{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"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":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"1908.09822","title":"Confidence Regularized Self-Training","created":"2019-08-26","cited_by_count":419},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"2003.03773","title":"Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation","created":"2020-03-08","cited_by_count":222},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"1704.04232","title":"Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization","created":"2017-04-13","cited_by_count":207},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"1702.08400","title":"Asymmetric Tri-training for Unsupervised Domain Adaptation","created":"2017-02-27","cited_by_count":152},{"id":"1909.03877","title":"Gaussian Temporal Awareness Networks for Action Localization","created":"2019-09-09","cited_by_count":135},{"id":"1703.03329","title":"UntrimmedNets for Weakly Supervised Action Recognition and Detection","created":"2017-03-09","cited_by_count":130},{"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":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"1712.05080","title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network","created":"2017-12-14","cited_by_count":100},{"id":"1911.04127","title":"Fast Learning of Temporal Action Proposal via Dense Boundary Generator","created":"2019-11-11","cited_by_count":89},{"id":"1805.09300","title":"SNIPER: Efficient Multi-Scale Training","created":"2018-05-23","cited_by_count":88},{"id":"1807.10418","title":"W-TALC: Weakly-supervised Temporal Activity Localization and Classification","created":"2018-07-27","cited_by_count":87},{"id":"2004.04725","title":"Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection","created":"2020-04-09","cited_by_count":80},{"id":"1807.08333","title":"AutoLoc: Weakly-supervised Temporal Action Localization","created":"2018-07-22","cited_by_count":75},{"id":"1911.09963","title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","created":"2019-11-22","cited_by_count":73},{"id":"1807.10706","title":"Diagnosing Error in Temporal Action Detectors","created":"2018-07-27","cited_by_count":71},{"id":"2103.16392","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","created":"2021-03-30","cited_by_count":69},{"id":"2003.12424","title":"Weakly-Supervised Action Localization by Generative Attention Modeling","created":"2020-03-27","cited_by_count":59},{"id":"1908.06552","title":"Weakly-supervised Action Localization with Background Modeling","created":"2019-08-19","cited_by_count":53},{"id":"2010.11594","title":"Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization","created":"2020-10-22","cited_by_count":53},{"id":"2004.00163","title":"Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning","created":"2020-03-31","cited_by_count":48},{"id":"2101.00545","title":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","created":"2021-01-03","cited_by_count":45},{"id":"2007.06643","title":"Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization","created":"2020-07-13","cited_by_count":40},{"id":"2104.14135","title":"Action Unit Memory Network for Weakly Supervised Temporal Action Localization","created":"2021-04-29","cited_by_count":26},{"id":"2108.06524","title":"Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization","created":"2021-08-14","cited_by_count":26},{"id":"1904.00227","title":"RefineLoc: Iterative Refinement for Weakly-Supervised Action Localization","created":"2019-03-30","cited_by_count":24},{"id":"2111.11067","title":"Semi-Supervised Vision Transformers","created":"2021-11-22","cited_by_count":24},{"id":"2012.08510","title":"GTA: Global Temporal Attention for Video Action Understanding","created":"2020-12-15","cited_by_count":20},{"id":"2104.02967","title":"ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization","created":"2021-04-07","cited_by_count":19},{"id":"2103.13183","title":"The Blessings of Unlabeled Background in Untrimmed Videos","created":"2021-03-24","cited_by_count":16},{"id":"1908.02422","title":"Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization","created":"2019-08-07","cited_by_count":14},{"id":"2001.07793","title":"Weakly Supervised Temporal Action Localization Using Deep Metric Learning","created":"2020-01-21","cited_by_count":14},{"id":"2104.01198","title":"Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories","created":"2021-04-02","cited_by_count":11},{"id":"2007.10321","title":"Hierarchical Contrastive Motion Learning for Video Action Recognition","created":"2020-07-20","cited_by_count":8}],"next_cursor":null}