{"list":"other","total":69,"rows":[{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"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":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"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":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2006.04131","title":"Deep Graph Contrastive Representation Learning","created":"2020-06-07","cited_by_count":539},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"id":"1812.04202","title":"Deep Learning on Graphs: A Survey","created":"2018-12-11","cited_by_count":393},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"1806.01810","title":"Videos as Space-Time Region Graphs","created":"2018-06-05","cited_by_count":221},{"id":"2002.12416","title":"Learning in the Frequency Domain","created":"2020-02-27","cited_by_count":198},{"id":"2012.11879","title":"FcaNet: Frequency Channel Attention Networks","created":"2020-12-22","cited_by_count":179},{"id":"1703.04044","title":"Colorization as a Proxy Task for Visual Understanding","created":"2017-03-11","cited_by_count":175},{"id":"1909.04656","title":"Video Representation Learning by Dense Predictive Coding","created":"2019-09-10","cited_by_count":175},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"1904.05049","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","created":"2019-04-10","cited_by_count":140},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2008.01065","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","created":"2020-08-03","cited_by_count":137},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"1811.12814","title":"Graph-Based Global Reasoning Networks","created":"2018-11-30","cited_by_count":120},{"id":"1712.00636","title":"Compressed Video Action Recognition","created":"2017-12-02","cited_by_count":106},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"id":"1904.03597","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","created":"2019-04-07","cited_by_count":92},{"id":"2007.10730","title":"Video Representation Learning by Recognizing Temporal Transformations","created":"2020-07-21","cited_by_count":83},{"id":"2011.07949","title":"RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning","created":"2020-10-27","cited_by_count":83},{"id":"2001.00294","title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","created":"2020-01-02","cited_by_count":81},{"id":"2010.05421","title":"Factorizable Graph Convolutional Networks","created":"2020-10-12","cited_by_count":79},{"id":"2002.12177","title":"Evolving Losses for Unsupervised Video Representation Learning","created":"2020-02-26","cited_by_count":74},{"id":"2009.05769","title":"Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning","created":"2020-09-12","cited_by_count":66},{"id":"2008.00975","title":"SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning","created":"2020-08-03","cited_by_count":65},{"id":"1505.04868","title":"Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors","created":"2015-05-19","cited_by_count":58},{"id":"1803.06131","title":"Towards Image Understanding from Deep Compression without Decoding","created":"2018-03-16","cited_by_count":52},{"id":"2008.02531","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","created":"2020-08-06","cited_by_count":46},{"id":"1812.11690","title":"Deep Residual Learning in the JPEG Transform Domain","created":"2018-12-31","cited_by_count":44},{"id":"2009.00210","title":"Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition","created":"2020-09-01","cited_by_count":37},{"id":"1807.11293","title":"Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning","created":"2018-07-30","cited_by_count":35},{"id":"1908.10700","title":"Explainable Video Action Reasoning via Prior Knowledge and State Transitions","created":"2019-08-28","cited_by_count":33},{"id":"2005.03141","title":"Towards Frequency-Based Explanation for Robust CNN","created":"2020-05-06","cited_by_count":29},{"id":"2008.13426","title":"Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics","created":"2020-08-31","cited_by_count":29},{"id":"2007.08025","title":"GraphCL: Contrastive Self-Supervised Learning of Graph Representations","created":"2020-07-15","cited_by_count":26},{"id":"2112.01849","title":"Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition","created":"2021-10-08","cited_by_count":25},{"id":"1908.09995","title":"Temporal Reasoning Graph for Activity Recognition","created":"2019-08-27","cited_by_count":22},{"id":"1911.10751","title":"Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition","created":"2019-11-25","cited_by_count":21},{"id":"1809.00421","title":"Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition","created":"2018-09-03","cited_by_count":16},{"id":"1909.08287","title":"Global Temporal Representation based CNNs for Infrared Action Recognition","created":"2019-09-18","cited_by_count":16},{"id":"1405.4506","title":"Bag of Visual Words and Fusion Methods for Action Recognition: Comprehensive Study and Good Practice","created":"2014-05-18","cited_by_count":13},{"id":"1909.08297","title":"Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition","created":"2019-09-18","cited_by_count":13},{"id":"1901.03067","title":"Multi-Granularity Reasoning for Social Relation Recognition from Images","created":"2019-01-10","cited_by_count":8},{"id":"1904.03579","title":"Adaptively Connected Neural Networks","created":"2019-04-07","cited_by_count":7},{"id":"2009.06902","title":"Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition","created":"2020-09-15","cited_by_count":4}],"next_cursor":null}