{"list":"other","total":61,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"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":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"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":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99},{"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":"2002.11616","title":"Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution","created":"2020-02-26","cited_by_count":91},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","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":"2008.09105","title":"Location-aware Graph Convolutional Networks for Video Question Answering","created":"2020-08-07","cited_by_count":80},{"id":"1811.11387","title":"Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction","created":"2018-11-28","cited_by_count":71},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68},{"id":"2008.00820","title":"Generating Visually Aligned Sound from Videos","created":"2020-07-14","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":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63},{"id":"1906.02549","title":"Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video","created":"2019-06-06","cited_by_count":60},{"id":"2106.11250","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","created":"2021-06-21","cited_by_count":56},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55},{"id":"2106.09212","title":"Long-Short Temporal Contrastive Learning of Video Transformers","created":"2021-06-17","cited_by_count":42},{"id":"2106.02342","title":"ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency","created":"2021-06-04","cited_by_count":35},{"id":"1511.06309","title":"Spatio-temporal video autoencoder with differentiable memory","created":"2015-11-19","cited_by_count":32},{"id":"2001.09308","title":"Look Closer to Ground Better: Weakly-Supervised Temporal Grounding of Sentence in Video","created":"2020-01-25","cited_by_count":29},{"id":"2207.11660","title":"MAR: Masked Autoencoders for Efficient Action Recognition","created":"2022-07-24","cited_by_count":29},{"id":"2105.02545","title":"Unsupervised Visual Representation Learning by Tracking Patches in Video","created":"2021-05-06","cited_by_count":20},{"id":"2103.13183","title":"The Blessings of Unlabeled Background in Untrimmed Videos","created":"2021-03-24","cited_by_count":16},{"id":"2006.15731","title":"Unsupervised Learning of Video Representations via Dense Trajectory Clustering","created":"2020-06-28","cited_by_count":11}],"next_cursor":null}