{"list":"other","total":57,"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":"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":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"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":"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":"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":"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":"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":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"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":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"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":"2005.06803","title":"TAM: Temporal Adaptive Module for Video Recognition","created":"2020-05-14","cited_by_count":139},{"id":"1708.01471","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","created":"2017-08-04","cited_by_count":117},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"1511.06062","title":"Compact Bilinear Pooling","created":"2015-11-19","cited_by_count":97},{"id":"1911.09435","title":"TEINet: Towards an Efficient Architecture for Video Recognition","created":"2019-11-21","cited_by_count":92},{"id":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"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":"1811.12006","title":"Global Second-order Pooling Convolutional Networks","created":"2018-11-29","cited_by_count":66},{"id":"1712.01034","title":"Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization","created":"2017-12-04","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":"1711.09125","title":"Appearance-and-Relation Networks for Video Classification","created":"2017-11-24","cited_by_count":61},{"id":"1711.01467","title":"Attentional Pooling for Action Recognition","created":"2017-11-04","cited_by_count":54},{"id":"1912.00998","title":"A Multigrid Method for Efficiently Training Video Models","created":"2019-12-02","cited_by_count":52},{"id":"1703.08050","title":"Is Second-order Information Helpful for Large-scale Visual Recognition?","created":"2017-03-23","cited_by_count":44},{"id":"1904.06836","title":"Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization","created":"2019-04-15","cited_by_count":42},{"id":"2006.14582","title":"SmallBigNet: Integrating Core and Contextual Views for Video Classification","created":"2020-06-25","cited_by_count":40},{"id":"1806.07754","title":"Spatio-Temporal Channel Correlation Networks for Action Classification","created":"2018-06-19","cited_by_count":38},{"id":"1810.13125","title":"Compact Generalized Non-local Network","created":"2018-10-31","cited_by_count":36},{"id":"2002.07442","title":"V4D:4D Convolutional Neural Networks for Video-level Representation Learning","created":"2020-02-18","cited_by_count":33},{"id":"1605.06182","title":"Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods","created":"2016-05-20","cited_by_count":29},{"id":"2012.14371","title":"Tensor Representations for Action Recognition","created":"2020-12-28","cited_by_count":28},{"id":"1611.06678","title":"Deep Temporal Linear Encoding Networks","created":"2016-11-21","cited_by_count":27},{"id":"1811.05014","title":"NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification","created":"2018-11-12","cited_by_count":24},{"id":"2012.08510","title":"GTA: Global Temporal Attention for Video Action Understanding","created":"2020-12-15","cited_by_count":20},{"id":"2007.12887","title":"Approximated Bilinear Modules for Temporal Modeling","created":"2020-07-25","cited_by_count":8},{"id":"1811.09974","title":"Temporal Bilinear Networks for Video Action Recognition","created":"2018-11-25","cited_by_count":5},{"id":"1303.6021","title":"Spatio-Temporal Covariance Descriptors for Action and Gesture Recognition","created":"2013-03-25","cited_by_count":4},{"id":"2012.10285","title":"Trying Bilinear Pooling in Video-QA","created":"2020-12-18","cited_by_count":1}],"next_cursor":null}