{"list":"other","total":70,"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"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":"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":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"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":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"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":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"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":"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":"2302.11813","title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","created":"2023-02-23","cited_by_count":132},{"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":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"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":"2108.08236","title":"LOKI: Long Term and Key Intentions for Trajectory Prediction","created":"2021-08-18","cited_by_count":57},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55},{"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":"1805.02834","title":"Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction","created":"2018-05-08","cited_by_count":40},{"id":"2111.09887","title":"PyTorchVideo: A Deep Learning Library for Video Understanding","created":"2021-11-18","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":"2304.07500","title":"The 7th AI City Challenge","created":"2023-04-15","cited_by_count":20},{"id":"2304.12160","title":"End-to-End Spatio-Temporal Action Localisation with Video Transformers","created":"2023-04-24","cited_by_count":20},{"id":"2112.00475","title":"Weakly-Supervised Video Object Grounding via Causal Intervention","created":"2021-12-01","cited_by_count":13},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12},{"id":"2312.01659","title":"RiskBench: A Scenario-based Benchmark for Risk Identification","created":"2023-12-04","cited_by_count":12},{"id":"2207.03807","title":"Beyond Transfer Learning: Co-finetuning for Action Localisation","created":"2022-07-08","cited_by_count":8},{"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":"2503.21055","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-03-27","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},{"id":"2003.13141","title":"Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection","created":"2020-03-29","cited_by_count":3},{"id":"2510.12206","title":"Controllable Collision Scenario Generation via Collision Pattern Prediction","created":"2025-10-14","cited_by_count":3},{"id":"2503.18553","title":"ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset","created":"2025-03-24","cited_by_count":2}],"next_cursor":null}