diff options
Diffstat (limited to 'site/datasets/final/voc.csv')
| -rw-r--r-- | site/datasets/final/voc.csv | 401 |
1 files changed, 0 insertions, 401 deletions
diff --git a/site/datasets/final/voc.csv b/site/datasets/final/voc.csv deleted file mode 100644 index 9400d7d6..00000000 --- a/site/datasets/final/voc.csv +++ /dev/null @@ -1,401 +0,0 @@ -index,dataset_name,key,lat,lng,loc,loc_type,paper_id,paper_type,paper_url,title,year -0,VOC,voc,0.0,0.0,,,abe9f3b91fd26fa1b50cd685c0d20debfb372f73,main,http://homepages.inf.ed.ac.uk/ckiw/postscript/ijcv_voc14.pdf,The Pascal Visual Object Classes Challenge: A Retrospective,2014 -1,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,ed2f711cf9bcd9d7ab039d746af109ed9573421a,citation,https://pdfs.semanticscholar.org/ed2f/711cf9bcd9d7ab039d746af109ed9573421a.pdf,Pixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks,2018 -2,VOC,voc,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,ed2f711cf9bcd9d7ab039d746af109ed9573421a,citation,https://pdfs.semanticscholar.org/ed2f/711cf9bcd9d7ab039d746af109ed9573421a.pdf,Pixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks,2018 -3,VOC,voc,13.0222347,77.56718325,Indian Institute of Science Bangalore,edu,a6ac6463b5c89ac9eb013c978f213b309cc6a5c7,citation,https://arxiv.org/pdf/1808.01134.pdf,iSPA-Net: Iterative Semantic Pose Alignment Network,2018 -4,VOC,voc,42.3583961,-71.09567788,MIT,edu,aaf4d938f2e66d158d5e635a9c1d279cdc7639c0,citation,http://pdfs.semanticscholar.org/aaf4/d938f2e66d158d5e635a9c1d279cdc7639c0.pdf,Toward visual understanding of everyday object,2015 -5,VOC,voc,42.2942142,-83.71003894,University of Michigan,edu,74dbcc09a3456ddacf5cece640b84045ebdf6be1,citation,https://arxiv.org/pdf/1810.05162.pdf,Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation,2018 -6,VOC,voc,49.2767454,-122.91777375,Simon Fraser University,edu,74dbcc09a3456ddacf5cece640b84045ebdf6be1,citation,https://arxiv.org/pdf/1810.05162.pdf,Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation,2018 -7,VOC,voc,46.109237,7.08453549,IDIAP Research Institute,edu,dedc7b080b8e13d72f8dc33e248e7637d191fdbf,citation,http://pdfs.semanticscholar.org/dedc/7b080b8e13d72f8dc33e248e7637d191fdbf.pdf,Beyond Dataset Bias: Multi-task Unaligned Shared Knowledge Transfer,2012 -8,VOC,voc,52.17638955,0.14308882,University of Cambridge,edu,dedc7b080b8e13d72f8dc33e248e7637d191fdbf,citation,http://pdfs.semanticscholar.org/dedc/7b080b8e13d72f8dc33e248e7637d191fdbf.pdf,Beyond Dataset Bias: Multi-task Unaligned Shared Knowledge Transfer,2012 -9,VOC,voc,39.00041165,-77.10327775,National Institutes of Health,edu,18c57ddc9c0164ee792661f43a5578f7a00d0330,citation,https://arxiv.org/pdf/1705.02315v2.pdf,ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases,2017 -10,VOC,voc,37.40253645,-122.11655107,Toyota Research Institute,edu,a825680aeb853fc34c65b5844c4c4391148f18c3,citation,https://arxiv.org/pdf/1711.10006.pdf,SSD-6D: Making RGB-Based 3D Detection and 6D Pose Estimation Great Again,2017 -11,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,f249c266321d661ae398c26ddb8c7409f6455ba1,citation,https://pdfs.semanticscholar.org/f249/c266321d661ae398c26ddb8c7409f6455ba1.pdf,Revisiting Faster R-CNN: A Deeper Look at Region Proposal Network,2017 -12,VOC,voc,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,7fa5ede4a34dbe604ce317d529eed78db6642bc0,citation,https://arxiv.org/pdf/1709.01829.pdf,Soft Proposal Networks for Weakly Supervised Object Localization,2017 -13,VOC,voc,35.9990522,-78.9290629,Duke University,edu,7fa5ede4a34dbe604ce317d529eed78db6642bc0,citation,https://arxiv.org/pdf/1709.01829.pdf,Soft Proposal Networks for Weakly Supervised Object Localization,2017 -14,VOC,voc,42.3583961,-71.09567788,MIT,edu,05fdd29536d55fe3ad00689b6f60ada8bc761e91,citation,http://people.csail.mit.edu/torralba/publications/ihog_iccv.pdf,HOGgles: Visualizing Object Detection Features,2013 -15,VOC,voc,24.7925484,120.9951183,National Tsing Hua University,edu,394bf41cd8578ec10cd34452c688c3e3de1c16a7,citation,https://pdfs.semanticscholar.org/394b/f41cd8578ec10cd34452c688c3e3de1c16a7.pdf,Multi-view to Novel View: Synthesizing Novel Views With Self-learned Confidence,2018 -16,VOC,voc,22.42031295,114.20788644,Chinese University of Hong Kong,edu,2453dd38cde21f3248b55d281405f11d58168fa9,citation,http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.342,Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation,2016 -17,VOC,voc,50.7791703,6.06728733,RWTH Aachen University,edu,ccb9ffa26b28dffc4f7d613821d1a9f0d60ea3f4,citation,https://arxiv.org/pdf/1706.09364.pdf,Online Adaptation of Convolutional Neural Networks for Video Object Segmentation,2017 -18,VOC,voc,39.87549675,32.78553506,Middle East Technical University,edu,d38af10096aa90dfccd7e4cec9757900bf6958bd,citation,https://arxiv.org/pdf/1807.04067.pdf,MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network,2018 -19,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,8c1e828a4826a1fb3eb47ee432f5333b974fa141,citation,http://pdfs.semanticscholar.org/8c1e/828a4826a1fb3eb47ee432f5333b974fa141.pdf,Spatial Graph for Image Classification,2012 -20,VOC,voc,38.88140235,121.52281098,Dalian University of Technology,edu,2a31b4bf2a294b6e67956a6cd5ed6d875af548e0,citation,https://arxiv.org/pdf/1710.01020.pdf,Learning Affinity via Spatial Propagation Networks,2017 -21,VOC,voc,39.2899685,-76.62196103,University of Maryland,edu,0790c400bfe6fbefe88ef7791476e1abf1952089,citation,https://arxiv.org/pdf/1511.04067v1.pdf,Deep Gaussian Conditional Random Field Network: A Model-Based Deep Network for Discriminative Denoising,2016 -22,VOC,voc,41.3868913,2.16352385,University of Barcelona,edu,442cf9b24661c9ea5c2a1dcabd4a5b8af1cd89da,citation,https://arxiv.org/pdf/1806.10805.pdf,Beyond One-hot Encoding: lower dimensional target embedding,2018 -23,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,04eda7eee3e0282de50e54554f50870dd17defa1,citation,https://arxiv.org/pdf/1705.08280v1.pdf,How Hard Can It Be? Estimating the Difficulty of Visual Search in an Image,2016 -24,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,90a4125974564a5ab6c2ce2ff685fc36e9cf0680,citation,https://arxiv.org/pdf/1703.08448.pdf,Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach,2017 -25,VOC,voc,39.94976005,116.33629046,Beijing Jiaotong University,edu,90a4125974564a5ab6c2ce2ff685fc36e9cf0680,citation,https://arxiv.org/pdf/1703.08448.pdf,Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach,2017 -26,VOC,voc,39.9922379,116.30393816,Peking University,edu,c3dd6c1ddbb9cfcc1bed6383ffaa0b1ce4d13625,citation,https://arxiv.org/pdf/1807.01544.pdf,TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes,2018 -27,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,2976605dc3b73377696537291d45f09f1ab1fbf5,citation,http://www.ri.cmu.edu/pub_files/2016/6/multi-task.pdf,Cross-Stitch Networks for Multi-task Learning,2016 -28,VOC,voc,28.54632595,77.27325504,Indian Institute of Technology Delhi,edu,25e9a2ec45c34d4610359196dc505a72c3833336,citation,http://pdfs.semanticscholar.org/25e9/a2ec45c34d4610359196dc505a72c3833336.pdf,Benchmarking KAZE and MCM for Multiclass Classification,2015 -29,VOC,voc,39.9808333,116.34101249,Beihang University,edu,935e639bebf905af2e35e8b1e7aa0538d7122185,citation,https://arxiv.org/pdf/1808.00313.pdf,A Network Structure to Explicitly Reduce Confusion Errors in Semantic Segmentation,2018 -30,VOC,voc,39.8011499,140.0459116,Akita Prefectural University,edu,211435a4e14d00f4aaed191acfb548185ee800b9,citation,http://pdfs.semanticscholar.org/2114/35a4e14d00f4aaed191acfb548185ee800b9.pdf,Visual Saliency Based Multiple Objects Segmentation and its Parallel Implementation for Real-Time Vision Processing,2015 -31,VOC,voc,49.25839375,-123.24658161,University of British Columbia,edu,9fae24003bbedecdb617f9779215d79d06b90dd8,citation,https://arxiv.org/pdf/1807.09856.pdf,Where Are the Blobs: Counting by Localization with Point Supervision,2018 -32,VOC,voc,40.72925325,-73.99625394,New York University,edu,c45681fa9d9c36a6a196017ef283ac38904f91bb,citation,https://arxiv.org/pdf/1711.07377.pdf,Pixel-wise object tracking,2017 -33,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,45f858f9e8d7713f60f52618e54089ba68dfcd6d,citation,http://openaccess.thecvf.com/content_ICCV_2017/papers/Sigurdsson_What_Actions_Are_ICCV_2017_paper.pdf,What Actions are Needed for Understanding Human Actions in Videos?,2017 -34,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,57bd01c042a5f64659b3a9f91c048b8594f762f6,citation,http://pdfs.semanticscholar.org/57bd/01c042a5f64659b3a9f91c048b8594f762f6.pdf,Advances in fine-grained visual categorization,2015 -35,VOC,voc,31.30104395,121.50045497,Fudan University,edu,9716416a15e79a36e3481bcdad79cdc905603e6d,citation,https://arxiv.org/pdf/1808.07016.pdf,Gaussian Word Embedding with a Wasserstein Distance Loss,2017 -36,VOC,voc,32.0565957,118.77408833,Nanjing University,edu,97265d64859e06900c11ae5bb5f03f3bd265f858,citation,https://arxiv.org/pdf/1612.01082.pdf,Multilabel Image Classification With Regional Latent Semantic Dependencies,2018 -37,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,97265d64859e06900c11ae5bb5f03f3bd265f858,citation,https://arxiv.org/pdf/1612.01082.pdf,Multilabel Image Classification With Regional Latent Semantic Dependencies,2018 -38,VOC,voc,-33.8809651,151.20107299,University of Technology Sydney,edu,97265d64859e06900c11ae5bb5f03f3bd265f858,citation,https://arxiv.org/pdf/1612.01082.pdf,Multilabel Image Classification With Regional Latent Semantic Dependencies,2018 -39,VOC,voc,42.3583961,-71.09567788,MIT,edu,a19904e76b5ded44e6aeb9af85997d160de6bb22,citation,http://pdfs.semanticscholar.org/a199/04e76b5ded44e6aeb9af85997d160de6bb22.pdf,TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation,2018 -40,VOC,voc,47.05821,15.46019568,Graz University of Technology,edu,96a9ca7a8366ae0efe6b58a515d15b44776faf6e,citation,https://arxiv.org/pdf/1609.00129.pdf,Grid Loss: Detecting Occluded Faces,2016 -41,VOC,voc,47.05821,15.46019568,Graz University of Technology,edu,513b8dc73a9fbc467e1ac130fe8c842b5839ca51,citation,http://pdfs.semanticscholar.org/513b/8dc73a9fbc467e1ac130fe8c842b5839ca51.pdf,Dissertation Scalable Visual Navigation for Micro Aerial Vehicles using Geometric Prior Knowledge,2013 -42,VOC,voc,37.8687126,-122.25586815,"University of California, Berkeley",edu,0ee3aa2a78f9680bb65a823bd9195c879572ec1c,citation,http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Dubey_What_Makes_an_ICCV_2015_paper.pdf,What Makes an Object Memorable?,2015 -43,VOC,voc,42.3583961,-71.09567788,MIT,edu,0ee3aa2a78f9680bb65a823bd9195c879572ec1c,citation,http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Dubey_What_Makes_an_ICCV_2015_paper.pdf,What Makes an Object Memorable?,2015 -44,VOC,voc,37.36566745,-120.42158888,"University of California, Merced",edu,0ee3aa2a78f9680bb65a823bd9195c879572ec1c,citation,http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Dubey_What_Makes_an_ICCV_2015_paper.pdf,What Makes an Object Memorable?,2015 -45,VOC,voc,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,a776acc53591c3eb0b53501d9758d984e2e52a97,citation,https://arxiv.org/pdf/1804.00880.pdf,Weakly Supervised Instance Segmentation using Class Peak Response,2018 -46,VOC,voc,35.9990522,-78.9290629,Duke University,edu,a776acc53591c3eb0b53501d9758d984e2e52a97,citation,https://arxiv.org/pdf/1804.00880.pdf,Weakly Supervised Instance Segmentation using Class Peak Response,2018 -47,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,423b941641728a21e37f41359a691815cdd84ceb,citation,http://arxiv.org/abs/1511.04517,Reversible Recursive Instance-Level Object Segmentation,2016 -48,VOC,voc,47.6423318,-122.1369302,Microsoft,company,666939690c564641b864eed0d60a410b31e49f80,citation,http://pdfs.semanticscholar.org/6669/39690c564641b864eed0d60a410b31e49f80.pdf,What Visual Attributes Characterize an Object Class?,2014 -49,VOC,voc,43.7776426,11.259765,University of Florence,edu,51e8e8c4cac8260ef21c25f9f2a0a68aedbc6d58,citation,https://arxiv.org/pdf/1704.02518.pdf,Deep Generative Adversarial Compression Artifact Removal,2017 -50,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,3b01a839d174dad6f2635cff7ebe7e1aaad701a4,citation,http://pdfs.semanticscholar.org/3b01/a839d174dad6f2635cff7ebe7e1aaad701a4.pdf,Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution,2016 -51,VOC,voc,31.83907195,117.26420748,University of Science and Technology of