{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1904.00607","title":"Video Object Segmentation using Space-Time Memory Networks","created":"2019-04-01","cited_by_count":438},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"1905.00413","title":"Pushing the Boundaries of View Extrapolation with Multiplane Images","created":"2019-05-01","cited_by_count":191},{"id":"1902.09513","title":"FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation","created":"2019-02-25","cited_by_count":178},{"id":"1806.09594","title":"Tracking Emerges by Colorizing Videos","created":"2018-06-25","cited_by_count":166},{"id":"2001.06810","title":"See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks","created":"2020-01-19","cited_by_count":138},{"id":"1904.09117","title":"SelFlow: Self-Supervised Learning of Optical Flow","created":"2019-04-19","cited_by_count":128},{"id":"2003.13045","title":"Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation","created":"2020-03-29","cited_by_count":120},{"id":"1812.00467","title":"\"Double-DIP\": Unsupervised Image Decomposition via Coupled Deep-Image-Priors","created":"2018-12-02","cited_by_count":114},{"id":"1706.09364","title":"Online Adaptation of Convolutional Neural Networks for Video Object Segmentation","created":"2017-06-28","cited_by_count":109},{"id":"2002.07793","title":"MAST: A Memory-Augmented Self-supervised Tracker","created":"2020-02-18","cited_by_count":109},{"id":"1709.06031","title":"Video Object Segmentation Without Temporal Information","created":"2017-09-18","cited_by_count":93},{"id":"1709.06750","title":"SegFlow: Joint Learning for Video Object Segmentation and Optical Flow","created":"2017-09-20","cited_by_count":92},{"id":"1904.03597","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","created":"2019-04-07","cited_by_count":92},{"id":"2001.06807","title":"Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks","created":"2020-01-19","cited_by_count":84},{"id":"1701.05384","title":"FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos","created":"2017-01-19","cited_by_count":77},{"id":"1907.02499","title":"Sim2real transfer learning for 3D human pose estimation: motion to the rescue","created":"2019-07-04","cited_by_count":76},{"id":"1901.03360","title":"Unsupervised Moving Object Detection via Contextual Information Separation","created":"2019-01-10","cited_by_count":72},{"id":"1604.00136","title":"It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos","created":"2016-04-01","cited_by_count":71},{"id":"2011.11630","title":"Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation","created":"2020-11-23","cited_by_count":62},{"id":"2008.11516","title":"Making a Case for 3D Convolutions for Object Segmentation in Videos","created":"2020-08-26","cited_by_count":56},{"id":"1612.07217","title":"Learning Motion Patterns in Videos","created":"2016-12-21","cited_by_count":53},{"id":"1902.03715","title":"Towards Segmenting Anything That Moves","created":"2019-02-11","cited_by_count":51},{"id":"2009.07833","title":"Layered Neural Rendering for Retiming People in Video","created":"2020-09-16","cited_by_count":51},{"id":"1910.10895","title":"Anchor Diffusion for Unsupervised Video Object Segmentation","created":"2019-10-24","cited_by_count":50},{"id":"2003.05020","title":"Learning Video Object Segmentation from Unlabeled Videos","created":"2020-03-10","cited_by_count":42},{"id":"1712.01127","title":"Learning to Segment Moving Objects","created":"2017-12-01","cited_by_count":39},{"id":"1812.02772","title":"Object Discovery in Videos as Foreground Motion Clustering","created":"2018-12-06","cited_by_count":32},{"id":"1812.01461","title":"The Visual Centrifuge: Model-Free Layered Video Representations","created":"2018-12-04","cited_by_count":23},{"id":"1807.05636","title":"Cross Pixel Optical Flow Similarity for Self-Supervised Learning","created":"2018-07-15","cited_by_count":21},{"id":"1910.11306","title":"Controllable Attention for Structured Layered Video Decomposition","created":"2019-10-24","cited_by_count":7},{"id":"1610.10033","title":"A Detailed Rubric for Motion Segmentation","created":"2016-10-31","cited_by_count":6}],"next_cursor":null}