddef66d0b009", "title": "Interactive tracking and action retrieval to support human behavior analysis", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/3434/ba5677e5c98e82ee17a1f2d0ddef66d0b009.pdf"}, {"id": "3676c29babe1563ee64a1149d2ae2f9f1369fe25", "title": "Visual saliency computation for image analysis", "addresses": [{"address": "Boston University", "lat": "42.35042530", "lng": "-71.10056114", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/3676/c29babe1563ee64a1149d2ae2f9f1369fe25.pdf"}, {"id": "a60540a8407fd117fd8e6857d4728e661f53dcc8", "title": "Deep Domain Generalization via Conditional Invariant Adversarial Networks", "addresses": [{"address": "University of Science and Technology of China", "lat": "31.83907195", "lng": "117.26420748", "type": "edu"}, {"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "University of Pittsburgh", "lat": "40.44415295", "lng": "-79.96243993", "type": "edu"}, {"address": "University of Sydney", "lat": "-33.88890695", "lng": "151.18943366", "type": "edu"}], "year": "2018", "pdf": "https://pdfs.semanticscholar.org/a605/40a8407fd117fd8e6857d4728e661f53dcc8.pdf"}, {"id": "4aa286914f17cd8cefa0320e41800a99c142a1cd", "title": "Leveraging Context to Support Automated Food Recognition in Restaurants", "addresses": [{"address": "Georgia Institute of Technology", "lat": "33.77603300", "lng": "-84.39884086", "type": "edu"}], "year": 2015, "pdf": "http://www.vbettadapura.com/egocentric/food/Food-Bettadapura15.pdf"}, {"id": "4ab10174a4f98f7e2da7cf6ccfeb9bc64c8e7da8", "title": "Efficient Metric Learning for Real-World Face Recognition", "addresses": [{"address": "Graz University of Technology", "lat": "47.05821000", "lng": "15.46019568", "type": "edu"}], "year": 2013, "pdf": "http://pdfs.semanticscholar.org/4ab1/0174a4f98f7e2da7cf6ccfeb9bc64c8e7da8.pdf"}, {"id": "e64fa00da02cc774559db5be88bc2862afbfd432", "title": "Histogram of Oriented Normal Vectors for Object Recognition with a Depth Sensor", "addresses": [{"address": "University of Missouri", "lat": "38.92676100", "lng": "-92.29193783", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/e64f/a00da02cc774559db5be88bc2862afbfd432.pdf"}, {"id": "0f0a5d8a7a087204026a6b67000887dbf5b6a20f", "title": "Generating objects going well with the surroundings", "addresses": [{"address": "Seoul National University", "lat": "37.26728000", "lng": "126.98411510", "type": "edu"}], "year": "2018", "pdf": "https://arxiv.org/pdf/1807.02925.pdf"}, {"id": "14a3194bb454f1f2e3fc1452045ac18c69959368", "title": "Fast Object Detection Using Multistage Particle Window Deformable Part Model", "addresses": [{"address": "National Chung Cheng University", "lat": "23.56306355", "lng": "120.47510531", "type": "edu"}], "year": 2014, "pdf": "http://www.cs.ccu.edu.tw/~wtchu/papers/2014ISM-chu.pdf"}, {"id": "187480101af3fb195993da1e2c17d917df24eb23", "title": "Unsupervised Visual Representation Learning by Context Prediction", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}, {"address": "University of California, Berkeley", "lat": "37.86871260", "lng": "-122.25586815", "type": "edu"}], "year": 2015, "pdf": "http://arxiv.org/pdf/1505.05192v2.pdf"}, {"id": "3b5787604b619c273bf98232b0bd3bce5d4a34ee", "title": "Learning Discriminative Hidden Structural Parts for Visual Tracking", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}, {"address": "University of Chinese Academy of Sciences", "lat": "39.90828040", "lng": "116.24585270", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/3b57/87604b619c273bf98232b0bd3bce5d4a34ee.pdf"}, {"id": "95f4b88d4b0a725d786b34558b60af47f5442230", "title": "Reconfigurable Processor for Deep Learning in Autonomous Vehicles", "addresses": [{"address": "Tsinghua