China,edu,d467035d83fb4e86c4a47b2ca87894388deb8c44,citation,https://pdfs.semanticscholar.org/d467/035d83fb4e86c4a47b2ca87894388deb8c44.pdf,Relief R-CNN : Utilizing Convolutional Feature Interrelationship for Object Detection,2016 -52,VOC,voc,30.284151,-97.73195598,University of Texas at Austin,edu,264a2b946fae4af23c646cc08fc56947b5be82cf,citation,http://doi.ieeecomputersociety.org/10.1109/CVPRW.2015.7301302,Robust object recognition in RGB-D egocentric videos based on Sparse Affine Hull Kernel,2015 -53,VOC,voc,34.0687788,-118.4450094,"University of California, Los Angeles",edu,480888bad59b314236f2d947ebf308ae146c98e4,citation,https://arxiv.org/pdf/1511.06881.pdf,Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net,2016 -54,VOC,voc,25.01682835,121.53846924,National Taiwan University,edu,a1ee55d529e04a80f4eae3b30d0961a985a64fa4,citation,http://www.cs.utexas.edu/~ycsu/publications/mm029-su.pdf,Enabling low bitrate mobile visual recognition: a performance versus bandwidth evaluation,2013 -55,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,0cd736baf31dceea1cc39ac72e00b65587f5fb9e,citation,http://pdfs.semanticscholar.org/4ad0/b6f189718a7287c6e7b90eb05331e56db334.pdf,Learning Hash Functions Using Column Generation,2013 -56,VOC,voc,39.2899685,-76.62196103,University of Maryland,edu,6424574cb92b316928c37232869bfadcb5b4c20f,citation,https://arxiv.org/pdf/1711.05282.pdf,C-WSL: Count-Guided Weakly Supervised Localization,2018 -57,VOC,voc,47.6543238,-122.30800894,University of Washington,edu,51eba481dac6b229a7490f650dff7b17ce05df73,citation,http://grail.cs.washington.edu/wp-content/uploads/2016/09/yatskar2016srv.pdf,Situation Recognition: Visual Semantic Role Labeling for Image Understanding,2016 -58,VOC,voc,47.3764534,8.54770931,ETH Zürich,edu,961a5d5750f18e91e28a767b3cb234a77aac8305,citation,http://pdfs.semanticscholar.org/961a/5d5750f18e91e28a767b3cb234a77aac8305.pdf,Face Detection without Bells and Whistles,2014 -59,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,0c05f60998628884a9ac60116453f1a91bcd9dda,citation,http://pdfs.semanticscholar.org/7b19/80d4ac1730fd0145202a8cb125bf05d96f01.pdf,Optimizing Open-Ended Crowdsourcing: The Next Frontier in Crowdsourced Data Management,2016 -60,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,efa2aacb0fbee857015fad1dba72767f56be6f39,citation,https://pdfs.semanticscholar.org/efa2/aacb0fbee857015fad1dba72767f56be6f39.pdf,Aggregating Crowdsourced Image Segmentations,2018 -61,VOC,voc,37.3936717,-122.0807262,Facebook,company,efa2aacb0fbee857015fad1dba72767f56be6f39,citation,https://pdfs.semanticscholar.org/efa2/aacb0fbee857015fad1dba72767f56be6f39.pdf,Aggregating Crowdsourced Image Segmentations,2018 -62,VOC,voc,34.0687788,-118.4450094,"University of California, Los Angeles",edu,17113b0f647ce05b2e50d1d40c856370f94da7de,citation,http://pdfs.semanticscholar.org/1711/3b0f647ce05b2e50d1d40c856370f94da7de.pdf,Zoom Better to See Clearer: Human Part Segmentation with Auto Zoom Net,2015 -63,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,549d55a06c5402696e063ce36b411f341a64f8a9,citation,http://arxiv.org/pdf/1511.06078v1.pdf,Learning Deep Structure-Preserving Image-Text Embeddings,2016 -64,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,549d55a06c5402696e063ce36b411f341a64f8a9,citation,http://arxiv.org/pdf/1511.06078v1.pdf,Learning Deep Structure-Preserving Image-Text Embeddings,2016 -65,VOC,voc,35.9020448,139.93622009,University of Tokyo,edu,44bfa5311f0921664e9036f63cadd71049a35f35,citation,https://pdfs.semanticscholar.org/44bf/a5311f0921664e9036f63cadd71049a35f35.pdf,Faster R-CNN-Based Glomerular Detection in Multistained Human Whole Slide Images,2018 -66,VOC,voc,49.2579566,7.04577417,Max Planck Institute for Informatics,edu,133f1f2679892d408420d8092283539010723359,citation,http://arxiv.org/pdf/1502.05082v3.pdf,What Makes for Effective Detection Proposals?,2016 -67,VOC,voc,60.18558755,24.8242733,Aalto University,edu,98d04187f091f402a90a6a9a2108393ca5f91563,citation,https://arxiv.org/pdf/1807.09828.pdf,ADVIO: An Authentic Dataset for Visual-Inertial Odometry,2018 -68,VOC,voc,61.44964205,23.85877462,Tampere University of Technology,edu,98d04187f091f402a90a6a9a2108393ca5f91563,citation,https://arxiv.org/pdf/1807.09828.pdf,ADVIO: An Authentic Dataset for Visual-Inertial Odometry,2018 -69,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,f8015e31d1421f6aee5e17fc3907070b8e0a5e59,citation,http://pdfs.semanticscholar.org/f801/5e31d1421f6aee5e17fc3907070b8e0a5e59.pdf,Towards Usable Multimedia Event Detection from Web Videos,2016 -70,VOC,voc,34.0224149,-118.28634407,University of Southern California,edu,6b9e8acef979c13fa9ecc8fe9b635b312fedbcbe,citation,https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Chang_Multiple_Structured-Instance_Learning_2014_CVPR_paper.pdf,Multiple Structured-Instance Learning for Semantic Segmentation with Uncertain Training Data,2014 -71,VOC,voc,51.4584837,-2.6097752,University of Bristol,edu,72fd97d21d6465d4bb407b6f8f3accd4419a2fb4,citation,https://pdfs.semanticscholar.org/384a/ea88ffd79295c99bcb80552f8655dbb87509.pdf,Automated Identification of Individual Great White Sharks from Unrestricted Fin Imagery,2015 -72,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,62b83bf64f200ebb9fa16dfb7108b85e390b2207,citation,https://arxiv.org/pdf/1807.11236.pdf,Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network,2018 -73,VOC,voc,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,62b83bf64f200ebb9fa16dfb7108b85e390b2207,citation,https://arxiv.org/pdf/1807.11236.pdf,Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network,2018 -74,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,2577211aeaaa1f2245ddc379564813bee3d46c06,citation,http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Misra_Seeing_Through_the_CVPR_2016_paper.pdf,Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels,2016 -75,VOC,voc,47.6423318,-122.1369302,Microsoft,company,2577211aeaaa1f2245ddc379564813bee3d46c06,citation,http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Misra_Seeing_Through_the_CVPR_2016_paper.pdf,Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels,2016 -76,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,3900fb44902396f94fb070be41199b4beecc9081,citation,https://arxiv.org/pdf/1612.02101.pdf,Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentation,2017 -77,VOC,voc,34.0687788,-118.4450094,"University of California, Los Angeles",edu,32c45df9e11e6751bcea1b928f398f6c134d22c6,citation,http://pdfs.semanticscholar.org/32c4/5df9e11e6751bcea1b928f398f6c134d22c6.pdf,Towards Unified Object Detection and Semantic Segmentation,2014 -78,VOC,voc,42.36782045,-71.12666653,Harvard University,edu,2bcd59835528c583bb5b310522a5ba6e99c58b15,citation,http://pdfs.semanticscholar.org/c0ef/596a212d0e40c79c6760673fe122e517b43c.pdf,Multi-class Open Set Recognition Using Probability of Inclusion,2014 -79,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,3920a205990abc7883c70cc96a0410a2d056c2a8,citation,http://groups.inf.ed.ac.uk/calvin/Publications/papazoglouICCV2013-camera-ready.pdf,Fast Object Segmentation in Unconstrained Video,2013 -80,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,b6810adcfd507b2e019ebc8afe4f44f953faf946,citation,https://pdfs.semanticscholar.org/b681/0adcfd507b2e019ebc8afe4f44f953faf946.pdf,ML-LocNet: Improving Object Localization with Multi-view Learning Network,2018 -81,VOC,voc,40.0141905,-83.0309143,University of Electronic Science and Technology of China,edu,b6810adcfd507b2e019ebc8afe4f44f953faf946,citation,https://pdfs.semanticscholar.org/b681/0adcfd507b2e019ebc8afe4f44f953faf946.pdf,ML-LocNet: Improving Object Localization with Multi-view Learning Network,2018 -82,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,0e08cf0b19f0600dadce0f6694420d643ea9828b,citation,http://openaccess.thecvf.com/content_iccv_2015/papers/Humayun_The_Middle_Child_ICCV_2015_paper.pdf,The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals,2015 -83,VOC,voc,45.5198289,-122.67797964,Oregon State University,edu,0e08cf0b19f0600dadce0f6694420d643ea9828b,citation,http://openaccess.thecvf.com/content_iccv_2015/papers/Humayun_The_Middle_Child_ICCV_2015_paper.pdf,The Middle Child Problem: Revisiting Parametric Min-Cut and Seeds for Object Proposals,2015 -84,VOC,voc,30.19331415,120.11930822,Zhejiang University,edu,81bf7a4b8b3c21d42cb82f946f762c94031e11b8,citation,https://pdfs.semanticscholar.org/81bf/7a4b8b3c21d42cb82f946f762c94031e11b8.pdf,Segmentation of Nerve on Ultrasound Images Using Deep Adversarial Network,2017 -85,VOC,voc,52.4107358,-4.05295501,Aberystwyth University,edu,30d8fbb9345cdf1096635af7d39a9b04af9b72f9,citation,https://pdfs.semanticscholar.org/30d8/fbb9345cdf1096635af7d39a9b04af9b72f9.pdf,Watching plants grow - a position paper on computer vision and Arabidopsis thaliana,2017 -86,VOC,voc,43.66333345,-79.39769975,University of Toronto,edu,87204e4e1a96b8f59cb91828199dacd192292231,citation,http://pdfs.semanticscholar.org/8720/4e4e1a96b8f59cb91828199dacd192292231.pdf,Towards Real-Time Detection and Tracking of Basketball Players using Deep Neural Networks,2017 -87,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,30a4637cbc461838c151073b265fb08e00492ff4,citation,http://faculty.ucmerced.edu/mhyang/papers/cvpr16_object_localization.pdf,Weakly Supervised Object Localization with Progressive Domain Adaptation,2016 -88,VOC,voc,50.7338124,7.1022465,University of Bonn,edu,606cfdcc43203351dbb944a3bb3719695e557e37,citation,https://pdfs.semanticscholar.org/606c/fdcc43203351dbb944a3bb3719695e557e37.pdf,Ex Paucis Plura : Learning Affordance Segmentation from Very Few Examples,2018 -89,VOC,voc,39.2899685,-76.62196103,University of Maryland,edu,47b6cd69c0746688f6e17b37d73fa12422826dbc,citation,http://pdfs.semanticscholar.org/47b6/cd69c0746688f6e17b37d73fa12422826dbc.pdf,Self corrective Perturbations for Semantic Segmentation and Classification,2017 -90,VOC,voc,38.99203005,-76.9461029,University of Maryland College Park,edu,47b6cd69c0746688f6e17b37d73fa12422826dbc,citation,http://pdfs.semanticscholar.org/47b6/cd69c0746688f6e17b37d73fa12422826dbc.pdf,Self corrective Perturbations for Semantic Segmentation and Classification,2017 -91,VOC,voc,42.8298248,-73.87719385,GE Global Research Center,edu,47b6cd69c0746688f6e17b37d73fa12422826dbc,citation,http://pdfs.semanticscholar.org/47b6/cd69c0746688f6e17b37d73fa12422826dbc.pdf,Self corrective Perturbations for Semantic Segmentation and Classification,2017 -92,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,14421119527aa5882e1552a651fbd2d73bc94637,citation,http://pdfs.semanticscholar.org/9b81/86b6bc1e05d7a473d2afebc8a12698d88691.pdf,Searching for objects driven by context,2012 -93,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,14421119527aa5882e1552a651fbd2d73bc94637,citation,http://pdfs.semanticscholar.org/9b81/86b6bc1e05d7a473d2afebc8a12698d88691.pdf,Searching for objects driven by context,2012 -94,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,3410a1489d04ec6fcfbb3d76d39055117931ccf0,citation,http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.126,Learning Collections of Part Models for Object Recognition,2013 -95,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,69b647afe6526256a93033eac14ce470204e7bae,citation,http://pdfs.semanticscholar.org/d7dd/4fb9074db71ebf9155d64b439102d4c7b0c5.pdf,Training Deep Neural Networks via Direct Loss Minimization,2016 -96,VOC,voc,43.66333345,-79.39769975,University of Toronto,edu,69b647afe6526256a93033eac14ce470204e7bae,citation,http://pdfs.semanticscholar.org/d7dd/4fb9074db71ebf9155d64b439102d4c7b0c5.pdf,Training Deep Neural Networks via Direct Loss Minimization,2016 -97,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,81825711c2aaa1b9d3ead1a300e71c4353a41382,citation,https://arxiv.org/pdf/1607.03476.pdf,End-to-end training of object class detectors for mean average precision,2016 -98,VOC,voc,39.993008,116.329882,SenseTime,company,2ce073da76e6ed87eda2da08da0e00f4f060f1a6,citation,http://doi.ieeecomputersociety.org/10.1109/CVPR.2016.78,Deep Saliency with Encoded Low Level Distance Map and High Level Features,2016 -99,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,2313c827d3cb9a291b6a00d015c29580862bbdcc,citation,https://arxiv.org/pdf/1808.03575.pdf,Weakly- and Semi-supervised Panoptic Segmentation,2018 -100,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,839a2155995acc0a053a326e283be12068b35cb8,citation,http://pdfs.semanticscholar.org/839a/2155995acc0a053a326e283be12068b35cb8.pdf,Handcrafted Local Features are Convolutional Neural Networks,2015 -101,VOC,voc,32.0565957,118.77408833,Nanjing University,edu,634e02d6107529d672cbbdf5b97990966e289829,citation,https://arxiv.org/pdf/1802.05394.pdf,Cost-Effective Training of Deep CNNs with Active Model Adaptation,2018 -102,VOC,voc,56.45796755,-2.98214831,University of Dundee,edu,d0137881f6c791997337b9cc7f1efbd61977270d,citation,http://pdfs.semanticscholar.org/d013/7881f6c791997337b9cc7f1efbd61977270d.pdf,"University of Dundee An automated pattern recognition system for classifying indirect immunofluorescence images for HEp-2 cells and specimens Manivannan,",2016 -103,VOC,voc,42.2942142,-83.71003894,University of Michigan,edu,ed173a39f4cd980eef319116b6ba39cec1b37c42,citation,https://arxiv.org/pdf/1611.05424.pdf,Associative Embedding: End-to-End Learning for Joint Detection and Grouping,2017 -104,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,ed173a39f4cd980eef319116b6ba39cec1b37c42,citation,https://arxiv.org/pdf/1611.05424.pdf,Associative Embedding: End-to-End Learning for Joint Detection and Grouping,2017 -105,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,84cf838be40e2ab05732fbefbb93ccb2afb0cb48,citation,http://pdfs.semanticscholar.org/84cf/838be40e2ab05732fbefbb93ccb2afb0cb48.pdf,Recognizing Handwritten Characters,2016 -106,VOC,voc,37.26728,126.9841151,Seoul National University,edu,b082f440ee91e2751701401919584203b37e1e1a,citation,https://pdfs.semanticscholar.org/303c/28f1ba643a7cd88255cc379e79052fb7e7b1.pdf,SeedNet : Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation,2018 -107,VOC,voc,22.2081469,114.25964115,University of Hong Kong,edu,6008213e4270e88cb414459de759c961469b92dd,citation,https://arxiv.org/pdf/1802.09129.pdf,"Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning",2018 -108,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,90b4470032f2796a347a0080bcd833c2db0e8bf0,citation,https://arxiv.org/pdf/1807.07760.pdf,Improving Image Clustering With Multiple Pretrained CNN Feature Extractors,2018 -109,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,beecaf2d6e9d102b6b2459ea38e15179a4b55ffd,citation,https://arxiv.org/pdf/1611.09587.pdf,Surveillance Video Parsing with Single Frame Supervision,2017 -110,VOC,voc,41.3868913,2.16352385,University of Barcelona,edu,0fb8317a8bf5feaf297af8e9b94c50c5ed0e8277,citation,http://pdfs.semanticscholar.org/0fb8/317a8bf5feaf297af8e9b94c50c5ed0e8277.pdf,Detecting Hands in Egocentric Videos: Towards Action Recognition,2017 -111,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,0e0179eb4b43016691f0f1473a08089dda21f8f0,citation,http://pdfs.semanticscholar.org/0e01/79eb4b43016691f0f1473a08089dda21f8f0.pdf,The Art of Detection,2016 -112,VOC,voc,49.2579566,7.04577417,Max Planck Institute for Informatics,edu,135c957f6a80f250507c7707479e584c288f430f,citation,http://doi.ieeecomputersociety.org/10.1109/CVPR.2014.498,Image-Based Synthesis and Re-synthesis of Viewpoints Guided by 3D Models,2014 -113,VOC,voc,39.00041165,-77.10327775,National Institutes of Health,edu,c72b063e23b8b45b57a42ebc2f9714297c539a6f,citation,https://arxiv.org/pdf/1801.04334.pdf,TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays,2018 -114,VOC,voc,36.05238585,140.11852361,National Institute of Advanced Industrial Science and Technology,edu,061ffd3967540424ac4e4066f4a605d8318bab90,citation,https://staff.aist.go.jp/takumi.kobayashi/publication/2014/CVPR2014.pdf,Dirichlet-Based Histogram Feature Transform for Image Classification,2014 -115,VOC,voc,42.3583961,-71.09567788,MIT,edu,1a2e9a56e5f71bf95a2f68b6e67e2aaa1c6bf91e,citation,http://pdfs.semanticscholar.org/1a2e/9a56e5f71bf95a2f68b6e67e2aaa1c6bf91e.pdf,FPM: Fine Pose Parts-Based Model with 3D CAD Models,2014 -116,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,c6f58adf4a5ee8499cbc9b9bc1e6f1c39f1f8eae,citation,https://pdfs.semanticscholar.org/c6f5/8adf4a5ee8499cbc9b9bc1e6f1c39f1f8eae.pdf,Earn to P Ay a Ttention,2018 -117,VOC,voc,32.87935255,-117.23110049,"University of California, San Diego",edu,3c8db2ca155ce4e15ec8a2c4c4b979de654fb296,citation,http://pages.ucsd.edu/~ztu/publication/iccv15_hed.pdf,Holistically-Nested Edge Detection,2015 -118,VOC,voc,59.34986645,18.07063213,"KTH Royal Institute of Technology, Stockholm",edu,8ccd6aaf1ee4b66c13fffbf560e3920f9bdf5f10,citation,http://pdfs.semanticscholar.org/8ccd/6aaf1ee4b66c13fffbf560e3920f9bdf5f10.pdf,A multitask deep learning model for real-time deployment in embedded systems,2017 -119,VOC,voc,53.5238572,-113.52282665,University of Alberta,edu,b4f5cf797a1c857f32e5740d53d9990bc925af2b,citation,https://pdfs.semanticscholar.org/b4f5/cf797a1c857f32e5740d53d9990bc925af2b.pdf,Review of Segmentation with Deep Learning and Discover Its Application in Ultrasound Images,2018 -120,VOC,voc,49.2579566,7.04577417,Max Planck Institute for Informatics,edu,3bad18554678ab46bbbf9de41d36423bc8083c83,citation,http://arxiv.org/pdf/1511.07803v1.pdf,Weakly Supervised Object Boundaries,2016 -121,VOC,voc,24.7925484,120.9951183,National Tsing Hua University,edu,07191c2047b5b643dd72a0583c1d537ba59f977a,citation,http://pdfs.semanticscholar.org/0719/1c2047b5b643dd72a0583c1d537ba59f977a.pdf,Interactive Segmentation from 1-Bit Feedback,2016 -122,VOC,voc,37.26728,126.9841151,Seoul National University,edu,ae6e8851dfd9c97e37e1cbd61b21cc54d5e2b9c7,citation,https://arxiv.org/pdf/1802.04977.pdf,Paraphrasing Complex Network: Network Compression via Factor Transfer,2018 -123,VOC,voc,37.26728,126.9841151,Seoul National University,edu,5375a3344017d9502ebb4170325435de3da1fa16,citation,https://doi.org/10.1007/978-3-642-37447-0,Computer Vision – ACCV 2012,2012 -124,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,5375a3344017d9502ebb4170325435de3da1fa16,citation,https://doi.org/10.1007/978-3-642-37447-0,Computer Vision – ACCV 2012,2012 -125,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,5375a3344017d9502ebb4170325435de3da1fa16,citation,https://doi.org/10.1007/978-3-642-37447-0,Computer Vision – ACCV 2012,2012 -126,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,fdfd57d4721174eba288e501c0c120ad076cdca8,citation,https://arxiv.org/pdf/1704.07129.pdf,An Analysis of Action Recognition Datasets for Language and Vision Tasks,2017 -127,VOC,voc,32.0565957,118.77408833,Nanjing University,edu,ec83c63e28ae2a658bc76a6750e078c3a54b9760,citation,https://arxiv.org/pdf/1705.02758.pdf,Deep Descriptor Transforming for Image Co-Localization,2017 -128,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,ec83c63e28ae2a658bc76a6750e078c3a54b9760,citation,https://arxiv.org/pdf/1705.02758.pdf,Deep Descriptor Transforming for Image Co-Localization,2017 -129,VOC,voc,59.34986645,18.07063213,"KTH Royal Institute of Technology, Stockholm",edu,b1177aad0db8bd6b605ffe0d68addaf97b1f9a6b,citation,https://pdfs.semanticscholar.org/5035/733022916db7e5965c565327e169da1e2f39.pdf,Visual Representations and Models: From Latent SVM to Deep Learning,2016 -130,VOC,voc,31.83907195,117.26420748,University of Science and Technology of China,edu,a5ae7d662ed086bc5b0c9a2c1dc54fcb23635000,citation,https://pdfs.semanticscholar.org/a5ae/7d662ed086bc5b0c9a2c1dc54fcb23635000.pdf,Relief R-CNN : Utilizing Convolutional Feature Interrelationship for Fast Object Detection Deployment,2016 -131,VOC,voc,22.53521465,113.9315911,Shenzhen University,edu,a5ae7d662ed086bc5b0c9a2c1dc54fcb23635000,citation,https://pdfs.semanticscholar.org/a5ae/7d662ed086bc5b0c9a2c1dc54fcb23635000.pdf,Relief R-CNN : Utilizing Convolutional Feature Interrelationship for Fast Object Detection Deployment,2016 -132,VOC,voc,53.38522185,-6.25740874,Dublin City University,edu,9528e2e8c20517ab916f803c0371abb4f0ed488b,citation,http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Pan_Shallow_and_Deep_CVPR_2016_paper.pdf,Shallow and Deep Convolutional Networks for Saliency Prediction,2016 -133,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,e2272f50ffa33b8e41509e4b795ad5a4eb27bb46,citation,https://arxiv.org/pdf/1607.07671.pdf,Region-based semantic segmentation with end-to-end training,2016 -134,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,b8d61dc56a4112e0317c6a7323417ee649476148,citation,https://arxiv.org/pdf/1807.05636.pdf,Cross Pixel Optical Flow Similarity for Self-Supervised Learning,2018 -135,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,db0a4af734dab1854c2e8dfe499fe0e353226e45,citation,https://pdfs.semanticscholar.org/db0a/4af734dab1854c2e8dfe499fe0e353226e45.pdf,Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection,2018 -136,VOC,voc,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,db0a4af734dab1854c2e8dfe499fe0e353226e45,citation,https://pdfs.semanticscholar.org/db0a/4af734dab1854c2e8dfe499fe0e353226e45.pdf,Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection,2018 -137,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,ffe0f43206169deef3a2bf64cec90fe35bb1a8e5,citation,http://pdfs.semanticscholar.org/ffe0/f43206169deef3a2bf64cec90fe35bb1a8e5.pdf,"Automated Processing of Imaging Data through Multi-tiered Classification of Biological Structures Illustrated Using Caenorhabditis elegans -",2015 -138,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,ffe0f43206169deef3a2bf64cec90fe35bb1a8e5,citation,http://pdfs.semanticscholar.org/ffe0/f43206169deef3a2bf64cec90fe35bb1a8e5.pdf,"Automated Processing of Imaging Data through Multi-tiered Classification of Biological Structures Illustrated Using Caenorhabditis elegans -",2015 -139,VOC,voc,45.77445695,126.67684917,Harbin Engineering University,edu,479eb6579194d4d944671dfe5e90b122ca4b58fd,citation,https://pdfs.semanticscholar.org/479e/b6579194d4d944671dfe5e90b122ca4b58fd.pdf,Structural inference embedded adversarial networks for scene parsing,2018 -140,VOC,voc,34.2469152,108.91061982,Northwestern Polytechnical University,edu,479eb6579194d4d944671dfe5e90b122ca4b58fd,citation,https://pdfs.semanticscholar.org/479e/b6579194d4d944671dfe5e90b122ca4b58fd.pdf,Structural inference embedded adversarial networks for scene parsing,2018 -141,VOC,voc,1.29500195,103.84909214,Singapore Management University,edu,d289ce63055c10937e5715e940a4bb9d0af7a8c5,citation,http://dl.acm.org/citation.cfm?id=3081360,DeepMon: Mobile GPU-based Deep Learning Framework for Continuous Vision Applications,2017 -142,VOC,voc,60.18558755,24.8242733,Aalto University,edu,061bba574c7c2ef0ba9de91afc4fcab70feddd4f,citation,http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.272,Paying Attention to Descriptions Generated by Image Captioning Models,2017 -143,VOC,voc,28.59899755,-81.19712501,University of Central Florida,edu,061bba574c7c2ef0ba9de91afc4fcab70feddd4f,citation,http://doi.ieeecomputersociety.org/10.1109/ICCV.2017.272,Paying Attention to Descriptions Generated by Image Captioning Models,2017 -144,VOC,voc,34.7275714,135.2371,Kobe University,edu,ee2217f9d22d6a18aaf97f05768035c38305d1fa,citation,https://doi.org/10.1109/APSIPA.2015.7415501,Detection of facial parts via deformable part model using part annotation,2015 -145,VOC,voc,50.7791703,6.06728733,RWTH Aachen University,edu,18219d85bb14f851fc4714df19cc7f38dff8ddc3,citation,http://pdfs.semanticscholar.org/1821/9d85bb14f851fc4714df19cc7f38dff8ddc3.pdf,Online Adaptation of Convolutional Neural Networks for the 2017 DAVIS Challenge on Video Object Segmentation,2017 -146,VOC,voc,31.20081505,121.42840681,Shanghai Jiao Tong University,edu,da44881db32c132eb9cdef524618e3c8ed340b47,citation,https://arxiv.org/pdf/1802.00383.pdf,Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters,2018 -147,VOC,voc,50.7338124,7.1022465,University of Bonn,edu,cc94b423c298003f0f164e63e63177d443291a77,citation,https://arxiv.org/pdf/1805.03994.pdf,Multi-View Semantic Labeling of 3D Point Clouds for Automated Plant Phenotyping,2018 -148,VOC,voc,39.9922379,116.30393816,Peking University,edu,83a811fd947415df2413d15386dbc558f07595cb,citation,https://arxiv.org/pdf/1709.08295.pdf,Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN,2017 -149,VOC,voc,-33.8809651,151.20107299,University of Technology Sydney,edu,3a5f5aca6138abcf22ede1af5572e01eb0f761d1,citation,https://pdfs.semanticscholar.org/3a5f/5aca6138abcf22ede1af5572e01eb0f761d1.pdf,Optimizing Multivariate Performance Measures from Multi-View Data,2016 -150,VOC,voc,34.2469152,108.91061982,Northwestern Polytechnical