{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1703.08448","title":"Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach","created":"2017-03-24","cited_by_count":201},{"id":"2004.01398","title":"TEA: Temporal Excitation and Aggregation for Action Recognition","created":"2020-04-03","cited_by_count":165},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"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":"1704.00138","title":"Multiple Instance Detection Network with Online Instance Classifier Refinement","created":"2017-04-01","cited_by_count":117},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"2010.05300","title":"Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification","created":"2020-10-11","cited_by_count":100},{"id":"2007.15796","title":"AR-Net: Adaptive Frame Resolution for Efficient Action Recognition","created":"2020-07-31","cited_by_count":88},{"id":"1811.11524","title":"Multi-granularity Generator for Temporal Action Proposal","created":"2018-11-28","cited_by_count":77},{"id":"2105.03245","title":"Adaptive Focus for Efficient Video Recognition","created":"2021-05-07","cited_by_count":77},{"id":"2012.10671","title":"SMART Frame Selection for Action Recognition","created":"2020-12-19","cited_by_count":73},{"id":"1907.13369","title":"Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition","created":"2019-07-31","cited_by_count":66},{"id":"1912.01601","title":"LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition","created":"2019-12-03","cited_by_count":65},{"id":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59},{"id":"1908.06552","title":"Weakly-supervised Action Localization with Background Modeling","created":"2019-08-19","cited_by_count":53},{"id":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48},{"id":"1502.07209","title":"Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks","created":"2015-02-25","cited_by_count":45},{"id":"2112.14238","title":"AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition","created":"2021-12-28","cited_by_count":37},{"id":"2012.06977","title":"MVFNet: Multi-View Fusion Network for Efficient Video Recognition","created":"2020-12-13","cited_by_count":36},{"id":"2105.05165","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","created":"2021-05-11","cited_by_count":36},{"id":"2108.10394","title":"Dynamic Network Quantization for Efficient Video Inference","created":"2021-08-23","cited_by_count":36},{"id":"2106.02342","title":"ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency","created":"2021-06-04","cited_by_count":35},{"id":"2006.15560","title":"Dynamic Sampling Networks for Efficient Action Recognition in Videos","created":"2020-06-28","cited_by_count":34},{"id":"2108.03825","title":"Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video","created":"2021-08-09","cited_by_count":32},{"id":"2106.06509","title":"Step-Wise Hierarchical Alignment Network for Image-Text Matching","created":"2021-06-11","cited_by_count":26},{"id":"2002.03342","title":"Dynamic Inference: A New Approach Toward Efficient Video Action Recognition","created":"2020-02-09","cited_by_count":25},{"id":"2201.04388","title":"OCSampler: Compressing Videos to One Clip with Single-step Sampling","created":"2022-01-12","cited_by_count":23},{"id":"2012.14950","title":"2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition","created":"2020-12-29","cited_by_count":22},{"id":"2112.07984","title":"Temporal Action Proposal Generation with Background Constraint","created":"2021-12-15","cited_by_count":16},{"id":"2105.12085","title":"DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning","created":"2021-05-25","cited_by_count":13},{"id":"1810.11189","title":"Fine-grained Video Categorization with Redundancy Reduction Attention","created":"2018-10-26","cited_by_count":12},{"id":"1905.11575","title":"Progressive Cross-Stream Cooperation in Spatial and Temporal Domain for Action Localization","created":"2019-05-28","cited_by_count":12},{"id":"2008.10850","title":"Discriminability Distillation in Group Representation Learning","created":"2020-08-25","cited_by_count":7},{"id":"2201.06304","title":"Action Keypoint Network for Efficient Video Recognition","created":"2022-01-17","cited_by_count":2}],"next_cursor":null}