{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"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":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"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":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"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":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"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":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1802.04865","title":"Learning Confidence for Out-of-Distribution Detection in Neural Networks","created":"2018-02-13","cited_by_count":245},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"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":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"1712.00636","title":"Compressed Video Action Recognition","created":"2017-12-02","cited_by_count":106},{"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":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"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":"1906.03349","title":"Video Modeling with Correlation Networks","created":"2019-06-07","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":"2003.03622","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","created":"2020-03-07","cited_by_count":66},{"id":"1711.09125","title":"Appearance-and-Relation Networks for Video Classification","created":"2017-11-24","cited_by_count":61},{"id":"1607.01794","title":"VideoLSTM Convolves, Attends and Flows for Action Recognition","created":"2016-07-06","cited_by_count":60},{"id":"1909.13130","title":"Grouped Spatial-Temporal Aggregation for Efficient Action Recognition","created":"2019-09-28","cited_by_count":55},{"id":"1810.01455","title":"Representation Flow for Action Recognition","created":"2018-10-02","cited_by_count":51},{"id":"1904.02422","title":"Resource Efficient 3D Convolutional Neural Networks","created":"2019-04-04","cited_by_count":50},{"id":"1804.00413","title":"End-to-End Learning of Motion Representation for Video Understanding","created":"2018-04-02","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":"1907.00865","title":"Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning","created":"2019-07-01","cited_by_count":37},{"id":"1807.10037","title":"Motion Feature Network: Fixed Motion Filter for Action Recognition","created":"2018-07-26","cited_by_count":34},{"id":"1708.03958","title":"Lattice Long Short-Term Memory for Human Action Recognition","created":"2017-08-13","cited_by_count":16},{"id":"1604.00427","title":"Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video","created":"2016-04-01","cited_by_count":6}],"next_cursor":null}