{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"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":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2002.11927","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","created":"2020-02-27","cited_by_count":325},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2109.04456","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","created":"2021-09-09","cited_by_count":174},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"2004.03548","title":"Temporal Pyramid Network for Action Recognition","created":"2020-04-07","cited_by_count":163},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146},{"id":"2112.05077","title":"Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior","created":"2021-12-09","cited_by_count":139},{"id":"2304.01893","title":"Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion","created":"2023-04-04","cited_by_count":138},{"id":"2203.11934","title":"Learning from All Vehicles","created":"2022-03-22","cited_by_count":135},{"id":"2302.11813","title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","created":"2023-02-23","cited_by_count":132},{"id":"2007.09654","title":"Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets","created":"2020-07-19","cited_by_count":122},{"id":"2208.01582","title":"ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries","created":"2022-08-02","cited_by_count":117},{"id":"2210.14222","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","created":"2022-10-25","cited_by_count":105},{"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":"2204.13683","title":"KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients","created":"2022-04-28","cited_by_count":96},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"2305.10507","title":"ReasonNet: End-to-End Driving with Temporal and Global Reasoning","created":"2023-05-17","cited_by_count":93},{"id":"2206.06922","title":"Object Scene Representation Transformer","created":"2022-06-14","cited_by_count":90},{"id":"1607.02643","title":"Hierarchical Deep Temporal Models for Group Activity Recognition","created":"2016-07-09","cited_by_count":89},{"id":"1904.10117","title":"Learning Actor Relation Graphs for Group Activity Recognition","created":"2019-04-23","cited_by_count":83},{"id":"2002.08945","title":"Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction","created":"2020-02-20","cited_by_count":71},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"2206.09682","title":"SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles","created":"2022-06-20","cited_by_count":66},{"id":"2003.13886","title":"TITAN: Future Forecast using Action Priors","created":"2020-03-31","cited_by_count":58},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51},{"id":"2209.08744","title":"AdvDO: Realistic Adversarial Attacks for Trajectory Prediction","created":"2022-09-19","cited_by_count":49},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44},{"id":"2111.09887","title":"PyTorchVideo: A Deep Learning Library for Video Understanding","created":"2021-11-18","cited_by_count":32},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32},{"id":"2112.08949","title":"Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation","created":"2021-12-16","cited_by_count":24},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22},{"id":"2110.13939","title":"CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation","created":"2021-10-26","cited_by_count":20},{"id":"2304.07500","title":"The 7th AI City Challenge","created":"2023-04-15","cited_by_count":20},{"id":"2306.10014","title":"Coaching a Teachable Student","created":"2023-06-16","cited_by_count":19},{"id":"1901.08616","title":"Boosting Standard Classification Architectures Through a Ranking Regularizer","created":"2019-01-24","cited_by_count":7},{"id":"2011.06165","title":"Universal Embeddings for Spatio-Temporal Tagging of Self-Driving Logs","created":"2020-11-12","cited_by_count":6},{"id":"2301.00714","title":"Learning Road Scene-level Representations via Semantic Region Prediction","created":"2023-01-02","cited_by_count":4}],"next_cursor":null}