University", "lat": "40.00229045", "lng": "116.32098908", "type": "edu"}, {"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/381e/7525bc8b9d47ae0343e471f5f1d5e6963bbe.pdf"}, {"id": "205e895e03969c96f3c482b0bd26308b16a12bd0", "title": "Image Captioning with an Intermediate Attributes Layer", "addresses": [{"address": "University of Adelaide", "lat": "-34.91892260", "lng": "138.60423668", "type": "edu"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/205e/895e03969c96f3c482b0bd26308b16a12bd0.pdf"}, {"id": "6bb19408458dbae075be7f1612b969b565b4767a", "title": "Approximate Log-Hilbert-Schmidt Distances between Covariance Operators for Image Classification", "addresses": [{"address": "Dartmouth College", "lat": "43.70479270", "lng": "-72.29259090", "type": "edu"}], "year": 2016, "pdf": "http://openaccess.thecvf.com/content_cvpr_2016/papers/Minh_Approximate_Log-Hilbert-Schmidt_Distances_CVPR_2016_paper.pdf"}, {"id": "719969807953d7ea8bda0397b1aadbaa6e205718", "title": "Automatic Dataset Augmentation", "addresses": [{"address": "Harbin Institute of Technology", "lat": "45.74139210", "lng": "126.62552755", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1708.08201.pdf"}, {"id": "bfea962697e9b445b89a865b465ae967dd55b4fe", "title": "Efficient object detection via structured learning and local classifiers", "addresses": [{"address": "Oxford Brookes University", "lat": "51.75552050", "lng": "-1.22615970", "type": "edu"}], "year": "2013", "pdf": "https://pdfs.semanticscholar.org/bfea/962697e9b445b89a865b465ae967dd55b4fe.pdf"}, {"id": "20b038c50cc7148dfb364e2de51cde120c907c9f", "title": "Integrated perception with recurrent multi-task neural networks", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1606.01735.pdf"}, {"id": "0faeec0d1c51623a511adb779dabb1e721a6309b", "title": "Seeing is Worse than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions", "addresses": [{"address": "National University of Ireland Maynooth", "lat": "53.38469750", "lng": "-6.60039458", "type": "edu"}, {"address": "Princeton University", "lat": "40.34829285", "lng": "-74.66308325", "type": "edu"}, {"address": "Purdue University", "lat": "40.43197220", "lng": "-86.92389368", "type": "edu"}, {"address": "Rutgers University", "lat": "40.47913175", "lng": "-74.43168868", "type": "edu"}, {"address": "Stanford University", "lat": "37.43131385", "lng": "-122.16936535", "type": "edu"}, {"address": "University of Michigan", "lat": "42.29421420", "lng": "-83.71003894", "type": "edu"}, {"address": "University of Texas at Arlington", "lat": "32.72836830", "lng": "-97.11201835", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/a075/782ea38167658fe28986755adddba7369b4f.pdf"}, {"id": "fdfd57d4721174eba288e501c0c120ad076cdca8", "title": "An Analysis of Action Recognition Datasets for Language and Vision Tasks", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1704.07129.pdf"}, {"id": "a2af07176a38fe844b0e2fdf4abae65472628b38", "title": "Dog breed classification via landmarks", "addresses": [{"address": "University of Delaware", "lat": "39.68103280", "lng": "-75.75401840", "type": "edu"}], "year": 2014, "pdf": "https://doi.org/10.1109/ICIP.2014.7026060"}, {"id": "ef2e36daf429899bb48d80ce6804731c3f99bb85", "title": "Debnath, Banerjee, Namboodiri: Adapting Ransac-svm to Detect Outliers for Robust Classification", "addresses": [{"address": "Indian Institute of Technology Kanpur", "lat": "26.51318800", "lng": "80.23651945", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/f7bd/b4df0fb5b3ff9fa0ebfe7c2a9ddc34c09a5c.pdf"}, {"id": "9d422e2c318ab63e6b49c83053757b4636f8308b", "title": "Object localization in ImageNet by looking out of the window", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2015", "pdf": "https://arxiv.org/pdf/1501.01181.pdf"}, {"id": "71f36c8e17a5c080fab31fce1ffea9551fc49e47", "title": "Predicting