University,edu,ce300b006f42c1b64ca0e53d1cf28d11a98ece8f,citation,https://pdfs.semanticscholar.org/ce30/0b006f42c1b64ca0e53d1cf28d11a98ece8f.pdf,Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l 1-Norm Distances,0 -151,VOC,voc,34.0224149,-118.28634407,University of Southern California,edu,71b038958df0b7855fc7b8b8e7dcde8537a7c1ad,citation,http://pdfs.semanticscholar.org/71b0/38958df0b7855fc7b8b8e7dcde8537a7c1ad.pdf,Kernel Methods for Unsupervised Domain Adaptation by Boqing Gong,2015 -152,VOC,voc,34.2469152,108.91061982,Northwestern Polytechnical University,edu,af7cab9b4a2a2a565a3efe0a226c517f47289077,citation,https://arxiv.org/pdf/1803.10910.pdf,Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective,2018 -153,VOC,voc,-35.2776999,149.118527,Australian National University,edu,af7cab9b4a2a2a565a3efe0a226c517f47289077,citation,https://arxiv.org/pdf/1803.10910.pdf,Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective,2018 -154,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,3a6ebdfb6375093885e846153a48139ef1ecfae6,citation,http://arxiv.org/abs/1411.7466,The treasure beneath convolutional layers: Cross-convolutional-layer pooling for image classification,2015 -155,VOC,voc,51.24303255,-0.59001382,University of Surrey,edu,a7e9d230bc44dfbe56757f3025d5b4caa49032f3,citation,http://pdfs.semanticscholar.org/a7e9/d230bc44dfbe56757f3025d5b4caa49032f3.pdf,Unity in Diversity: Discovering Topics from Words - Information Theoretic Co-clustering for Visual Categorization,2012 -156,VOC,voc,37.5557271,127.0436642,Hanyang University,edu,50137d663802224e683951c48970496b38b02141,citation,http://pdfs.semanticscholar.org/5013/7d663802224e683951c48970496b38b02141.pdf,DETRAC: A New Benchmark and Protocol for Multi-Object Tracking,2015 -157,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,07de8371ad4901356145722aa29abaeafd0986b9,citation,http://pdfs.semanticscholar.org/07de/8371ad4901356145722aa29abaeafd0986b9.pdf,Towards Usable Multimedia Event Detection,2017 -158,VOC,voc,41.21002475,-73.80407056,IBM Thomas J. Watson Research Center,company,af386bb1b5e8c9f65b3ae836198a93aa860d6331,citation,https://arxiv.org/pdf/1805.04574.pdf,Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation,2018 -159,VOC,voc,17.4454957,78.34854698,International Institute of Information Technology,edu,d6b1b0e60e1764982ef95d4ade8fcaa10bfb156a,citation,http://pdfs.semanticscholar.org/d6b1/b0e60e1764982ef95d4ade8fcaa10bfb156a.pdf,A Sketch-based Approach for Multimedia Retrieval,2016 -160,VOC,voc,51.49887085,-0.17560797,Imperial College London,edu,37b3637dab65b91a5c91bb6a583e69c448823cc1,citation,https://arxiv.org/pdf/1705.05994.pdf,Learning a Hierarchical Latent-Variable Model of 3D Shapes,2018 -161,VOC,voc,39.9574,-75.19026706,Drexel University,edu,83d16fb8f53156c9e2b28d75abb6532af515440f,citation,http://pdfs.semanticscholar.org/83d1/6fb8f53156c9e2b28d75abb6532af515440f.pdf,Large-scale Document Labeling using Supervised Sequence Embedding,2012 -162,VOC,voc,45.51181205,-122.68492999,Portland State University,edu,05e45f61dc7577c50114a382abc6e952ae24cdac,citation,https://pdfs.semanticscholar.org/05e4/5f61dc7577c50114a382abc6e952ae24cdac.pdf,"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",2012 -163,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,192235f5a9e4c9d6a28ec0d333e36f294b32f764,citation,http://www.andrew.cmu.edu/user/sjayasur/iccv.pdf,Reconfiguring the Imaging Pipeline for Computer Vision,2017 -164,VOC,voc,42.4505507,-76.4783513,Cornell University,edu,192235f5a9e4c9d6a28ec0d333e36f294b32f764,citation,http://www.andrew.cmu.edu/user/sjayasur/iccv.pdf,Reconfiguring the Imaging Pipeline for Computer Vision,2017 -165,VOC,voc,50.0764296,14.41802312,Czech Technical University,edu,bd4f2e7a196c0d6033a49390ee8836f4f551b7c8,citation,http://rrc.cvc.uab.es/files/Robust-Reading-Competition-Karatzas.pdf,ICDAR 2015 competition on Robust Reading,2015 -166,VOC,voc,33.59914655,130.22359848,Kyushu University,edu,bd4f2e7a196c0d6033a49390ee8836f4f551b7c8,citation,http://rrc.cvc.uab.es/files/Robust-Reading-Competition-Karatzas.pdf,ICDAR 2015 competition on Robust Reading,2015 -167,VOC,voc,49.2579566,7.04577417,Max Planck Institute for Informatics,edu,3d5575e9ba02128d94c20330f4525fc816411ec2,citation,https://arxiv.org/pdf/1612.02646.pdf,Learning Video Object Segmentation from Static Images,2017 -168,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,78f62042bfb3bb49ba10e142d118a9bb058b2a19,citation,http://pdfs.semanticscholar.org/78f6/2042bfb3bb49ba10e142d118a9bb058b2a19.pdf,WebSeg: Learning Semantic Segmentation from Web Searches,2018 -169,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,0c7aac75ccd17d696cff2e1ce95db0493f5c18a2,citation,https://arxiv.org/pdf/1809.01123.pdf,VideoMatch: Matching Based Video Object Segmentation,2018 -170,VOC,voc,3.12267405,101.65356103,University of Malaya,edu,6c78add400f749c897dc3eb93996eda1c796e91c,citation,https://arxiv.org/pdf/1410.3752.pdf,Enhanced Random Forest with Image/Patch-Level Learning for Image Understanding,2014 -171,VOC,voc,51.49887085,-0.17560797,Imperial College London,edu,6c78add400f749c897dc3eb93996eda1c796e91c,citation,https://arxiv.org/pdf/1410.3752.pdf,Enhanced Random Forest with Image/Patch-Level Learning for Image Understanding,2014 -172,VOC,voc,39.9922379,116.30393816,Peking University,edu,6c78add400f749c897dc3eb93996eda1c796e91c,citation,https://arxiv.org/pdf/1410.3752.pdf,Enhanced Random Forest with Image/Patch-Level Learning for Image Understanding,2014 -173,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,b61c0b11b1c25958d202b4f7ca772e1d95ee1037,citation,http://pdfs.semanticscholar.org/b61c/0b11b1c25958d202b4f7ca772e1d95ee1037.pdf,Bridging Category-level and Instance-level Semantic Image Segmentation,2016 -174,VOC,voc,34.0224149,-118.28634407,University of Southern California,edu,79894ddf290d3c7a768d634eceb7888564b5cf19,citation,https://arxiv.org/pdf/1708.01676.pdf,Query-Guided Regression Network with Context Policy for Phrase Grounding,2017 -175,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,fec2a5a06a3aab5efe923a78d208ec747d5e4894,citation,https://arxiv.org/pdf/1805.12018.pdf,Generalizing to Unseen Domains via Adversarial Data Augmentation,2018 -176,VOC,voc,31.30104395,121.50045497,Fudan University,edu,5ac63895a7d3371a739d066bb1631fc178d8276a,citation,http://doi.acm.org/10.1145/3123266.3123379,Learning Semantic Feature Map for Visual Content Recognition,2017 -177,VOC,voc,39.2899685,-76.62196103,University of Maryland,edu,5ac63895a7d3371a739d066bb1631fc178d8276a,citation,http://doi.acm.org/10.1145/3123266.3123379,Learning Semantic Feature Map for Visual Content Recognition,2017 -178,VOC,voc,-34.40505545,150.87834655,University of Wollongong,edu,4e559f23bcf502c752f2938ad7f0182047b8d1e4,citation,http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Wang_A_Fast_Approximate_2013_CVPR_paper.pdf,A Fast Approximate AIB Algorithm for Distributional Word Clustering,2013 -179,VOC,voc,-35.2776999,149.118527,Australian National University,edu,7536b6a9f3cb4ae810e2ef6d0219134b4e546dd0,citation,http://pdfs.semanticscholar.org/7536/b6a9f3cb4ae810e2ef6d0219134b4e546dd0.pdf,Semi-Automatic Image Labelling Using Depth Information,2015 -180,VOC,voc,42.7298459,-73.67950216,Rensselaer Polytechnic Institute,edu,11b89011298e193d9e6a1d99302221c1d8645bda,citation,http://openaccess.thecvf.com/content_iccv_2015/papers/Gao_Structured_Feature_Selection_ICCV_2015_paper.pdf,Structured Feature Selection,2015 -181,VOC,voc,39.9601488,116.35193921,Beijing University of Posts and Telecommunications,edu,de3245c795bc50ebdb5d929c8da664341238264a,citation,https://arxiv.org/pdf/1705.08590.pdf,Generative Model With Coordinate Metric Learning for Object Recognition Based on 3D Models,2018 -182,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,cc2eaa182f33defbb33d69e9547630aab7ed9c9c,citation,http://pdfs.semanticscholar.org/ce2e/e807a63bbdffa530c80915b04d11a7f29a21.pdf,Surpassing Humans and Computers with JELLYBEAN: Crowd-Vision-Hybrid Counting Algorithms,2015 -183,VOC,voc,40.00471095,-83.02859368,Ohio State University,edu,cc2eaa182f33defbb33d69e9547630aab7ed9c9c,citation,http://pdfs.semanticscholar.org/ce2e/e807a63bbdffa530c80915b04d11a7f29a21.pdf,Surpassing Humans and Computers with JELLYBEAN: Crowd-Vision-Hybrid Counting Algorithms,2015 -184,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,cc2eaa182f33defbb33d69e9547630aab7ed9c9c,citation,http://pdfs.semanticscholar.org/ce2e/e807a63bbdffa530c80915b04d11a7f29a21.pdf,Surpassing Humans and Computers with JELLYBEAN: Crowd-Vision-Hybrid Counting Algorithms,2015 -185,VOC,voc,32.0565957,118.77408833,Nanjing University,edu,9c71e6f4e27b3a6f0f872ec683b0f6dfe0966c05,citation,http://pdfs.semanticscholar.org/9c71/e6f4e27b3a6f0f872ec683b0f6dfe0966c05.pdf,"Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey",2017 -186,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,b88b83d2ffd30bf3bc3be3fb7492fd88f633b2fe,citation,http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR2013/data/Papers/4989a827.pdf,Subcategory-Aware Object Classification,2013 -187,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,b6a3802075d460093977f8566c451f950edf7a47,citation,https://pdfs.semanticscholar.org/0999/e5baf505eed0df8e2661c29354f3757b3399.pdf,Facilitating and Exploring Planar Homogeneous Texture for Indoor Scene Understanding,2016 -188,VOC,voc,51.7555205,-1.2261597,Oxford Brookes University,edu,cd6cab9357f333ad9966abc76f830c190a1b7911,citation,https://pdfs.semanticscholar.org/cd6c/ab9357f333ad9966abc76f830c190a1b7911.pdf,"Recognition, reorganisation, reconstruction and reinteraction for scene understanding",2014 -189,VOC,voc,47.3764534,8.54770931,ETH Zürich,edu,0fe8b5503681128da84a8454a4cc94470adc09ea,citation,http://pdfs.semanticscholar.org/b96a/0ccae1d15cffe3b479b2c56d9132b05cd846.pdf,Sparsity Potentials for Detecting Objects with the Hough Transform,2012 -190,VOC,voc,35.7036227,51.35125097,Sharif University of Technology,edu,0fe8b5503681128da84a8454a4cc94470adc09ea,citation,http://pdfs.semanticscholar.org/b96a/0ccae1d15cffe3b479b2c56d9132b05cd846.pdf,Sparsity Potentials for Detecting Objects with the Hough Transform,2012 -191,VOC,voc,47.6423318,-122.1369302,Microsoft,company,9bbc952adb3e3c6091d45d800e806d3373a52bac,citation,https://pdfs.semanticscholar.org/9bbc/952adb3e3c6091d45d800e806d3373a52bac.pdf,Learning Visual Classifiers using Human-centric Annotations,2015 -192,VOC,voc,35.6572957,139.54255868,University of Electro-Communications,edu,6e209d7d33c0be8afae863f4e4e9c3e86826711f,citation,http://img.cs.uec.ac.jp/pub/conf16/161204shimok_1_ppt.pdf,Weakly-supervised segmentation by combining CNN feature maps and object saliency maps,2016 -193,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,46d85e1dc7057bef62647bd9241601e9896a1b02,citation,http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2A_040_ext.pdf,Improving object proposals with multi-thresholding straddling expansion,2015 -194,VOC,voc,35.2742655,137.01327841,Chubu University,edu,67e3fac91c699c085d47774990572d8ccdc36f15,citation,http://pdfs.semanticscholar.org/67e3/fac91c699c085d47774990572d8ccdc36f15.pdf,Multiple Skip Connections and Dilated Convolutions for Semantic Segmentation,2017 -195,VOC,voc,34.0224149,-118.28634407,University of Southern California,edu,a4f29217d2120ed1490aea7e1c5b78c3b76e972f,citation,https://arxiv.org/pdf/1610.06907.pdf,Enhanced object detection via fusion with prior beliefs from image classification,2017 -196,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,f2d07a77711a8d74bbfa48a0436dae18a698b05a,citation,http://pdfs.semanticscholar.org/f2d0/7a77711a8d74bbfa48a0436dae18a698b05a.pdf,Composite Statistical Learning and Inference for Semantic Segmentation,2014 -197,VOC,voc,40.2075951,-8.42566148,University of Coimbra,edu,f2d07a77711a8d74bbfa48a0436dae18a698b05a,citation,http://pdfs.semanticscholar.org/f2d0/7a77711a8d74bbfa48a0436dae18a698b05a.pdf,Composite Statistical Learning and Inference for Semantic Segmentation,2014 -198,VOC,voc,55.7039571,13.1902011,Lund University,edu,f2d07a77711a8d74bbfa48a0436dae18a698b05a,citation,http://pdfs.semanticscholar.org/f2d0/7a77711a8d74bbfa48a0436dae18a698b05a.pdf,Composite Statistical Learning and Inference for Semantic Segmentation,2014 -199,VOC,voc,61.44964205,23.85877462,Tampere University of Technology,edu,ff11cb09e409996020a2dc3a8afc3b535e6b2482,citation,https://arxiv.org/pdf/1807.03142.pdf,Faster Bounding Box Annotation for Object Detection in Indoor