{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"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":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2109.01847","title":"Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering","created":"2021-09-04","cited_by_count":228},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1511.07571","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","created":"2015-11-24","cited_by_count":176},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"2010.07548","title":"MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking","created":"2020-10-15","cited_by_count":136},{"id":"2104.04691","title":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","created":"2021-04-10","cited_by_count":133},{"id":"1811.12814","title":"Graph-Based Global Reasoning Networks","created":"2018-11-30","cited_by_count":120},{"id":"2008.11714","title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","created":"2020-08-26","cited_by_count":117},{"id":"1902.03748","title":"Peeking into the Future: Predicting Future Person Activities and Locations in Videos","created":"2019-02-11","cited_by_count":114},{"id":"1912.09930","title":"Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks","created":"2019-12-20","cited_by_count":114},{"id":"1906.11883","title":"Unsupervised Learning of Object Keypoints for Perception and Control","created":"2019-06-19","cited_by_count":109},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"1805.00833","title":"Learnable PINs: Cross-Modal Embeddings for Person Identity","created":"2018-05-02","cited_by_count":60},{"id":"1912.07414","title":"Learning Canonical Representations for Scene Graph to Image Generation","created":"2019-12-16","cited_by_count":60},{"id":"1811.11155","title":"FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery","created":"2018-11-27","cited_by_count":58},{"id":"2004.00542","title":"Future Video Synthesis with Object Motion Prediction","created":"2020-04-01","cited_by_count":57},{"id":"1708.04225","title":"Deep Object-Centric Representations for Generalizable Robot Learning","created":"2017-08-14","cited_by_count":50},{"id":"1904.03177","title":"Structured agents for physical construction","created":"2019-04-05","cited_by_count":50},{"id":"1802.05451","title":"Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction","created":"2018-02-15","cited_by_count":44},{"id":"1812.03544","title":"A Structured Model For Action Detection","created":"2018-12-09","cited_by_count":43},{"id":"1908.08522","title":"Compositional Video Prediction","created":"2019-08-22","cited_by_count":43},{"id":"1802.10217","title":"Investigating Human Priors for Playing Video Games","created":"2018-02-28","cited_by_count":39},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"1711.06330","title":"Attend and Interact: Higher-Order Object Interactions for Video Understanding","created":"2017-11-16","cited_by_count":37},{"id":"1706.00932","title":"See, Hear, and Read: Deep Aligned Representations","created":"2017-06-03","cited_by_count":32},{"id":"2007.06705","title":"Unsupervised object-centric video generation and decomposition in 3D","created":"2020-07-07","cited_by_count":31},{"id":"1803.10362","title":"Referring Relationships","created":"2018-03-28","cited_by_count":29},{"id":"1910.03568","title":"Object-centric Forward Modeling for Model Predictive Control","created":"2019-10-08","cited_by_count":19},{"id":"2111.01936","title":"Revisiting spatio-temporal layouts for compositional action recognition","created":"2021-11-02","cited_by_count":19},{"id":"2012.05689","title":"Interactive Fusion of Multi-level Features for Compositional Activity Recognition","created":"2020-12-10","cited_by_count":9},{"id":"2004.00180","title":"Spatio-Temporal Action Detection with Multi-Object Interaction","created":"2020-04-01","cited_by_count":4}],"next_cursor":null}