Failures of Vision Systems", "addresses": [{"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": 2014, "pdf": "http://openaccess.thecvf.com/content_cvpr_2014/papers/Zhang_Predicting_Failures_of_2014_CVPR_paper.pdf"}, {"id": "7caa3a74313f9a7a2dd5b4c2cd7f825d895d3794", "title": "Markov Chain Monte Carlo for Automated Face Image Analysis", "addresses": [{"address": "University of Basel", "lat": "47.56126510", "lng": "7.57529610", "type": "edu"}], "year": "2016", "pdf": "http://doi.org/10.1007/s11263-016-0967-5"}, {"id": "26c58e24687ccbe9737e41837aab74e4a499d259", "title": "Codemaps - Segment, Classify and Search Objects Locally", "addresses": [{"address": "University of Amsterdam", "lat": "52.35536550", "lng": "4.95016440", "type": "edu"}], "year": 2013, "pdf": "http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Li_Codemaps_-_Segment_2013_ICCV_paper.pdf"}, {"id": "1f9102f425f28552e477cf71af0846550f3f9ed9", "title": "Incremental Domain Adaptation of Deformable Part-based Models", "addresses": [{"address": "Universitat Aut\u00f2noma de Barcelona", "lat": "41.50078110", "lng": "2.11143663", "type": "edu"}], "year": 2014, "pdf": "http://pdfs.semanticscholar.org/63ba/ef71a57d9ea6764c2bc3907cb6596b7f294a.pdf"}, {"id": "50953b9a15aca6ef3351e613e7215abdcae1435e", "title": "Learning coarse-to-fine sparselets for efficient object detection and scene classification", "addresses": [{"address": "Northwestern Polytechnical University", "lat": "34.24691520", "lng": "108.91061982", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2015/ext/1B_007_ext.pdf"}, {"id": "a63104ad235f98bc5ee0b44fefbcdb49e32c205a", "title": "Has My Algorithm Succeeded? An Evaluator for Human Pose Estimators", "addresses": [{"address": "University of Oxford", "lat": "51.75345380", "lng": "-1.25400997", "type": "edu"}, {"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/a631/04ad235f98bc5ee0b44fefbcdb49e32c205a.pdf"}, {"id": "f6e00d6430cbbaa64789d826d093f7f3e323b082", "title": "Visual Object Recognition", "addresses": [{"address": "RWTH Aachen University", "lat": "50.77917030", "lng": "6.06728733", "type": "edu"}, {"address": "University of Texas at Austin", "lat": "30.28415100", "lng": "-97.73195598", "type": "edu"}], "year": "2011", "pdf": "https://pdfs.semanticscholar.org/5255/490925aa1e01ac0b9a55e93ec8c82efc07b7.pdf"}, {"id": "ae5b2b449f59ae0f46f6a31ed4826d98241c394c", "title": "Accurate real-time people counting for crowded environments", "addresses": [{"address": "University of Florence", "lat": "43.77764260", "lng": "11.25976500", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/ae5b/2b449f59ae0f46f6a31ed4826d98241c394c.pdf"}, {"id": "0b9c5bfb4d8349bb3f6ddd6fb612b7f9657c93f8", "title": "Inverting and Visualizing Features for Object Detection", "addresses": [{"address": "MIT", "lat": "42.35839610", "lng": "-71.09567788", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/0b9c/5bfb4d8349bb3f6ddd6fb612b7f9657c93f8.pdf"}, {"id": "2cd7821fcf5fae53a185624f7eeda007434ae037", "title": "Exploring the geo-dependence of human face appearance", "addresses": [{"address": "University of Kentucky", "lat": "38.03337420", "lng": "-84.50177580", "type": "edu"}], "year": 2014, "pdf": "http://cs.uky.edu/~jacobs/papers/islam2014faces.pdf"}, {"id": "45e616093a92e5f1e61a7c6037d5f637aa8964af", "title": "Fine-grained evaluation on face detection in the wild", "addresses": [{"address": "Chinese Academy of Sciences", "lat": "40.00447950", "lng": "116.37023800", "type": "edu"}], "year": 2015, "pdf": "http://www.cs.toronto.edu/~byang/papers/malf_fg15.pdf"}, {"id": "81825711c2aaa1b9d3ead1a300e71c4353a41382", "title": "End-to-end training of object class detectors for mean average