Scenes,2018 -200,VOC,voc,35.84658875,127.1350133,Chonbuk National University,edu,e103fa24d7fa297cd206b22b3bf670bfda6c65c4,citation,https://pdfs.semanticscholar.org/e103/fa24d7fa297cd206b22b3bf670bfda6c65c4.pdf,Object Detection in Very High-Resolution Aerial Images Using One-Stage Densely Connected Feature Pyramid Network,2018 -201,VOC,voc,41.8268682,-71.40123146,Brown University,edu,9a781a01b5a9c210dd2d27db8b73b7d62bc64837,citation,http://pdfs.semanticscholar.org/9a78/1a01b5a9c210dd2d27db8b73b7d62bc64837.pdf,An Attempt to Build Object Detection Models by Reusing Parts,2013 -202,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,ac559888f996923c06b1cf90db6b57b12e582289,citation,http://pdfs.semanticscholar.org/ac55/9888f996923c06b1cf90db6b57b12e582289.pdf,Benchmarking neuromorphic vision: lessons learnt from computer vision,2015 -203,VOC,voc,47.3764534,8.54770931,ETH Zürich,edu,ac559888f996923c06b1cf90db6b57b12e582289,citation,http://pdfs.semanticscholar.org/ac55/9888f996923c06b1cf90db6b57b12e582289.pdf,Benchmarking neuromorphic vision: lessons learnt from computer vision,2015 -204,VOC,voc,39.2899685,-76.62196103,University of Maryland,edu,ac559888f996923c06b1cf90db6b57b12e582289,citation,http://pdfs.semanticscholar.org/ac55/9888f996923c06b1cf90db6b57b12e582289.pdf,Benchmarking neuromorphic vision: lessons learnt from computer vision,2015 -205,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,2a4fc35acaf09517e9c63821cadd428a84832416,citation,http://www.vision.ee.ethz.ch/en/publications/papers/proceedings/eth_biwi_00905.pdf,Learning object class detectors from weakly annotated video,2012 -206,VOC,voc,22.053565,113.39913285,Jilin University,edu,cd4850de71e4e858be5f5e6ef7f48d5bf7decea6,citation,http://pdfs.semanticscholar.org/cd48/50de71e4e858be5f5e6ef7f48d5bf7decea6.pdf,Distribution Entropy Boosted VLAD for Image Retrieval,2016 -207,VOC,voc,40.4319722,-86.92389368,Purdue University,edu,34b925a111ba29f73f5c0d1b363f357958d563c1,citation,https://www.microsoft.com/en-us/research/wp-content/uploads/2015/03/Shoaib_DATE_2015.pdf,SAPPHIRE: An always-on context-aware computer vision system for portable devices,2015 -208,VOC,voc,47.6423318,-122.1369302,Microsoft,company,34b925a111ba29f73f5c0d1b363f357958d563c1,citation,https://www.microsoft.com/en-us/research/wp-content/uploads/2015/03/Shoaib_DATE_2015.pdf,SAPPHIRE: An always-on context-aware computer vision system for portable devices,2015 -209,VOC,voc,24.7925484,120.9951183,National Tsing Hua University,edu,c76b611a986a2e09df22603d93b2d9125aaff369,citation,https://arxiv.org/pdf/1810.07050.pdf,Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation,2018 -210,VOC,voc,22.053565,113.39913285,Jilin University,edu,1927d01b6b9acf865401b544e25b62a7ddbac5fa,citation,https://pdfs.semanticscholar.org/1927/d01b6b9acf865401b544e25b62a7ddbac5fa.pdf,An Enhanced Region Proposal Network for object detection using deep learning method,2018 -211,VOC,voc,-33.8809651,151.20107299,University of Technology Sydney,edu,1ecd20f7fc34344e396825d27bc5a9871ab0d0c2,citation,https://arxiv.org/pdf/1810.09091.pdf,SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation,2018 -212,VOC,voc,42.3583961,-71.09567788,MIT,edu,26aa0aff1ea1baf848a521363cc455044690e090,citation,http://pdfs.semanticscholar.org/26aa/0aff1ea1baf848a521363cc455044690e090.pdf,A 2D + 3D Rich Data Approach to Scene Understanding,2013 -213,VOC,voc,46.0658836,11.1159894,University of Trento,edu,3548cb9ee54bd4c8b3421f1edd393da9038da293,citation,http://www.huppelen.nl/publications/2012cvprUnseenEventCompositionality.pdf,(Unseen) event recognition via semantic compositionality,2012 -214,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,25ee08db14dca641d085584909b551042618b8bf,citation,http://pdfs.semanticscholar.org/25ee/08db14dca641d085584909b551042618b8bf.pdf,Learning to Segment Instances in Videos with Spatial Propagation Network,2017 -215,VOC,voc,37.36566745,-120.42158888,"University of California, Merced",edu,25ee08db14dca641d085584909b551042618b8bf,citation,http://pdfs.semanticscholar.org/25ee/08db14dca641d085584909b551042618b8bf.pdf,Learning to Segment Instances in Videos with Spatial Propagation Network,2017 -216,VOC,voc,48.9095338,9.1831892,University of Stuttgart,edu,d0f81c31e11af1783644704321903a3d2bd83fd6,citation,https://pdfs.semanticscholar.org/d0f8/1c31e11af1783644704321903a3d2bd83fd6.pdf,3D Façade Labeling over Complex Scenarios: A Case Study Using Convolutional Neural Network and Structure-From-Motion,2018 -217,VOC,voc,50.7369302,-3.53647672,University of Exeter,edu,d0f81c31e11af1783644704321903a3d2bd83fd6,citation,https://pdfs.semanticscholar.org/d0f8/1c31e11af1783644704321903a3d2bd83fd6.pdf,3D Façade Labeling over Complex Scenarios: A Case Study Using Convolutional Neural Network and Structure-From-Motion,2018 -218,VOC,voc,38.99203005,-76.9461029,University of Maryland College Park,edu,a996f22a2d0c685f7e4972df9f45e99efc3cbb76,citation,https://arxiv.org/pdf/1708.00079.pdf,Towards the Success Rate of One: Real-Time Unconstrained Salient Object Detection,2018 -219,VOC,voc,47.05821,15.46019568,Graz University of Technology,edu,4da5f0c1d07725a06c6b4a2646e31ea3a5f14435,citation,http://pdfs.semanticscholar.org/4da5/f0c1d07725a06c6b4a2646e31ea3a5f14435.pdf,End-to-End Training of Hybrid CNN-CRF Models for Semantic Segmentation using Structured Learning,2017 -220,VOC,voc,52.3553655,4.9501644,University of Amsterdam,edu,26c58e24687ccbe9737e41837aab74e4a499d259,citation,http://www.cv-foundation.org/openaccess/content_iccv_2013/papers/Li_Codemaps_-_Segment_2013_ICCV_paper.pdf,"Codemaps - Segment, Classify and Search Objects Locally",2013 -221,VOC,voc,37.4219999,-122.0840575,Google,company,299b65d5d3914dad9aae2f936165dcebcf78db88,citation,http://doi.ieeecomputersociety.org/10.1109/ICCV.2015.203,Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation,2015 -222,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,cb5dcd048b0eaa78a887a014be26a8a7b1325d36,citation,https://arxiv.org/pdf/1709.04093.pdf,Joint Learning of Set Cardinality and State Distribution,2018 -223,VOC,voc,34.2469152,108.91061982,Northwestern Polytechnical University,edu,63660c50e2669a5115c2379e622549d8ed79be00,citation,http://porikli.com/mysite/pdfs/porikli%202017%20-%20Deep%20salient%20object%20detection%20by%20integrating%20multi-level%20cues.pdf,Deep Salient Object Detection by Integrating Multi-level Cues,2017 -224,VOC,voc,-35.2776999,149.118527,Australian National University,edu,63660c50e2669a5115c2379e622549d8ed79be00,citation,http://porikli.com/mysite/pdfs/porikli%202017%20-%20Deep%20salient%20object%20detection%20by%20integrating%20multi-level%20cues.pdf,Deep Salient Object Detection by Integrating Multi-level Cues,2017 -225,VOC,voc,48.14955455,11.56775314,Technical University Munich,edu,472541ccd941b9b4c52e1f088cc1152de9b3430f,citation,https://arxiv.org/pdf/1612.00197.pdf,Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses,2017 -226,VOC,voc,47.3764534,8.54770931,ETH Zürich,edu,9184b0c04013bfdfd82f4f271b5f017396c2f085,citation,https://pdfs.semanticscholar.org/9184/b0c04013bfdfd82f4f271b5f017396c2f085.pdf,Semantic Segmentation for Line Drawing Vectorization Using Neural Networks,2018 -227,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,57488aa24092fa7118aa5374c90b282a32473cf9,citation,https://arxiv.org/pdf/1807.01257.pdf,A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities,2018 -228,VOC,voc,39.9492344,-75.19198985,University of Pennsylvania,edu,57488aa24092fa7118aa5374c90b282a32473cf9,citation,https://arxiv.org/pdf/1807.01257.pdf,A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities,2018 -229,VOC,voc,32.0565957,118.77408833,Nanjing University,edu,7771807cd05f78a4591f2d0b094ddd3e0bd5339a,citation,https://arxiv.org/pdf/1707.06399.pdf,Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors,2017 -230,VOC,voc,50.7944026,-1.0971748,Cambridge University,edu,4558338873556d01fd290de6ddc55721c633a1ad,citation,http://pdfs.semanticscholar.org/4558/338873556d01fd290de6ddc55721c633a1ad.pdf,Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation,2016 -231,VOC,voc,42.3583961,-71.09567788,MIT,edu,85957b49896246bb416c0a182e52b355a8fa40b4,citation,https://arxiv.org/pdf/1806.03510.pdf,Feature Pyramid Network for Multi-Class Land Segmentation,2018 -232,VOC,voc,17.4454957,78.34854698,International Institute of Information Technology,edu,f5eb411217f729ad7ae84bfd4aeb3dedb850206a,citation,https://pdfs.semanticscholar.org/f5eb/411217f729ad7ae84bfd4aeb3dedb850206a.pdf,Tackling Low Resolution for Better Scene Understanding,2018 -233,VOC,voc,53.8338371,10.7035939,Institute of Systems and Robotics,edu,7fb8d9c36c23f274f2dd84945dd32ec2cc143de1,citation,http://pdfs.semanticscholar.org/8e44/ba779d7cdc23d597c2c6e4420129834e7e21.pdf,Semantic Segmentation with Second-Order Pooling,2012 -234,VOC,voc,50.7338124,7.1022465,University of Bonn,edu,7fb8d9c36c23f274f2dd84945dd32ec2cc143de1,citation,http://pdfs.semanticscholar.org/8e44/ba779d7cdc23d597c2c6e4420129834e7e21.pdf,Semantic Segmentation with Second-Order Pooling,2012 -235,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,b5e3beb791cc17cdaf131d5cca6ceb796226d832,citation,http://pdfs.semanticscholar.org/b5e3/beb791cc17cdaf131d5cca6ceb796226d832.pdf,Novel Dataset for Fine-Grained Image Categorization: Stanford Dogs,2012 -236,VOC,voc,39.94976005,116.33629046,Beijing Jiaotong University,edu,b5968e7bb23f5f03213178c22fd2e47af3afa04c,citation,https://arxiv.org/pdf/1705.07206.pdf,Multiple-Human Parsing in the Wild,2017 -237,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,b5968e7bb23f5f03213178c22fd2e47af3afa04c,citation,https://arxiv.org/pdf/1705.07206.pdf,Multiple-Human Parsing in the Wild,2017 -238,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,532c089b43983935e1001c5e35aa35440263beaf,citation,https://arxiv.org/pdf/1804.03166.pdf,G-Distillation: Reducing Overconfident Errors on Novel Samples,2018 -239,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,35fc0b28d0d674b28dd625d170bc641a36b17318,citation,http://pdfs.semanticscholar.org/35fc/0b28d0d674b28dd625d170bc641a36b17318.pdf,CSI: Composite Statistical Inference Techniques for Semantic Segmentation,2013 -240,VOC,voc,55.7039571,13.1902011,Lund University,edu,35fc0b28d0d674b28dd625d170bc641a36b17318,citation,http://pdfs.semanticscholar.org/35fc/0b28d0d674b28dd625d170bc641a36b17318.pdf,CSI: Composite Statistical Inference Techniques for Semantic Segmentation,2013 -241,VOC,voc,58.38131405,26.72078081,University of Tartu,edu,e4cb27d2a3e1153cb517d97d61de48ff0483c988,citation,https://pdfs.semanticscholar.org/e4cb/27d2a3e1153cb517d97d61de48ff0483c988.pdf,Viktoria Plemakova Vehicle Detection Based on Convolutional Neural Networks,2018 -242,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,3d0660e18c17db305b9764bb86b21a429241309e,citation,https://arxiv.org/pdf/1604.03505.pdf,Counting Everyday Objects in Everyday Scenes,2017 -243,VOC,voc,37.2381023,127.1903431,Myongji University,edu,a67da2dd79c01e8cc4029ecc5a05b97967403862,citation,https://pdfs.semanticscholar.org/a67d/a2dd79c01e8cc4029ecc5a05b97967403862.pdf,On Selecting Helpful Unlabeled Data for Improving Semi-Supervised Support Vector Machines,2014 -244,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,4ab69672e1116427d685bf7c1edb5b1fd0573b5e,citation,http://bigml.cs.tsinghua.edu.cn/~lingxi/PDFs/Xie_ACMMM12_EdgeGPP.pdf,Spatial pooling of heterogeneous features for image applications,2012 -245,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,989c7cdafa9b90ab2ea0a9d8fa60634cc698f174,citation,http://pdfs.semanticscholar.org/989c/7cdafa9b90ab2ea0a9d8fa60634cc698f174.pdf,YoloFlow Real - time Object Tracking in Video CS 229 Course Project,2016 -246,VOC,voc,3.12267405,101.65356103,University of Malaya,edu,85af6c005df806b57b306a732dcb98e096d15bfb,citation,https://arxiv.org/pdf/1805.11227.pdf,Getting to Know Low-light Images with The Exclusively Dark Dataset,2018 -247,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,cdb293381ff396d6e9c0f5e9578d411e759347fd,citation,https://pdfs.semanticscholar.org/022e/eae0edc09deb228da26d5390874f781ace0f.pdf,3 DR 2 N 2 : A Unified Approach for Single and Multiview 3 D Object Reconstruction,2016 -248,VOC,voc,51.7534538,-1.25400997,University of Oxford,edu,0e67717484684d90ae9d4e1bb9cdceb74b194910,citation,http://pdfs.semanticscholar.org/0e67/717484684d90ae9d4e1bb9cdceb74b194910.pdf,Mining Pixels: Weakly Supervised Semantic