{"list":"other","total":67,"rows":[{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"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":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2004.01398","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","created":"2020-04-03","cited_by_count":165},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"1908.02486","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","created":"2019-08-07","cited_by_count":142},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"1811.12432","title":"AdaFrame: Adaptive Frame Selection for Fast Video Recognition","created":"2018-11-29","cited_by_count":134},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"2010.08001","title":"Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness","created":"2020-10-15","cited_by_count":121},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"2010.10864","title":"A Short Note on the Kinetics-700-2020 Human Action Dataset","created":"2020-10-21","cited_by_count":92},{"id":"1611.02155","title":"Spatiotemporal Residual Networks for Video Action Recognition","created":"2016-11-07","cited_by_count":91},{"id":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"id":"2007.15796","title":"AR-Net: Adaptive Frame Resolution for Efficient Action Recognition","created":"2020-07-31","cited_by_count":88},{"id":"1711.11152","title":"Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition","created":"2017-11-29","cited_by_count":82},{"id":"1912.00381","title":"Gate-Shift Networks for Video Action Recognition","created":"2019-12-01","cited_by_count":76},{"id":"1704.02895","title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","created":"2017-04-10","cited_by_count":73},{"id":"1906.03349","title":"Video Modeling with Correlation Networks","created":"2019-06-07","cited_by_count":73},{"id":"2007.09933","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","created":"2020-07-20","cited_by_count":72},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"1912.01601","title":"LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition","created":"2019-12-03","cited_by_count":65},{"id":"1912.00869","title":"More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation","created":"2019-12-02","cited_by_count":64},{"id":"1607.01794","title":"VideoLSTM Convolves, Attends and Flows for Action Recognition","created":"2016-07-06","cited_by_count":60},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"id":"1905.05143","title":"VideoGraph: Recognizing Minutes-Long Human Activities in Videos","created":"2019-05-13","cited_by_count":57},{"id":"1909.13130","title":"Grouped Spatial-Temporal Aggregation for Efficient Action Recognition","created":"2019-09-28","cited_by_count":55},{"id":"1711.01467","title":"Attentional Pooling for Action Recognition","created":"2017-11-04","cited_by_count":54},{"id":"1810.01455","title":"Representation Flow for Action Recognition","created":"2018-10-02","cited_by_count":51},{"id":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48},{"id":"1905.13209","title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","created":"2019-05-30","cited_by_count":46},{"id":"1804.00413","title":"End-to-End Learning of Motion Representation for Video Understanding","created":"2018-04-02","cited_by_count":43},{"id":"1510.00562","title":"Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks","created":"2015-10-02","cited_by_count":40},{"id":"1901.03460","title":"DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition","created":"2019-01-11","cited_by_count":36},{"id":"2012.06977","title":"MVFNet: Multi-View Fusion Network for Efficient Video Recognition","created":"2020-12-13","cited_by_count":36},{"id":"1807.10037","title":"Motion Feature Network: Fixed Motion Filter for Action Recognition","created":"2018-07-26","cited_by_count":34},{"id":"1807.11195","title":"Multi-Fiber Networks for Video Recognition","created":"2018-07-30","cited_by_count":34},{"id":"2002.07442","title":"V4D:4D Convolutional Neural Networks for Video-level Representation Learning","created":"2020-02-18","cited_by_count":33},{"id":"2008.08072","title":"AssembleNet++: Assembling Modality Representations via Attention Connections","created":"2020-08-18","cited_by_count":28},{"id":"1902.10640","title":"Efficient Video Classification Using Fewer Frames","created":"2019-02-27","cited_by_count":26},{"id":"2106.01603","title":"CT-Net: Channel Tensorization Network for Video Classification","created":"2021-06-03","cited_by_count":26},{"id":"1903.01197","title":"Collaborative Spatio-temporal Feature Learning for Video Action Recognition","created":"2019-03-04","cited_by_count":24},{"id":"2007.12034","title":"AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification","created":"2020-07-23","cited_by_count":23},{"id":"1902.01078","title":"Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions","created":"2019-02-04","cited_by_count":20},{"id":"1908.07625","title":"Action recognition with spatial-temporal discriminative filter banks","created":"2019-08-20","cited_by_count":15},{"id":"2007.11040","title":"Directional Temporal Modeling for Action Recognition","created":"2020-07-21","cited_by_count":14},{"id":"2007.12887","title":"Approximated Bilinear Modules for Temporal Modeling","created":"2020-07-25","cited_by_count":8}],"next_cursor":null}