precision", "addresses": [{"address": "University of Edinburgh", "lat": "55.94951105", "lng": "-3.19534913", "type": "edu"}], "year": "2016", "pdf": "https://arxiv.org/pdf/1607.03476.pdf"}, {"id": "488fff23542ff397cdb1ced64db2c96320afc560", "title": "Weakly supervised localization of novel objects using appearance transfer", "addresses": [{"address": "University of Manitoba", "lat": "49.80915360", "lng": "-97.13304179", "type": "edu"}], "year": 2015, "pdf": "http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_106_ext.pdf"}, {"id": "02b1a5d4b113211198e9c66d51153eb63ca680e2", "title": "Scene Invariant Crowd Segmentation and Counting Using Scale-Normalized Histogram of Moving Gradients (HoMG)", "addresses": [{"address": "University of Waterloo", "lat": "43.47061295", "lng": "-80.54724732", "type": "edu"}], "year": 2016, "pdf": "http://pdfs.semanticscholar.org/02b1/a5d4b113211198e9c66d51153eb63ca680e2.pdf"}, {"id": "7d520f474f2fc59422d910b980f8485716ce0a3e", "title": "Designing Convolutional Neural Networks for Urban Scene Understanding", "addresses": [{"address": "Robotics Institute", "lat": "13.65450525", "lng": "100.49423171", "type": "edu"}, {"address": "Carnegie Mellon University", "lat": "37.41021930", "lng": "-122.05965487", "type": "edu"}], "year": "2017", "pdf": "https://pdfs.semanticscholar.org/2128/4a9310a4b4c836b8dfb6af39c682b7348128.pdf"}, {"id": "50f6888d9a7edb746e43a78c682a57c7ef36765b", "title": "Near-duplicate keyframe retrieval by semi-supervised learning and nonrigid image matching", "addresses": [{"address": "Zhejiang University", "lat": "30.19331415", "lng": "120.11930822", "type": "edu"}, {"address": "Nanyang Technological University", "lat": "1.34841040", "lng": "103.68297965", "type": "edu"}, {"address": "Chinese University of Hong Kong", "lat": "22.42031295", "lng": "114.20788644", "type": "edu"}, {"address": "National University of Singapore", "lat": "1.29620180", "lng": "103.77689944", "type": "edu"}], "year": 2011, "pdf": "http://www.cse.cuhk.edu.hk/lyu/_media/paper/jkzhu_comccap.pdf?cache=cache&id=publications:journal2"}, {"id": "72a4390a6c3b2bc2c3e7d83fc1f99e65e6137573", "title": "Collective Activity Localization with Contextual Spatial Pyramid", "addresses": [{"address": "University of Tokyo", "lat": "35.90204480", "lng": "139.93622009", "type": "edu"}], "year": 2012, "pdf": "http://pdfs.semanticscholar.org/72a4/390a6c3b2bc2c3e7d83fc1f99e65e6137573.pdf"}, {"id": "d012f6d7fd45051adaff8da4ce0860de9f81d445", "title": "A Deep Multi-task Learning Approach to Skin Lesion Classification", "addresses": [{"address": "University of Rochester", "lat": "43.15769690", "lng": "-77.58829158", "type": "edu"}], "year": "2017", "pdf": "https://arxiv.org/pdf/1812.03527.pdf"}, {"id": "f678f31e7bb5eda34098b0fed608cfad5e372509", "title": "Discriminative Kernel Feature Extraction and Learning for Object Recognition and Detection", "addresses": [{"address": "Southeast University", "lat": "32.05752790", "lng": "118.78682252", "type": "edu"}], "year": "2015", "pdf": "https://pdfs.semanticscholar.org/f678/f31e7bb5eda34098b0fed608cfad5e372509.pdf"}, {"id": "07ba3c796244f76b5e6914246fd83b66d3b65c34", "title": "Real-time Human Detection based on Personness Estimation", "addresses": [{"address": "Yonsei University", "lat": "37.56004060", "lng": "126.93692480", "type": "edu"}], "year": 2015, "pdf": "http://pdfs.semanticscholar.org/07ba/3c796244f76b5e6914246fd83b66d3b65c34.pdf"}, {"id": "fe5c43aa19da5cbbf5a42e4697659875f7389b91", "title": "Tracking People in Broadcast Sports", "addresses": [{"address": "ETH Z\u00fcrich", "lat": "47.37645340", "lng": "8.54770931", "type": "edu"}], "year": 2010, "pdf": "http://pdfs.semanticscholar.org/fe5c/43aa19da5cbbf5a42e4697659875f7389b91.pdf"}]}
\ No newline at end of file |