Segmentation Using Image Labels,2016 -249,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,5b4b84ce3518c8a14f57f5f95a1d07fb60e58223,citation,https://pdfs.semanticscholar.org/9f92/05a60ddf1135929e0747db34363b3a8c6bc8.pdf,Diagnosing Error in Object Detectors,2012 -250,VOC,voc,42.718568,-84.47791571,Michigan State University,edu,47203943c86e4d9355ffd99cd3d75f37211fd805,citation,http://pdfs.semanticscholar.org/be18/9c7066c4d99d617d137c975139c594ad09af.pdf,Semi-Crowdsourced Clustering: Generalizing Crowd Labeling by Robust Distance Metric Learning,2012 -251,VOC,voc,42.8298248,-73.87719385,GE Global Research Center,edu,47203943c86e4d9355ffd99cd3d75f37211fd805,citation,http://pdfs.semanticscholar.org/be18/9c7066c4d99d617d137c975139c594ad09af.pdf,Semi-Crowdsourced Clustering: Generalizing Crowd Labeling by Robust Distance Metric Learning,2012 -252,VOC,voc,39.95472495,-75.15346905,Temple University,edu,45ff38add61df32a027048624f58952a67a7c5f5,citation,http://pdfs.semanticscholar.org/45ff/38add61df32a027048624f58952a67a7c5f5.pdf,Deep Context Convolutional Neural Networks for Semantic Segmentation,2017 -253,VOC,voc,43.08250655,-77.67121663,Rochester Institute of Technology,edu,0a789733ccb300d0dd9df6174faaa7e8c64e0409,citation,http://pdfs.semanticscholar.org/0a78/9733ccb300d0dd9df6174faaa7e8c64e0409.pdf,High-Resolution Multispectral Dataset for Semantic Segmentation,2017 -254,VOC,voc,47.05821,15.46019568,Graz University of Technology,edu,9d3a6e459e0cecda20a8afd69d182877ff0224cf,citation,http://pdfs.semanticscholar.org/9d3a/6e459e0cecda20a8afd69d182877ff0224cf.pdf,A Framework for Articulated Hand Pose Estimation and Evaluation,2015 -255,VOC,voc,52.3553655,4.9501644,University of Amsterdam,edu,943a1e218b917172199e524944006aa349f58968,citation,https://arxiv.org/pdf/1807.11857.pdf,Joint Learning of Intrinsic Images and Semantic Segmentation,2018 -256,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,5f68e2131d9275d56092e9fca05bcfc65abea0d8,citation,http://doi.acm.org/10.1145/2806416.2806469,Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation,2015 -257,VOC,voc,40.9153196,-73.1270626,Stony Brook University,edu,f989a20fbcc2d576c0c4514a0e5085c741580778,citation,https://arxiv.org/pdf/1612.03236.pdf,Co-localization with Category-Consistent Features and Geodesic Distance Propagation,2017 -258,VOC,voc,42.36782045,-71.12666653,Harvard University,edu,f989a20fbcc2d576c0c4514a0e5085c741580778,citation,https://arxiv.org/pdf/1612.03236.pdf,Co-localization with Category-Consistent Features and Geodesic Distance Propagation,2017 -259,VOC,voc,24.7925484,120.9951183,National Tsing Hua University,edu,cf94200a476dc15d6da95db809349db4cfd8e92c,citation,https://arxiv.org/pdf/1807.11436.pdf,Leveraging Motion Priors in Videos for Improving Human Segmentation,2018 -260,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,25dba68e4db0ce361032126b91f734f9252cae7c,citation,https://arxiv.org/pdf/1611.08998.pdf,DeepSetNet: Predicting Sets with Deep Neural Networks,2017 -261,VOC,voc,59.34986645,18.07063213,"KTH Royal Institute of Technology, Stockholm",edu,883767948f535ea2bf8a0c03047ca9064e1b078f,citation,https://pdfs.semanticscholar.org/8837/67948f535ea2bf8a0c03047ca9064e1b078f.pdf,A Combination of Object Recognition and Localisation for an Autonomous Racecar,0 -262,VOC,voc,23.09461185,113.28788994,Sun Yat-Sen University,edu,18095a530b532a70f3b615fef2f59e6fdacb2d84,citation,https://arxiv.org/pdf/1604.02271v3.pdf,Deep Structured Scene Parsing by Learning with Image Descriptions,2016 -263,VOC,voc,45.7413921,126.62552755,Harbin Institute of Technology,edu,18095a530b532a70f3b615fef2f59e6fdacb2d84,citation,https://arxiv.org/pdf/1604.02271v3.pdf,Deep Structured Scene Parsing by Learning with Image Descriptions,2016 -264,VOC,voc,-27.47715625,153.02841004,Queensland University of Technology,edu,9397e7acd062245d37350f5c05faf56e9cfae0d6,citation,http://pdfs.semanticscholar.org/9397/e7acd062245d37350f5c05faf56e9cfae0d6.pdf,DeepFruits: A Fruit Detection System Using Deep Neural Networks,2016 -265,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,03a24d15533dae78de78fd9d5f6c9050fb97f186,citation,https://doi.org/10.1109/SSCI.2016.7850112,Pedestrian detection aided by scale-discriminative network,2016 -266,VOC,voc,-33.88890695,151.18943366,University of Sydney,edu,17d4fd92352baf6f0039ec64d43ca572c8252384,citation,https://arxiv.org/pdf/1806.07049.pdf,MoE-SPNet: A mixture-of-experts scene parsing network,2018 -267,VOC,voc,47.05821,15.46019568,Graz University of Technology,edu,30a29f6c407749e97bc7c2db5674a62773af9d27,citation,http://pdfs.semanticscholar.org/30a2/9f6c407749e97bc7c2db5674a62773af9d27.pdf,Tracking and Visual Quality Inspection in Harsh Environments (print-version),2012 -268,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,280d632ef3234c5ab06018c6eaccead75bc173b3,citation,http://pdfs.semanticscholar.org/6b1a/c8e438041ac02cc8fab5762ca069c386f473.pdf,Efficient Image and Video Co-localization with Frank-Wolfe Algorithm,2014 -269,VOC,voc,31.83907195,117.26420748,University of Science and Technology of China,edu,0f945f796a9343b51a3dc69941c0fa1a98c0f448,citation,http://pdfs.semanticscholar.org/a7ef/979ce52b9e4bcbd6ee5524dfd4e92baf6292.pdf,Local Hypersphere Coding Based on Edges between Visual Words,2012 -270,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,0db6a58927a671c01089c53248b0e1c36bdc3231,citation,http://openaccess.thecvf.com/content_cvpr_2016/papers/Pham_Efficient_Point_Process_CVPR_2016_paper.pdf,Efficient Point Process Inference for Large-Scale Object Detection,2016 -271,VOC,voc,42.2942142,-83.71003894,University of Michigan,edu,14d0afea52c4e9b7a488f6398e4a92bd4f4b93c7,citation,https://arxiv.org/pdf/1804.07667.pdf,Rethinking the Faster R-CNN Architecture for Temporal Action Localization,2018 -272,VOC,voc,42.2942142,-83.71003894,University of Michigan,edu,8da1b0834688edb311a803532e33939e9ecf8292,citation,https://arxiv.org/pdf/1808.01244.pdf,CornerNet: Detecting Objects as Paired Keypoints,2018 -273,VOC,voc,39.2899685,-76.62196103,University of Maryland,edu,f42d3225afd9e463ddb7a355f64b54af8bd14227,citation,https://arxiv.org/pdf/1804.10343.pdf,Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation,2018 -274,VOC,voc,31.83907195,117.26420748,University of Science and Technology of China,edu,a1dd88f44d045b360569a9a8721f728afbd951c3,citation,https://pdfs.semanticscholar.org/a1dd/88f44d045b360569a9a8721f728afbd951c3.pdf,Relief Impression Image Detection : Unsupervised Extracting Objects Directly From Feature Arrangements of Deep CNN,2016 -275,VOC,voc,34.0687788,-118.4450094,"University of California, Los Angeles",edu,fc027fccb19512a439fc17181c34ee1c3aad51b5,citation,https://arxiv.org/pdf/1708.03383.pdf,Joint Multi-person Pose Estimation and Semantic Part Segmentation,2017 -276,VOC,voc,39.329053,-76.619425,Johns Hopkins University,edu,377f2b65e6a9300448bdccf678cde59449ecd337,citation,https://arxiv.org/pdf/1804.10275.pdf,Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results,2018 -277,VOC,voc,40.47913175,-74.43168868,Rutgers University,edu,377f2b65e6a9300448bdccf678cde59449ecd337,citation,https://arxiv.org/pdf/1804.10275.pdf,Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results,2018 -278,VOC,voc,31.20081505,121.42840681,Shanghai Jiao Tong University,edu,451eed7fd8ae281d1cc76ca8cdecbaf47816e55a,citation,http://pdfs.semanticscholar.org/451e/ed7fd8ae281d1cc76ca8cdecbaf47816e55a.pdf,Close Yet Distinctive Domain Adaptation,2017 -279,VOC,voc,35.9990522,-78.9290629,Duke University,edu,992b93ab9d016640551a8cebcaf4757288154f32,citation,http://pdfs.semanticscholar.org/e38c/f96363aaf1f17c487c484ad27d3175ca4b31.pdf,Nested Pictorial Structures,2012 -280,VOC,voc,43.08250655,-77.67121663,Rochester Institute of Technology,edu,7489990ea3d6ab4c1c86c9ed9f049399961dfaef,citation,https://people.rit.edu/ndcsma/pubs/WNYISPW_Nov_2014_Chew.pdf,Normalized cutswith soft must-link constraints for image segmentation and clustering,2014 -281,VOC,voc,59.34986645,18.07063213,"KTH Royal Institute of Technology, Stockholm",edu,41199678ad9370ff8ca7e9e3c2617b62a297fac3,citation,http://pdfs.semanticscholar.org/4119/9678ad9370ff8ca7e9e3c2617b62a297fac3.pdf,Multitask Deep Learning models for real-time deployment in embedded systems,2017 -282,VOC,voc,39.7487516,30.47653071,Eskisehir Osmangazi University,edu,7fb74f5abab4830e3cdaf477230e5571d9e3ca57,citation,http://openaccess.thecvf.com/content_cvpr_2017/papers/Cevikalp_Polyhedral_Conic_Classifiers_CVPR_2017_paper.pdf,Polyhedral Conic Classifiers for Visual Object Detection and Classification,2017 -283,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,10793d1475607929fedc6d9a677911ad16843e58,citation,http://openaccess.thecvf.com/content_cvpr_2016/papers/Li_Unsupervised_Learning_of_CVPR_2016_paper.pdf,Unsupervised Learning of Edges,2016 -284,VOC,voc,31.30104395,121.50045497,Fudan University,edu,c94fd258a8f1e8f4033a7fe491f1372dcf7d3cd6,citation,https://arxiv.org/pdf/1807.04897.pdf,TS ^2 2 C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection,2018 -285,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,c94fd258a8f1e8f4033a7fe491f1372dcf7d3cd6,citation,https://arxiv.org/pdf/1807.04897.pdf,TS ^2 2 C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection,2018 -286,VOC,voc,52.5180641,13.3250425,TU Berlin,edu,2581a12189eb1a0b5b27a7fd1c2cbe44c88fcc20,citation,http://arxiv.org/pdf/1512.00172v1.pdf,Analyzing Classifiers: Fisher Vectors and Deep Neural Networks,2016 -287,VOC,voc,32.0565957,118.77408833,Nanjing University,edu,96416b1b44fb05302c6e9a8ab1b74d9204995e73,citation,http://pdfs.semanticscholar.org/9641/6b1b44fb05302c6e9a8ab1b74d9204995e73.pdf,Learning Effective Binary Visual Representations with Deep Networks,2018 -288,VOC,voc,42.3619407,-71.0904378,MIT CSAIL,edu,aa2ddae22760249729ac2c2c4e24c8b665bcd40e,citation,https://pdfs.semanticscholar.org/8c47/635ae7f1641c2bdd45026ad7dbff70c24398.pdf,Interpretable Basis Decomposition for Visual Explanation,2018 -289,VOC,voc,42.2942142,-83.71003894,University of Michigan,edu,60542b1a857024c79db8b5b03db6e79f74ec8f9f,citation,https://arxiv.org/pdf/1702.05448.pdf,Learning to Detect Human-Object Interactions,2018 -290,VOC,voc,36.3693473,120.673818,Shandong University,edu,bd8a85acaa45d4068fca584e8d9e3bd3bb4eea4d,citation,http://pdfs.semanticscholar.org/bd8a/85acaa45d4068fca584e8d9e3bd3bb4eea4d.pdf,Toward Scene Recognition by Discovering Semantic Structures and Parts,2015 -291,VOC,voc,49.2767454,-122.91777375,Simon Fraser University,edu,bd8a85acaa45d4068fca584e8d9e3bd3bb4eea4d,citation,http://pdfs.semanticscholar.org/bd8a/85acaa45d4068fca584e8d9e3bd3bb4eea4d.pdf,Toward Scene Recognition by Discovering Semantic Structures and Parts,2015 -292,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,456abee9c8d31f004b2f0a3b47222043e20f5042,citation,https://arxiv.org/pdf/1603.09188.pdf,Unsupervised Visual Sense Disambiguation for Verbs using Multimodal Embeddings,2016 -293,VOC,voc,31.83907195,117.26420748,University of Science and Technology of China,edu,7c2f6424b0bb2c28f282fbc0b4e98bf85d5584eb,citation,http://pdfs.semanticscholar.org/a5ae/7d662ed086bc5b0c9a2c1dc54fcb23635000.pdf,Relief R-CNN: Utilizing Convolutional Feature Interrelationship for Fast Object Detection Deployment,2016 -294,VOC,voc,22.53521465,113.9315911,Shenzhen University,edu,7c2f6424b0bb2c28f282fbc0b4e98bf85d5584eb,citation,http://pdfs.semanticscholar.org/a5ae/7d662ed086bc5b0c9a2c1dc54fcb23635000.pdf,Relief R-CNN: Utilizing Convolutional Feature Interrelationship for Fast Object Detection Deployment,2016 -295,VOC,voc,37.5557271,127.0436642,Hanyang University,edu,59e9934720baf3c5df3a0e1e988202856e1f83ce,citation,https://arxiv.org/pdf/1511.04136.pdf,UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking,2015 -296,VOC,voc,40.0141905,-83.0309143,University of Electronic Science and Technology of China,edu,d58c44bd9b464d9ac1db1344445c31364925f75a,citation,https://pdfs.semanticscholar.org/d58c/44bd9b464d9ac1db1344445c31364925f75a.pdf,TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights,2018 -297,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,81ba5202424906f64b77f68afca063658139fbb2,citation,https://arxiv.org/pdf/1611.09078.pdf,Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition,2017 -298,VOC,voc,46.109237,7.08453549,IDIAP Research Institute,edu,81ba5202424906f64b77f68afca063658139fbb2,citation,https://arxiv.org/pdf/1611.09078.pdf,Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition,2017 -299,VOC,voc,50.7338124,7.1022465,University of Bonn,edu,0b6f64c78c44dc043e2972fa7bfe2a5753768609,citation,https://doi.org/10.1109/ICPR.2016.7900008,A future for learning semantic models of man-made environments,2016 -300,VOC,voc,30.5097537,114.4062881,Huazhong University of Science and Technology,edu,016eb7b32d1fdec0899151fb03799378bf59bbe5,citation,http://pdfs.semanticscholar.org/016e/b7b32d1fdec0899151fb03799378bf59bbe5.pdf,Point Linking Network for Object Detection,2017 -301,VOC,voc,33.9928298,-81.02685168,University of South Carolina,edu,cd9d654c6a4250e0cf8bcfddc2afab9e70ee6cae,citation,http://pdfs.semanticscholar.org/cd9d/654c6a4250e0cf8bcfddc2afab9e70ee6cae.pdf,Object Detection with Mask-based Feature Encoding,2018 -302,VOC,voc,36.20304395,117.05842113,Tianjin University,edu,cd9d654c6a4250e0cf8bcfddc2afab9e70ee6cae,citation,http://pdfs.semanticscholar.org/cd9d/654c6a4250e0cf8bcfddc2afab9e70ee6cae.pdf,Object Detection with Mask-based Feature Encoding,2018 -303,VOC,voc,39.9601488,116.35193921,Beijing University of Posts and Telecommunications,edu,28737575297a20d431dd2b777a79a8be2c9c2bbd,citation,http://pdfs.semanticscholar.org/2873/7575297a20d431dd2b777a79a8be2c9c2bbd.pdf,Object Ranking on Deformable Part Models with Bagged LambdaMART,2014 -304,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,46702e0127e16a4d6a1feda3ffc5f0f123957e87,citation,https://arxiv.org/pdf/1809.06131.pdf,Revisit Multinomial Logistic Regression in Deep Learning: Data Dependent Model Initialization for Image Recognition,2018 -305,VOC,voc,34.0687788,-118.4450094,"University of California, Los Angeles",edu,d2b2cb1d5cc1aa30cf5be7bcb0494198934caabb,citation,http://pdfs.semanticscholar.org/d2b2/cb1d5cc1aa30cf5be7bcb0494198934caabb.pdf,A Restricted Visual Turing Test for Deep Scene and Event Understanding,2015 -306,VOC,voc,37.8687126,-122.25586815,"University of California, Berkeley",edu,446fbff6a2a7c9989b0a0465f960e236d9a5e886,citation,http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Pathak_Context_Encoders_Feature_CVPR_2016_paper.pdf,Context Encoders: Feature Learning by Inpainting,2016 -307,VOC,voc,51.49887085,-0.17560797,Imperial College London,edu,291e5377df2eec4835b5c6889896941831a11c69,citation,http://pdfs.semanticscholar.org/291e/5377df2eec4835b5c6889896941831a11c69.pdf,Recovering 6D Object Pose: Multi-modal Analyses on Challenges,2017 -308,VOC,voc,40.9153196,-73.1270626,Stony Brook University,edu,b69fbf046faf685655b5fa52fef07fb77e75eff4,citation,http://pdfs.semanticscholar.org/b69f/bf046faf685655b5fa52fef07fb77e75eff4.pdf,Modeling guidance and recognition in categorical search: bridging human and computer object detection.,2013 -309,VOC,voc,39.7487516,30.47653071,Eskisehir Osmangazi University,edu,13bda03fc8984d5943ed8d02e49a779d27c84114,citation,http://doi.ieeecomputersociety.org/10.1109/CVPR.2012.6248047,Efficient object detection using cascades of nearest convex model classifiers,2012 -310,VOC,voc,50.7338124,7.1022465,University of Bonn,edu,87a66ccc68374ffb704ee6fb9fa7df369718095c,citation,http://pdfs.semanticscholar.org/ea90/16fb585ba6449d3d6f98bf85fa0bcd1f4621.pdf,Multi-person Pose Estimation with Local Joint-to-Person Associations,2016 -311,VOC,voc,39.9922379,116.30393816,Peking University,edu,4960ab1cef23e5ccd60173725ea280f462164a0e,citation,https://pdfs.semanticscholar.org/4960/ab1cef23e5ccd60173725ea280f462164a0e.pdf,Video Object Segmentation by Learning Location-Sensitive Embeddings,2018 -312,VOC,voc,39.977217,116.337632,Microsoft Research Asia,company,4960ab1cef23e5ccd60173725ea280f462164a0e,citation,https://pdfs.semanticscholar.org/4960/ab1cef23e5ccd60173725ea280f462164a0e.pdf,Video Object Segmentation by Learning Location-Sensitive Embeddings,2018 -313,VOC,voc,35.9990522,-78.9290629,Duke University,edu,8856fbf333b2aba7b9f1f746e16a2b7f083ee5b8,citation,http://pdfs.semanticscholar.org/8856/fbf333b2aba7b9f1f746e16a2b7f083ee5b8.pdf,Analyzing animal behavior via classifying each video frame using convolutional neural networks,2015 -314,VOC,voc,34.1235825,108.83546,Xidian University,edu,f9f01af981f8d25f0c96ea06d88be62dabb79256,citation,https://pdfs.semanticscholar.org/f9f0/1af981f8d25f0c96ea06d88be62dabb79256.pdf,Terahertz Image Detection with the Improved Faster Region-Based Convolutional Neural Network,2018 -315,VOC,voc,37.5600406,126.9369248,Yonsei University,edu,09066d7d0bb6273bf996c8538d7b34c38ea6a500,citation,https://arxiv.org/pdf/1809.01845.pdf,"Yes, IoU loss is submodular - as a function of the mispredictions",2018 -316,VOC,voc,49.2579566,7.04577417,Max Planck Institute for Informatics,edu,4aeebd1c9b4b936ed2e4d988d8d28e27f129e6f1,citation,http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Chiu_See_the_Difference_ICCV_2015_paper.pdf,See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG,2015 -317,VOC,voc,34.0687788,-118.4450094,"University of California, Los Angeles",edu,232ff2dab49cb5a1dae1012fd7ba53382909ec18,citation,http://pdfs.semanticscholar.org/232f/f2dab49cb5a1dae1012fd7ba53382909ec18.pdf,Semantic Video Segmentation from Occlusion Relations within a Convex Optimization Framework,2013 -318,VOC,voc,50.13053055,8.69234224,University of Frankfurt,edu,465c34c3334f29de28f973b7702a235509649429,citation,http://pdfs.semanticscholar.org/465c/34c3334f29de28f973b7702a235509649429.pdf,Stereopsis via deep learning,2013 -319,VOC,voc,47.6543238,-122.30800894,University of Washington,edu,caa2ded6d8d5de97c824d29b0c7a18d220c596c8,citation,https://arxiv.org/pdf/1709.02554.pdf,Learning to Segment Breast Biopsy Whole Slide Images,2018 -320,VOC,voc,44.48116865,-73.2002179,University of Vermont,edu,caa2ded6d8d5de97c824d29b0c7a18d220c596c8,citation,https://arxiv.org/pdf/1709.02554.pdf,Learning to Segment Breast Biopsy Whole Slide Images,2018 -321,VOC,voc,42.2942142,-83.71003894,University of Michigan,edu,289d833a35c2156b7e332e67d1cb099fd0683025,citation,http://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Chao_HICO_A_Benchmark_ICCV_2015_paper.pdf,HICO: A Benchmark for Recognizing Human-Object Interactions in Images,2015 -322,VOC,voc,37.8687126,-122.25586815,"University of California, Berkeley",edu,0fbdd4b8eb9e4c4cfbe5b76ab29ab8b0219fbdc0,citation,https://people.eecs.berkeley.edu/~pathak/papers/iccv15.pdf,Constrained Convolutional Neural Networks for Weakly Supervised Segmentation,2015 -323,VOC,voc,39.9601488,116.35193921,Beijing University of Posts and Telecommunications,edu,f94f79168c1cfaebb8eab5151e01d56478ab0b73,citation,http://pdfs.semanticscholar.org/f94f/79168c1cfaebb8eab5151e01d56478ab0b73.pdf,Optimizing Region Selection for Weakly Supervised Object Detection,2017 -324,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,6bb51f431f348b2b3e1db859827e80f97a576c30,citation,http://pdfs.semanticscholar.org/6bb5/1f431f348b2b3e1db859827e80f97a576c30.pdf,Irregular Convolutional Neural Networks,2017 -325,VOC,voc,22.42031295,114.20788644,Chinese University of Hong Kong,edu,b78e611c32dc0daf762cfa93044558cdb545d857,citation,http://pdfs.semanticscholar.org/b78e/611c32dc0daf762cfa93044558cdb545d857.pdf,Temporal Action Detection with Structured Segment Networks Supplementary Materials,2017 -326,VOC,voc,48.14955455,11.56775314,Technical University Munich,edu,bc12715a1ddf1a540dab06bf3ac4f3a32a26b135,citation,http://pdfs.semanticscholar.org/bc12/715a1ddf1a540dab06bf3ac4f3a32a26b135.pdf,Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking,2017 -327,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,bc12715a1ddf1a540dab06bf3ac4f3a32a26b135,citation,http://pdfs.semanticscholar.org/bc12/715a1ddf1a540dab06bf3ac4f3a32a26b135.pdf,Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking,2017 -328,VOC,voc,31.20081505,121.42840681,Shanghai Jiao Tong University,edu,4d1757aacbc49c74a5d4e53259c92ab0e47544da,citation,https://arxiv.org/pdf/1805.04310.pdf,Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer,2018 -329,VOC,voc,36.1112058,140.1055176,University of Tsukuba,edu,d392098688a999c70589c995bd4427c212eff69d,citation,http://pdfs.semanticscholar.org/d392/098688a999c70589c995bd4427c212eff69d.pdf,Object Repositioning Based on the Perspective in a Single Image,2014 -330,VOC,voc,22.42031295,114.20788644,Chinese University of Hong Kong,edu,1c1f21bf136fe2eec412e5f70fd918c27c5ccb0a,citation,http://pdfs.semanticscholar.org/1c1f/21bf136fe2eec412e5f70fd918c27c5ccb0a.pdf,Object Detection and Viewpoint Estimation with Auto-masking Neural Network,2014 -331,VOC,voc,22.59805605,113.98533784,Shenzhen Institutes of Advanced Technology,edu,1c1f21bf136fe2eec412e5f70fd918c27c5ccb0a,citation,http://pdfs.semanticscholar.org/1c1f/21bf136fe2eec412e5f70fd918c27c5ccb0a.pdf,Object Detection and Viewpoint Estimation with Auto-masking Neural Network,2014 -332,VOC,voc,51.49887085,-0.17560797,Imperial College London,edu,72e9acdd64e71fc2084acaf177aafaa2e075bd8c,citation,http://pdfs.semanticscholar.org/72e9/acdd64e71fc2084acaf177aafaa2e075bd8c.pdf,The 2017 Hands in the Million Challenge on 3D Hand Pose Estimation,2017 -333,VOC,voc,51.49887085,-0.17560797,Imperial College London,edu,0209389b8369aaa2a08830ac3b2036d4901ba1f1,citation,https://arxiv.org/pdf/1612.01202v2.pdf,DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild,2017 -334,VOC,voc,51.5231607,-0.1282037,University College London,edu,0209389b8369aaa2a08830ac3b2036d4901ba1f1,citation,https://arxiv.org/pdf/1612.01202v2.pdf,DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild,2017 -335,VOC,voc,50.7338124,7.1022465,University of Bonn,edu,07b8a9a225b738c4074a50cf80ee5fe516878421,citation,https://arxiv.org/pdf/1807.09169.pdf,Convolutional Simplex Projection Network for Weakly Supervised Semantic Segmentation,2018 -336,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,1bd1645a629f1b612960ab9bba276afd4cf7c666,citation,http://arxiv.org/pdf/1506.04878.pdf,End-to-End People Detection in Crowded Scenes,2016 -337,VOC,voc,49.2579566,7.04577417,Max Planck Institute for Informatics,edu,1bd1645a629f1b612960ab9bba276afd4cf7c666,citation,http://arxiv.org/pdf/1506.04878.pdf,End-to-End People Detection in Crowded Scenes,2016 -338,VOC,voc,43.7776426,11.259765,University of Florence,edu,1bbe0371ca22c2fdb6e0d098049bbf6430324bdb,citation,http://doi.acm.org/10.1145/2906152,"Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval",2016 -339,VOC,voc,37.43131385,-122.16936535,Stanford University,edu,1bbe0371ca22c2fdb6e0d098049bbf6430324bdb,citation,http://doi.acm.org/10.1145/2906152,"Socializing the Semantic Gap: A Comparative Survey on Image Tag Assignment, Refinement and Retrieval",2016 -340,VOC,voc,34.7275714,135.2371,Kobe University,edu,9954f7ee5288724184f9420e39cca9165efa6822,citation,http://www.me.cs.scitec.kobe-u.ac.jp/~takigu/pdf/2015/Th5_4.pdf,Estimation of object functions using deformable part model,2015 -341,VOC,voc,48.14955455,11.56775314,Technical University Munich,edu,e212b2bc41645fe467a73d004067fcf1ca77d87f,citation,http://pdfs.semanticscholar.org/e212/b2bc41645fe467a73d004067fcf1ca77d87f.pdf,Deep Active Contours,2016 -342,VOC,voc,55.94951105,-3.19534913,University of Edinburgh,edu,51c4ecf4539f56c4b1035b890f743b3a91dd758b,citation,http://arxiv.org/abs/1504.06434,Situational object boundary detection,2015 -343,VOC,voc,37.8687126,-122.25586815,"University of California, Berkeley",edu,007e86cb55f0ba0415a7764a1e9f9566c1e8784b,citation,http://pdfs.semanticscholar.org/2677/3023b17ba560bad6a679930710a9049abca5.pdf,Adversarial Feature Learning,2016 -344,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,54d97ea9a5f92761dddd148fb0e602c2293e7c16,citation,https://pdfs.semanticscholar.org/54d9/7ea9a5f92761dddd148fb0e602c2293e7c16.pdf,Associating Inter-image Salient Instances for Weakly Supervised Semantic Segmentation,2018 -345,VOC,voc,51.4879961,-3.17969747,Cardiff University,edu,54d97ea9a5f92761dddd148fb0e602c2293e7c16,citation,https://pdfs.semanticscholar.org/54d9/7ea9a5f92761dddd148fb0e602c2293e7c16.pdf,Associating Inter-image Salient Instances for Weakly Supervised Semantic Segmentation,2018 -346,VOC,voc,51.5231607,-0.1282037,University College London,edu,0e923b74fd41f73f57e22f66397feeea67e834f0,citation,http://pdfs.semanticscholar.org/0e92/3b74fd41f73f57e22f66397feeea67e834f0.pdf,Invariant encoding schemes for visual recognition,2012 -347,VOC,voc,34.0224149,-118.28634407,University of Southern California,edu,93cba94ff0ff96f865ce24ea01e9c006369d75ff,citation,https://arxiv.org/pdf/1803.03879.pdf,Knowledge Aided Consistency for Weakly