{"list":"other","total":52,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1909.12605","title":"Towards Real-Time Multi-Object Tracking","created":"2019-09-27","cited_by_count":311},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1912.07515","title":"Learning a Neural Solver for Multiple Object Tracking","created":"2019-12-16","cited_by_count":198},{"id":"1804.07667","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","created":"2018-04-20","cited_by_count":194},{"id":"1409.7618","title":"Multiple Object Tracking: A Literature Review","created":"2014-09-26","cited_by_count":166},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"2005.10356","title":"TAO: A Large-Scale Benchmark for Tracking Any Object","created":"2020-05-20","cited_by_count":147},{"id":"1804.09066","title":"ECO: Efficient Convolutional Network for Online Video Understanding","created":"2018-04-24","cited_by_count":115},{"id":"2006.07327","title":"GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning","created":"2020-06-12","cited_by_count":113},{"id":"1804.06055","title":"Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation","created":"2018-04-17","cited_by_count":106},{"id":"1803.10859","title":"Features for Multi-Target Multi-Camera Tracking and Re-Identification","created":"2018-03-28","cited_by_count":88},{"id":"2005.00214","title":"The AVA-Kinetics Localized Human Actions Video Dataset","created":"2020-05-01","cited_by_count":82},{"id":"1705.01861","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","created":"2017-05-04","cited_by_count":77},{"id":"2004.07485","title":"Asynchronous Interaction Aggregation for Action Detection","created":"2020-04-16","cited_by_count":65},{"id":"1611.08563","title":"Online Real-time Multiple Spatiotemporal Action Localisation and Prediction","created":"2016-11-25","cited_by_count":57},{"id":"2001.04608","title":"Actions as Moving Points","created":"2020-01-14","cited_by_count":55},{"id":"2006.14550","title":"Lifted Disjoint Paths with Application in Multiple Object Tracking","created":"2020-06-25","cited_by_count":55},{"id":"1904.09288","title":"STEP: Spatio-Temporal Progressive Learning for Video Action Detection","created":"2019-04-19","cited_by_count":51},{"id":"1411.6031","title":"Finding Action Tubes","created":"2014-11-21","cited_by_count":50},{"id":"1703.10664","title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","created":"2017-03-30","cited_by_count":50},{"id":"1706.03038","title":"Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection","created":"2017-06-09","cited_by_count":46},{"id":"2003.04852","title":"PANDA: A Gigapixel-level Human-centric Video Dataset","created":"2020-03-10","cited_by_count":45},{"id":"1506.01929","title":"Learning to track for spatio-temporal action localization","created":"2015-06-05","cited_by_count":44},{"id":"1502.05082","title":"What makes for effective detection proposals?","created":"2015-02-17","cited_by_count":38},{"id":"1705.01180","title":"Cascaded Boundary Regression for Temporal Action Detection","created":"2017-05-02","cited_by_count":35},{"id":"1704.00616","title":"Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection","created":"2017-04-03","cited_by_count":34},{"id":"1907.09658","title":"Make Skeleton-based Action Recognition Model Smaller, Faster and Better","created":"2019-07-23","cited_by_count":22},{"id":"1604.07602","title":"Spot On: Action Localization from Pointly-Supervised Proposals","created":"2016-04-26","cited_by_count":17},{"id":"2007.03200","title":"ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation","created":"2020-07-07","cited_by_count":17},{"id":"1807.10066","title":"A Better Baseline for AVA","created":"2018-07-26","cited_by_count":16},{"id":"1812.11631","title":"Actor Conditioned Attention Maps for Video Action Detection","created":"2018-12-30","cited_by_count":15},{"id":"1907.05315","title":"Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking","created":"2019-07-11","cited_by_count":15},{"id":"1806.03084","title":"Unifying Identification and Context Learning for Person Recognition","created":"2018-06-08","cited_by_count":10},{"id":"1803.03347","title":"Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking","created":"2018-03-09","cited_by_count":9},{"id":"2008.08332","title":"CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization","created":"2020-08-19","cited_by_count":7}],"next_cursor":null}