{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"1905.00561","title":"Large-scale weakly-supervised pre-training for video action recognition","created":"2019-05-02","cited_by_count":130},{"id":"1902.04502","title":"Fast-SCNN: Fast Semantic Segmentation Network","created":"2019-02-12","cited_by_count":125},{"id":"1703.01515","title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos","created":"2017-03-04","cited_by_count":112},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105},{"id":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104},{"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":"1712.05080","title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","created":"2017-12-14","cited_by_count":100},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"1604.04494","title":"Long-term Temporal Convolutions for Action Recognition","created":"2016-04-15","cited_by_count":84},{"id":"1812.06587","title":"Grounded Video Description","created":"2018-12-17","cited_by_count":78},{"id":"2011.11479","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","created":"2020-11-23","cited_by_count":77},{"id":"1904.04189","title":"Unsupervised learning of action classes with continuous temporal embedding","created":"2019-04-08","cited_by_count":76},{"id":"2003.02824","title":"Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation","created":"2020-03-05","cited_by_count":74},{"id":"1703.08132","title":"Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling","created":"2017-03-23","cited_by_count":70},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"1803.09490","title":"Unsupervised Learning and Segmentation of Complex Activities from Video","created":"2018-03-26","cited_by_count":61},{"id":"2003.12424","title":"Weakly-Supervised Action Localization by Generative Attention Modeling","created":"2020-03-27","cited_by_count":59},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48},{"id":"1905.13209","title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","created":"2019-05-30","cited_by_count":46},{"id":"2011.10830","title":"Boundary-sensitive Pre-training for Temporal Localization in Videos","created":"2020-11-21","cited_by_count":41},{"id":"1803.06316","title":"Temporal Gaussian Mixture Layer for Videos","created":"2018-03-16","cited_by_count":40},{"id":"2103.03027","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","created":"2021-03-04","cited_by_count":32},{"id":"1712.01938","title":"Learning Latent Super-Events to Detect Multiple Activities in Videos","created":"2017-12-05","cited_by_count":30},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28},{"id":"1811.10575","title":"Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation","created":"2018-11-26","cited_by_count":25},{"id":"2103.16024","title":"Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation","created":"2021-03-30","cited_by_count":25},{"id":"2103.15088","title":"ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization","created":"2021-03-28","cited_by_count":20},{"id":"2103.15233","title":"Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization","created":"2021-03-28","cited_by_count":20},{"id":"1504.00983","title":"Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images","created":"2015-04-04","cited_by_count":19},{"id":"1910.01286","title":"Learning Temporal Action Proposals With Fewer Labels","created":"2019-10-03","cited_by_count":17},{"id":"2007.04515","title":"Aligning Videos in Space and Time","created":"2020-07-09","cited_by_count":13}],"next_cursor":null}