Supervised Phrase Grounding,2018 -348,VOC,voc,35.704514,51.40972058,Amirkabir University of Technology,edu,24fc311970e097efc317c0f98d2df37b828bfbad,citation,https://arxiv.org/pdf/1709.08019v2.pdf,Semi-supervised hierarchical semantic object parsing,2017 -349,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,5c4d4fd37e8c80ae95c00973531f34a6d810ea3a,citation,https://arxiv.org/pdf/1603.09439.pdf,The Open World of Micro-Videos,2016 -350,VOC,voc,37.26728,126.9841151,Seoul National University,edu,71b973c87965e4086e75fd2379dd1bd8e3f8231e,citation,https://arxiv.org/pdf/1606.02393.pdf,Progressive Attention Networks for Visual Attribute Prediction,2018 -351,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,20c02e98602f6adf1cebaba075d45cef50de089f,citation,https://arxiv.org/pdf/1808.07507.pdf,Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition,2018 -352,VOC,voc,33.776033,-84.39884086,Georgia Institute of Technology,edu,20c02e98602f6adf1cebaba075d45cef50de089f,citation,https://arxiv.org/pdf/1808.07507.pdf,Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition,2018 -353,VOC,voc,47.6543238,-122.30800894,University of Washington,edu,c17ed26650a67e80151f5312fa15b5c423acc797,citation,http://pdfs.semanticscholar.org/c17e/d26650a67e80151f5312fa15b5c423acc797.pdf,Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration,2017 -354,VOC,voc,36.05238585,140.11852361,Institute of Industrial Science,edu,c17ed26650a67e80151f5312fa15b5c423acc797,citation,http://pdfs.semanticscholar.org/c17e/d26650a67e80151f5312fa15b5c423acc797.pdf,Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration,2017 -355,VOC,voc,35.9020448,139.93622009,University of Tokyo,edu,c17ed26650a67e80151f5312fa15b5c423acc797,citation,http://pdfs.semanticscholar.org/c17e/d26650a67e80151f5312fa15b5c423acc797.pdf,Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration,2017 -356,VOC,voc,47.6423318,-122.1369302,Microsoft,company,c17ed26650a67e80151f5312fa15b5c423acc797,citation,http://pdfs.semanticscholar.org/c17e/d26650a67e80151f5312fa15b5c423acc797.pdf,Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration,2017 -357,VOC,voc,31.21051105,29.91314562,Alexandria University,edu,0ce08f1cc6684495d12c2da157a056c7b88ffcd9,citation,http://pdfs.semanticscholar.org/0ce0/8f1cc6684495d12c2da157a056c7b88ffcd9.pdf,Multi-Modality Feature Transform: An Interactive Image Segmentation Approach,2015 -358,VOC,voc,1.3484104,103.68297965,Nanyang Technological University,edu,567078a51ea63b70396dca5dabb50a10a736d991,citation,https://pdfs.semanticscholar.org/1b5a/3bdb174df1ff36c1c101739d6daaec07760d.pdf,Conditional Generative Adversarial Network for Structured Domain Adaptation,2018 -359,VOC,voc,43.0008093,-78.7889697,University at Buffalo,edu,567078a51ea63b70396dca5dabb50a10a736d991,citation,https://pdfs.semanticscholar.org/1b5a/3bdb174df1ff36c1c101739d6daaec07760d.pdf,Conditional Generative Adversarial Network for Structured Domain Adaptation,2018 -360,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,6e4e5ef25f657de8fb383c8dfeb8e229eea28bb9,citation,https://arxiv.org/pdf/1707.01691.pdf,RON: Reverse Connection with Objectness Prior Networks for Object Detection,2017 -361,VOC,voc,50.0764296,14.41802312,Czech Technical University,edu,cf528f9fe6588b71efa94c219979ce111fc9c1c9,citation,http://pdfs.semanticscholar.org/cf52/8f9fe6588b71efa94c219979ce111fc9c1c9.pdf,On Evaluation of 6D Object Pose Estimation,2016 -362,VOC,voc,22.2081469,114.25964115,University of Hong Kong,edu,3b67645cd512898806aaf1df1811035f2d957f6b,citation,https://arxiv.org/pdf/1705.04043.pdf,SCNet: Learning Semantic Correspondence,2017 -363,VOC,voc,26.513188,80.23651945,Indian Institute of Technology Kanpur,edu,ef2e36daf429899bb48d80ce6804731c3f99bb85,citation,http://pdfs.semanticscholar.org/f7bd/b4df0fb5b3ff9fa0ebfe7c2a9ddc34c09a5c.pdf,"Debnath, Banerjee, Namboodiri: Adapting Ransac-svm to Detect Outliers for Robust Classification",2015 -364,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,79a3a07661b8c6a36070fd767344e15c847a30ef,citation,http://pdfs.semanticscholar.org/79a3/a07661b8c6a36070fd767344e15c847a30ef.pdf,Contextual Pooling in Image Classification,2012 -365,VOC,voc,13.0222347,77.56718325,Indian Institute of Science Bangalore,edu,5aa7f33cdc00787284b609aa63f5eb5c0a3212f6,citation,http://pdfs.semanticscholar.org/5aa7/f33cdc00787284b609aa63f5eb5c0a3212f6.pdf,Multiplicative mixing of object identity and image attributes in single inferior temporal neurons,2018 -366,VOC,voc,51.5247272,-0.03931035,Queen Mary University of London,edu,38f88655debf4bf32978a7b39fbd56aea6ee5752,citation,https://arxiv.org/pdf/1712.03162.pdf,Class Rectification Hard Mining for Imbalanced Deep Learning,2017 -367,VOC,voc,36.1244756,-97.05004383,Oklahoma State University,edu,7b3b2912c1d7a70839bc71a150e33f8634d0fff3,citation,https://pdfs.semanticscholar.org/7b3b/2912c1d7a70839bc71a150e33f8634d0fff3.pdf,Convolutional Neural Network-Based Embarrassing Situation Detection under Camera for Social Robot in Smart Homes,2018 -368,VOC,voc,40.00229045,116.32098908,Tsinghua University,edu,acdc333f7b32d987e65ce15f21db64e850ca9471,citation,https://pdfs.semanticscholar.org/acdc/333f7b32d987e65ce15f21db64e850ca9471.pdf,Direct Loss Minimization for Training Deep Neural Nets,2015 -369,VOC,voc,43.66333345,-79.39769975,University of Toronto,edu,acdc333f7b32d987e65ce15f21db64e850ca9471,citation,https://pdfs.semanticscholar.org/acdc/333f7b32d987e65ce15f21db64e850ca9471.pdf,Direct Loss Minimization for Training Deep Neural Nets,2015 -370,VOC,voc,28.2290209,112.99483204,"National University of Defense Technology, China",edu,da4137396f26bf3e76d04eeed0c94e11b7824aa6,citation,https://arxiv.org/pdf/1711.06828.pdf,Transferable Semi-Supervised Semantic Segmentation,2018 -371,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,da4137396f26bf3e76d04eeed0c94e11b7824aa6,citation,https://arxiv.org/pdf/1711.06828.pdf,Transferable Semi-Supervised Semantic Segmentation,2018 -372,VOC,voc,40.11571585,-88.22750772,Beckman Institute,edu,da4137396f26bf3e76d04eeed0c94e11b7824aa6,citation,https://arxiv.org/pdf/1711.06828.pdf,Transferable Semi-Supervised Semantic Segmentation,2018 -373,VOC,voc,40.9153196,-73.1270626,Stony Brook University,edu,5240941af3b263609acaa168f96e1decdb0b3fe4,citation,http://www.cv-foundation.org/openaccess/content_cvpr_workshops_2015/W06/papers/Ge_Action_Classification_in_2015_CVPR_paper.pdf,Action classification in still images using human eye movements,2015 -374,VOC,voc,43.66333345,-79.39769975,University of Toronto,edu,126250d6077a6a68ae06277352eb42c4fa4c8b10,citation,http://pdfs.semanticscholar.org/1262/50d6077a6a68ae06277352eb42c4fa4c8b10.pdf,Learning Patch-based Structural Element Models with Hierarchical Palettes Abstract Learning Patch-based Structural Element Models with Hierarchical Palettes,2012 -375,VOC,voc,40.11116745,-88.22587665,"University of Illinois, Urbana-Champaign",edu,0cbbbfac2fe925479c6b34712e056f840a10fa4d,citation,https://pdfs.semanticscholar.org/0cbb/bfac2fe925479c6b34712e056f840a10fa4d.pdf,Quality Evaluation Methods for Crowdsourced Image Segmentation,2018 -376,VOC,voc,37.3936717,-122.0807262,Facebook,company,0cbbbfac2fe925479c6b34712e056f840a10fa4d,citation,https://pdfs.semanticscholar.org/0cbb/bfac2fe925479c6b34712e056f840a10fa4d.pdf,Quality Evaluation Methods for Crowdsourced Image Segmentation,2018 -377,VOC,voc,42.718568,-84.47791571,Michigan State University,edu,28df3f11894ce0c48dd8aee65a6ec76d9009cbbd,citation,https://arxiv.org/pdf/1809.08318.pdf,Recurrent Flow-Guided Semantic Forecasting,2018 -378,VOC,voc,42.30791465,-83.07176915,University of Windsor,edu,535ed3850e79ccd51922601546ef0fc48c5fb468,citation,http://arxiv.org/abs/1705.04301,A feature embedding strategy for high-level CNN representations from multiple convnets,2017 -379,VOC,voc,30.19331415,120.11930822,Zhejiang University,edu,535ed3850e79ccd51922601546ef0fc48c5fb468,citation,http://arxiv.org/abs/1705.04301,A feature embedding strategy for high-level CNN representations from multiple convnets,2017 -380,VOC,voc,-34.9189226,138.60423668,University of Adelaide,edu,247ca98c5a46616044cf6ae32b0d5b4140a7a161,citation,http://pdfs.semanticscholar.org/247c/a98c5a46616044cf6ae32b0d5b4140a7a161.pdf,High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks,2016 -381,VOC,voc,28.2290209,112.99483204,"National University of Defense Technology, China",edu,5f771fed91c8e4b666489ba2384d0705bcf75030,citation,https://arxiv.org/pdf/1804.03287.pdf,Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing,2018 -382,VOC,voc,1.2962018,103.77689944,National University of Singapore,edu,5f771fed91c8e4b666489ba2384d0705bcf75030,citation,https://arxiv.org/pdf/1804.03287.pdf,Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing,2018 -383,VOC,voc,51.6091578,-3.97934429,Swansea University,edu,d115c4a66d765fef596b0b171febca334cea15b5,citation,http://pdfs.semanticscholar.org/d115/c4a66d765fef596b0b171febca334cea15b5.pdf,Combining Stacked Denoising Autoencoders and Random Forests for Face Detection,2016 -384,VOC,voc,39.2899685,-76.62196103,University of Maryland,edu,e20ab84ac7fa0a5d36d4cf2266b7065c60e1c804,citation,https://pdfs.semanticscholar.org/e20a/b84ac7fa0a5d36d4cf2266b7065c60e1c804.pdf,Stacked U-Nets for Ground Material Segmentation in Remote Sensing Imagery,0 -385,VOC,voc,22.3386304,114.2620337,Hong Kong University of Science and Technology,edu,a1fdf45e6649b0020eb533c70d6062b9183561ff,citation,https://arxiv.org/pdf/1802.07931.pdf,Where's YOUR focus: Personalized Attention,2017 -386,VOC,voc,36.05238585,140.11852361,National Institute of Advanced Industrial Science and Technology,edu,775c51b965e8ff37646a265aab64136b4a620526,citation,http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2A_059_ext.pdf,Three viewpoints toward exemplar SVM,2015 -387,VOC,voc,28.59899755,-81.19712501,University of Central Florida,edu,0688c0568f3ab418719260d443cc0d86c3af2914,citation,https://arxiv.org/pdf/1707.09465.pdf,Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes,2017 -388,VOC,voc,37.4102193,-122.05965487,Carnegie Mellon University,edu,5d92531e74c4c2cdce91fdcd3c7ff090c8c29504,citation,http://pdfs.semanticscholar.org/5d92/531e74c4c2cdce91fdcd3c7ff090c8c29504.pdf,Synthesizing Scenes for Instance Detection,2017 -389,VOC,voc,58.38131405,26.72078081,University of Tartu,edu,c919a9f61656cdcd3a26076057ee006c48e8f609,citation,https://pdfs.semanticscholar.org/c919/a9f61656cdcd3a26076057ee006c48e8f609.pdf,High-Value Target Detection,2018 -390,VOC,voc,39.9082804,116.2458527,University of Chinese Academy of Sciences,edu,c6ce8eb37dafed09e1c55735fd1f1e9dc9c6bfe2,citation,https://arxiv.org/pdf/1707.07584.pdf,Joint background reconstruction and foreground segmentation via a two-stage convolutional neural network,2017 -391,VOC,voc,40.0044795,116.370238,Chinese Academy of Sciences,edu,c6ce8eb37dafed09e1c55735fd1f1e9dc9c6bfe2,citation,https://arxiv.org/pdf/1707.07584.pdf,Joint background reconstruction and foreground segmentation via a two-stage convolutional neural network,2017 -392,VOC,voc,55.7039571,13.1902011,Lund University,edu,c0006a2268d299644e9f1b455601bcbe89ddc2b5,citation,https://arxiv.org/pdf/1612.08871.pdf,Semantic Video Segmentation by Gated Recurrent Flow Propagation,2016 -393,VOC,voc,34.13710185,-118.12527487,California Institute of Technology,edu,273b9b7c63ac9196fb12734b49b74d0523ca4df4,citation,https://arxiv.org/pdf/1406.2807v2.pdf,The Secrets of Salient Object Segmentation,2014 -394,VOC,voc,34.0687788,-118.4450094,"University of California, Los Angeles",edu,273b9b7c63ac9196fb12734b49b74d0523ca4df4,citation,https://arxiv.org/pdf/1406.2807v2.pdf,The Secrets of Salient Object Segmentation,2014 -395,VOC,voc,33.59914655,130.22359848,Kyushu University,edu,e771661fa441f008c111ea786eb275153919da6e,citation,http://pdfs.semanticscholar.org/e771/661fa441f008c111ea786eb275153919da6e.pdf,Globally Optimal Object Tracking with Fully Convolutional Networks,2016 -396,VOC,voc,41.5007811,2.11143663,Universitat Autònoma de Barcelona,edu,5feacd9dd73827fb438a6bf6c8b406f4f11aa2fa,citation,http://pdfs.semanticscholar.org/5fea/cd9dd73827fb438a6bf6c8b406f4f11aa2fa.pdf,Slanted Stixels: Representing San Francisco's Steepest Streets,2017 -397,VOC,voc,47.3764534,8.54770931,ETH Zürich,edu,5feacd9dd73827fb438a6bf6c8b406f4f11aa2fa,citation,http://pdfs.semanticscholar.org/5fea/cd9dd73827fb438a6bf6c8b406f4f11aa2fa.pdf,Slanted Stixels: Representing San Francisco's Steepest Streets,2017 |