{"list":"other","total":76,"rows":[{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"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":"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":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85},{"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":"1705.01861","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","created":"2017-05-04","cited_by_count":77},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"1604.02532","title":"T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos","created":"2016-04-09","cited_by_count":67},{"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":"2112.01514","title":"Self-supervised Video Transformer","created":"2021-12-02","cited_by_count":64},{"id":"2001.04608","title":"Actions as Moving Points","created":"2020-01-14","cited_by_count":55},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"id":"1904.09288","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","created":"2019-04-19","cited_by_count":51},{"id":"1703.10664","title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","created":"2017-03-30","cited_by_count":50},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44},{"id":"2204.01018","title":"TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting","created":"2022-04-03","cited_by_count":44},{"id":"2005.10229","title":"Intra- and Inter-Action Understanding via Temporal Action Parsing","created":"2020-05-20","cited_by_count":41},{"id":"2009.05757","title":"Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion","created":"2020-09-12","cited_by_count":39},{"id":"2106.02342","title":"ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency","created":"2021-06-04","cited_by_count":35},{"id":"2005.08465","title":"Context-aware and Scale-insensitive Temporal Repetition Counting","created":"2020-05-18","cited_by_count":34},{"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":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29},{"id":"2108.08426","title":"Self-Supervised Video Representation Learning with Meta-Contrastive Network","created":"2021-08-19","cited_by_count":28},{"id":"1912.06617","title":"Action Modifiers: Learning from Adverbs in Instructional Videos","created":"2019-12-13","cited_by_count":27},{"id":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27},{"id":"1702.06355","title":"Object Detection in Videos with Tubelet Proposal Networks","created":"2017-02-21","cited_by_count":24},{"id":"2203.14221","title":"How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?","created":"2022-03-27","cited_by_count":23},{"id":"2104.00240","title":"Self-supervised Motion Learning from Static Images","created":"2021-04-01","cited_by_count":21},{"id":"2109.11593","title":"Long Short View Feature Decomposition via Contrastive Video Representation Learning","created":"2021-09-23","cited_by_count":21},{"id":"1804.03247","title":"Fine-grained Activity Recognition in Baseball Videos","created":"2018-04-09","cited_by_count":20},{"id":"2105.02545","title":"Unsupervised Visual Representation Learning by Tracking Patches in Video","created":"2021-05-06","cited_by_count":20},{"id":"2108.08363","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","created":"2021-08-18","cited_by_count":18},{"id":"2105.01646","title":"Motion-Augmented Self-Training for Video Recognition at Smaller Scale","created":"2021-05-04","cited_by_count":17},{"id":"2209.01425","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","created":"2022-09-03","cited_by_count":17},{"id":"2111.01673","title":"Relational Self-Attention: What's Missing in Attention for Video Understanding","created":"2021-11-02","cited_by_count":15},{"id":"2003.02692","title":"Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video","created":"2020-03-05","cited_by_count":11},{"id":"2208.06105","title":"Motion Sensitive Contrastive Learning for Self-supervised Video Representation","created":"2022-08-12","cited_by_count":11},{"id":"2106.09703","title":"MaCLR: Motion-aware Contrastive Learning of Representations for Videos","created":"2021-06-17","cited_by_count":10},{"id":"1801.09571","title":"End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding","created":"2018-01-29","cited_by_count":9},{"id":"1811.08815","title":"Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection","created":"2018-11-21","cited_by_count":9},{"id":"2205.15814","title":"Contrasting quadratic assignments for set-based representation learning","created":"2022-05-31","cited_by_count":6},{"id":"2107.01194","title":"Inter-intra Variant Dual Representations forSelf-supervised Video Recognition","created":"2021-07-02","cited_by_count":5}],"next_cursor":null}