{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"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":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"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":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"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":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"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":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"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":"2012.10071","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","created":"2020-12-18","cited_by_count":183},{"id":"1908.02486","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","created":"2019-08-07","cited_by_count":142},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"1611.02155","title":"Spatiotemporal Residual Networks for Video Action Recognition","created":"2016-11-07","cited_by_count":91},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84},{"id":"2012.06399","title":"Spatial Temporal Transformer Network for Skeleton-based Action Recognition","created":"2020-12-11","cited_by_count":77},{"id":"2103.07372","title":"ACTION-Net: Multipath Excitation for Action Recognition","created":"2021-03-11","cited_by_count":63},{"id":"1906.05571","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","created":"2019-06-13","cited_by_count":61},{"id":"1912.00998","title":"A Multigrid Method for Efficiently Training Video Models","created":"2019-12-02","cited_by_count":52},{"id":"2010.11757","title":"Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition","created":"2020-10-22","cited_by_count":45},{"id":"2101.03904","title":"Trear: Transformer-based RGB-D Egocentric Action Recognition","created":"2021-01-05","cited_by_count":39},{"id":"1804.08254","title":"Memory Attention Networks for Skeleton-based Action Recognition","created":"2018-04-23","cited_by_count":36},{"id":"2102.07092","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","created":"2021-02-14","cited_by_count":31},{"id":"2108.03267","title":"BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation","created":"2021-08-06","cited_by_count":31},{"id":"2006.16479","title":"MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos","created":"2020-06-30","cited_by_count":25},{"id":"2103.15395","title":"No frame left behind: Full Video Action Recognition","created":"2021-03-29","cited_by_count":24},{"id":"1908.09995","title":"Temporal Reasoning Graph for Activity Recognition","created":"2019-08-27","cited_by_count":22},{"id":"1704.03593","title":"Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation","created":"2017-04-12","cited_by_count":16},{"id":"1811.11082","title":"Automatic Face Aging in Videos via Deep Reinforcement Learning","created":"2018-11-27","cited_by_count":16},{"id":"1703.08617","title":"Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition","created":"2017-03-24","cited_by_count":15},{"id":"2008.03462","title":"PAN: Towards Fast Action Recognition via Learning Persistence of Appearance","created":"2020-08-08","cited_by_count":12},{"id":"1606.02254","title":"Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines","created":"2016-06-07","cited_by_count":10},{"id":"1905.10170","title":"Fast Flow Reconstruction via Robust Invertible nxn Convolution","created":"2019-05-24","cited_by_count":6},{"id":"1607.06871","title":"Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modeling","created":"2016-07-23","cited_by_count":5}],"next_cursor":null}