{"list":"other","total":52,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"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":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"2103.13137","title":"Learning Salient Boundary Feature for Anchor-free Temporal Action Localization","created":"2021-03-24","cited_by_count":156},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154},{"id":"1705.10915","title":"Unsupervised Learning of Disentangled Representations from Video","created":"2017-05-31","cited_by_count":139},{"id":"1909.03877","title":"Gaussian Temporal Awareness Networks for Action Localization","created":"2019-09-09","cited_by_count":135},{"id":"1806.04166","title":"Learning to Decompose and Disentangle Representations for Video Prediction","created":"2018-06-11","cited_by_count":121},{"id":"1803.02991","title":"Disentangled Sequential Autoencoder","created":"2018-03-08","cited_by_count":120},{"id":"1912.05534","title":"Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition","created":"2019-12-11","cited_by_count":117},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117},{"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":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","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":"2001.03152","title":"Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias","created":"2020-01-09","cited_by_count":91},{"id":"1911.04127","title":"Fast Learning of Temporal Action Proposal via Dense Boundary Generator","created":"2019-11-11","cited_by_count":89},{"id":"2008.01432","title":"Boundary Content Graph Neural Network for Temporal Action Proposal Generation","created":"2020-08-04","cited_by_count":88},{"id":"1811.11524","title":"Multi-granularity Generator for Temporal Action Proposal","created":"2018-11-28","cited_by_count":77},{"id":"1911.09963","title":"Background Suppression Network for Weakly-supervised Temporal Action Localization","created":"2019-11-22","cited_by_count":73},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64},{"id":"1608.00797","title":"CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016","created":"2016-08-02","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":"2012.09434","title":"Multi-shot Temporal Event Localization: a Benchmark","created":"2020-12-17","cited_by_count":52},{"id":"2103.10095","title":"On Semantic Similarity in Video Retrieval","created":"2021-03-18","cited_by_count":46},{"id":"1804.00413","title":"End-to-End Learning of Motion Representation for Video Understanding","created":"2018-04-02","cited_by_count":43},{"id":"1910.12003","title":"Learning Disentangled Representation for Robust Person Re-identification","created":"2019-10-26","cited_by_count":40},{"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":"1903.01594","title":"Unsupervised Domain-Specific Deblurring via Disentangled Representations","created":"2019-03-05","cited_by_count":37},{"id":"1804.03487","title":"Exploring Disentangled Feature Representation Beyond Face Identification","created":"2018-04-10","cited_by_count":36},{"id":"2104.00862","title":"Self-supervised Video Representation Learning by Context and Motion Decoupling","created":"2021-04-02","cited_by_count":34},{"id":"2103.03027","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","created":"2021-03-04","cited_by_count":32},{"id":"2105.12405","title":"Unsupervised Part Segmentation through Disentangling Appearance and Shape","created":"2021-05-26","cited_by_count":29},{"id":"2112.00302","title":"Graph Convolutional Module for Temporal Action Localization in Videos","created":"2021-12-01","cited_by_count":29},{"id":"1704.04671","title":"Temporal Action Localization by Structured Maximal Sums","created":"2017-04-15","cited_by_count":28},{"id":"2003.04145","title":"Accurate Temporal Action Proposal Generation with Relation-Aware Pyramid Network","created":"2020-03-09","cited_by_count":28},{"id":"2111.12449","title":"Background-Click Supervision for Temporal Action Localization","created":"2021-11-24","cited_by_count":21},{"id":"1908.00707","title":"Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos","created":"2019-08-02","cited_by_count":17},{"id":"1809.01936","title":"Disentangled Variational Representation for Heterogeneous Face Recognition","created":"2018-09-06","cited_by_count":13},{"id":"1812.01285","title":"Rare Event Detection using Disentangled Representation Learning","created":"2018-12-04","cited_by_count":12},{"id":"2103.16155","title":"Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context","created":"2021-03-30","cited_by_count":12},{"id":"1708.03280","title":"Exploring Temporal Preservation Networks for Precise Temporal Action Localization","created":"2017-08-10","cited_by_count":11}],"next_cursor":null}