{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"1702.05693","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","created":"2017-02-19","cited_by_count":172},{"id":"1804.09626","title":"Charades-Ego: A Large-Scale Dataset of Paired Third and First Person Videos","created":"2018-04-25","cited_by_count":128},{"id":"1811.02307","title":"Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning","created":"2018-11-06","cited_by_count":102},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"id":"1812.04767","title":"TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions","created":"2018-12-12","cited_by_count":82},{"id":"1903.01568","title":"The H3D Dataset for Full-Surround 3D Multi-Object Detection and Tracking in Crowded Urban Scenes","created":"2019-03-04","cited_by_count":80},{"id":"1705.01861","title":"Action Tubelet Detector for Spatio-Temporal Action Localization","created":"2017-05-04","cited_by_count":77},{"id":"1805.11773","title":"Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice","created":"2018-05-30","cited_by_count":76},{"id":"1909.07541","title":"A*3D Dataset: Towards Autonomous Driving in Challenging Environments","created":"2019-09-17","cited_by_count":65},{"id":"2004.07485","title":"Asynchronous Interaction Aggregation for Action Detection","created":"2020-04-16","cited_by_count":65},{"id":"2003.13886","title":"TITAN: Future Forecast using Action Priors","created":"2020-03-31","cited_by_count":58},{"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":"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":"1804.07871","title":"A Reinforcement Learning Based Approach for Automated Lane Change Maneuvers","created":"2018-04-21","cited_by_count":46},{"id":"1712.05812","title":"Occam's razor is insufficient to infer the preferences of irrational agents","created":"2017-12-15","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":"1809.07408","title":"Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems","created":"2018-09-19","cited_by_count":42},{"id":"1905.13417","title":"TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection","created":"2019-05-31","cited_by_count":36},{"id":"1608.01529","title":"Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos","created":"2016-08-04","cited_by_count":35},{"id":"1904.00696","title":"Dance with Flow: Two-in-One Stream Action Detection","created":"2019-04-01","cited_by_count":30},{"id":"1904.01975","title":"D$^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios","created":"2019-04-03","cited_by_count":28},{"id":"1807.10580","title":"Is the Pedestrian going to Cross? Answering by 2D Pose Estimation","created":"2018-07-15","cited_by_count":25},{"id":"2004.14747","title":"Pedestrian Path, Pose and Intention Prediction through Gaussian Process Dynamical Models and Pedestrian Activity Recognition","created":"2020-04-30","cited_by_count":20},{"id":"1807.10066","title":"A Better Baseline for AVA","created":"2018-07-26","cited_by_count":16},{"id":"1704.04952","title":"AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture","created":"2017-04-17","cited_by_count":9},{"id":"1808.00297","title":"TraMNet - Transition Matrix Network for Efficient Action Tube Proposals","created":"2018-08-01","cited_by_count":6},{"id":"1808.07712","title":"Predicting Action Tubes","created":"2018-08-23","cited_by_count":6},{"id":"1704.01358","title":"Incremental Tube Construction for Human Action Detection","created":"2017-04-05","cited_by_count":5},{"id":"2004.01494","title":"Two-Stream AMTnet for Action Detection","created":"2020-04-03","cited_by_count":4},{"id":"1901.06563","title":"Consistent Optimization for Single-Shot Object Detection","created":"2019-01-19","cited_by_count":3},{"id":"1710.04459","title":"Arguing Machines: Human Supervision of Black Box AI Systems That Make Life-Critical Decisions","created":"2017-10-12","cited_by_count":2}],"next_cursor":null}