{"list":"other","total":76,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"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":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"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":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1511.06335","title":"Unsupervised Deep Embedding for Clustering Analysis","created":"2015-11-19","cited_by_count":767},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"1609.02612","title":"Generating Videos with Scene Dynamics","created":"2016-09-08","cited_by_count":376},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2010.10144","title":"Keystroke Dynamics as Part of Lifelogging","created":"2020-10-20","cited_by_count":334},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1406.6909","title":"Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks","created":"2014-06-26","cited_by_count":300},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"2010.09709","title":"Self-supervised Co-training for Video Representation Learning","created":"2020-10-19","cited_by_count":232},{"id":"1708.07860","title":"Multi-task Self-Supervised Visual Learning","created":"2017-08-25","cited_by_count":200},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"1806.09594","title":"Tracking Emerges by Colorizing Videos","created":"2018-06-25","cited_by_count":166},{"id":"2007.13003","title":"Robust and Generalizable Visual Representation Learning via Random Convolutions","created":"2020-07-25","cited_by_count":142},{"id":"2008.01065","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","created":"2020-08-03","cited_by_count":137},{"id":"1905.00561","title":"Large-scale weakly-supervised pre-training for video action recognition","created":"2019-05-02","cited_by_count":130},{"id":"1506.09215","title":"Unsupervised Learning from Narrated Instruction Videos","created":"2015-06-30","cited_by_count":116},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"2004.14646","title":"Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning","created":"2020-04-30","cited_by_count":102},{"id":"2010.10241","title":"BYOL works even without batch statistics","created":"2020-10-20","cited_by_count":95},{"id":"1606.07873","title":"An Uncertain Future: Forecasting from Static Images using Variational Autoencoders","created":"2016-06-25","cited_by_count":87},{"id":"1904.11567","title":"Unsupervised Deep Learning by Neighbourhood Discovery","created":"2019-04-25","cited_by_count":78},{"id":"2002.12177","title":"Evolving Losses for Unsupervised Video Representation Learning","created":"2020-02-26","cited_by_count":74},{"id":"2002.12247","title":"Learning Representations by Predicting Bags of Visual Words","created":"2020-02-27","cited_by_count":73},{"id":"2012.10671","title":"SMART Frame Selection for Action Recognition","created":"2020-12-19","cited_by_count":73},{"id":"1812.08249","title":"D3D: Distilled 3D Networks for Video Action Recognition","created":"2018-12-19","cited_by_count":60},{"id":"1711.02209","title":"Unsupervised Learning of Semantic Audio Representations","created":"2017-11-06","cited_by_count":44},{"id":"1608.08792","title":"CliqueCNN: Deep Unsupervised Exemplar Learning","created":"2016-08-31","cited_by_count":41},{"id":"1511.06309","title":"Spatio-temporal video autoencoder with differentiable memory","created":"2015-11-19","cited_by_count":32},{"id":"1503.01558","title":"What's Cookin'? Interpreting Cooking Videos using Text, Speech and Vision","created":"2015-03-05","cited_by_count":31},{"id":"1911.05894","title":"Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision","created":"2019-11-14","cited_by_count":27},{"id":"2003.05078","title":"Visual Grounding in Video for Unsupervised Word Translation","created":"2020-03-11","cited_by_count":27},{"id":"1506.08438","title":"Unsupervised Semantic Parsing of Video Collections","created":"2015-06-28","cited_by_count":26},{"id":"2007.13278","title":"Representation Learning with Video Deep InfoMax","created":"2020-07-27","cited_by_count":17}],"next_cursor":null}