{"list":"other","total":69,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"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":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"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":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"id":"1807.10982","title":"Actor-Centric Relation Network","created":"2018-07-28","cited_by_count":87},{"id":"1604.04494","title":"Long-term Temporal Convolutions for Action Recognition","created":"2016-04-15","cited_by_count":84},{"id":"2003.12737","title":"Actor-Transformers for Group Activity Recognition","created":"2020-03-28","cited_by_count":84},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"1705.01861","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","created":"2017-05-04","cited_by_count":77},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"2004.07485","title":"Asynchronous Interaction Aggregation for Action Detection","created":"2020-04-16","cited_by_count":65},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64},{"id":"1911.06644","title":"You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization","created":"2019-11-15","cited_by_count":59},{"id":"1611.08563","title":"Online Real-time Multiple Spatiotemporal Action Localisation and Prediction","created":"2016-11-25","cited_by_count":57},{"id":"2001.04608","title":"Actions as Moving Points","created":"2020-01-14","cited_by_count":55},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"id":"1910.07721","title":"Deep Contextual Attention for Human-Object Interaction Detection","created":"2019-10-17","cited_by_count":54},{"id":"1904.09288","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","created":"2019-04-19","cited_by_count":51},{"id":"1703.10664","title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","created":"2017-03-30","cited_by_count":50},{"id":"2010.10001","title":"Contextual Heterogeneous Graph Network for Human-Object Interaction Detection","created":"2020-10-20","cited_by_count":50},{"id":"1506.01929","title":"Learning to track for spatio-temporal action localization","created":"2015-06-05","cited_by_count":44},{"id":"1812.03544","title":"A Structured Model For Action Detection","created":"2018-12-09","cited_by_count":43},{"id":"1806.07754","title":"Spatio-Temporal Channel Correlation Networks for Action Classification","created":"2018-06-19","cited_by_count":38},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"1608.01529","title":"Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos","created":"2016-08-04","cited_by_count":35},{"id":"2210.12686","title":"Holistic Interaction Transformer Network for Action Detection","created":"2022-10-23","cited_by_count":28},{"id":"1807.10066","title":"A Better Baseline for AVA","created":"2018-07-26","cited_by_count":16},{"id":"1604.07279","title":"Actionness Estimation Using Hybrid Fully Convolutional Networks","created":"2016-04-25","cited_by_count":15},{"id":"1812.11631","title":"Actor Conditioned Attention Maps for Video Action Detection","created":"2018-12-30","cited_by_count":15},{"id":"2008.13196","title":"Finding Action Tubes with a Sparse-to-Dense Framework","created":"2020-08-30","cited_by_count":4}],"next_cursor":null}