{"total":1288,"rows":[{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484,"area":"vla"},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422,"area":null},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360,"area":null},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823,"area":null},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764,"area":null},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717,"area":null},{"id":"2104.10133","title":"Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset","created":"2021-04-20","cited_by_count":537,"area":null},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482,"area":null},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382,"area":null},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381,"area":null},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371,"area":null},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370,"area":"offlinerl"},{"id":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303,"area":null},{"id":"2202.01197","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","created":"2022-02-02","cited_by_count":300,"area":null},{"id":"2204.05575","title":"DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection","created":"2022-04-12","cited_by_count":273,"area":null},{"id":"2306.14846","title":"ViNT: A Foundation Model for Visual Navigation","created":"2023-06-26","cited_by_count":222,"area":null},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220,"area":null},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219,"area":null},{"id":"2106.11037","title":"One Million Scenes for Autonomous Driving: ONCE Dataset","created":"2021-06-21","cited_by_count":218,"area":null},{"id":"2103.15597","title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","created":"2021-03-29","cited_by_count":215,"area":null},{"id":"2108.08265","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","created":"2021-08-18","cited_by_count":194,"area":"driving"},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192,"area":null},{"id":"2210.03370","title":"GNM: A General Navigation Model to Drive Any Robot","created":"2022-10-07","cited_by_count":171,"area":null},{"id":"2303.07601","title":"V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception","created":"2023-03-14","cited_by_count":155,"area":null},{"id":"2104.14812","title":"SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation","created":"2021-04-30","cited_by_count":150,"area":null},{"id":"2211.09791","title":"MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors","created":"2022-11-17","cited_by_count":148,"area":null},{"id":"2206.08367","title":"SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation","created":"2022-06-16","cited_by_count":146,"area":null},{"id":"2203.11089","title":"PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark","created":"2022-03-21","cited_by_count":140,"area":null},{"id":"2107.01153","title":"A Survey on Deep Learning Technique for Video Segmentation","created":"2021-07-02","cited_by_count":132,"area":null},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131,"area":null},{"id":"2310.14414","title":"Vision Language Models in Autonomous Driving: A Survey and Outlook","created":"2023-10-22","cited_by_count":126,"area":"mllm"},{"id":"2501.04003","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","created":"2025-01-07","cited_by_count":122,"area":"mllm"},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117,"area":null},{"id":"2403.12036","title":"One-Step Image Translation with Text-to-Image Models","created":"2024-03-18","cited_by_count":116,"area":"diffusion"},{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114,"area":"driving"},{"id":"2206.08171","title":"K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions","created":"2022-06-16","cited_by_count":108,"area":null},{"id":"2307.04370","title":"Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey","created":"2023-07-10","cited_by_count":103,"area":"driving"},{"id":"2106.03149","title":"Large-scale Unsupervised Semantic Segmentation","created":"2021-06-06","cited_by_count":101,"area":null},{"id":"2302.05155","title":"TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation","created":"2023-02-10","cited_by_count":101,"area":null},{"id":"2203.07724","title":"CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving","created":"2022-03-15","cited_by_count":100,"area":null},{"id":"2105.13502","title":"Unsupervised Domain Adaptation of Object Detectors: A Survey","created":"2021-05-27","cited_by_count":93,"area":null},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93,"area":null},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93,"area":null},{"id":"2204.02548","title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","created":"2022-04-06","cited_by_count":89,"area":null},{"id":"2307.15700","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","created":"2023-07-28","cited_by_count":88,"area":null},{"id":"2204.08808","title":"SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation","created":"2022-04-19","cited_by_count":87,"area":null},{"id":"2301.05499","title":"CLIP the Gap: A Single Domain Generalization Approach for Object Detection","created":"2023-01-13","cited_by_count":87,"area":null},{"id":"1912.00177","title":"Urban Driving with Conditional Imitation Learning","created":"2019-11-30","cited_by_count":86,"area":"offlinerl"},{"id":"2107.07919","title":"A Survey on Bias in Visual Datasets","created":"2021-07-16","cited_by_count":84,"area":null},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2304.10440","title":"OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping","created":"2023-04-20","cited_by_count":83,"area":null},{"id":"2305.02008","title":"Zenseact Open Dataset: A large-scale and diverse multimodal dataset for autonomous driving","created":"2023-05-03","cited_by_count":83,"area":null},{"id":"2312.04265","title":"Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation","created":"2023-12-07","cited_by_count":83,"area":null},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82,"area":null},{"id":"2103.07351","title":"Monocular Quasi-Dense 3D Object Tracking","created":"2021-03-12","cited_by_count":81,"area":null},{"id":"2307.01197","title":"Segment Anything Meets Point Tracking","created":"2023-07-03","cited_by_count":81,"area":null},{"id":"2101.05307","title":"Explainability of deep vision-based autonomous driving systems: Review and challenges","created":"2021-01-13","cited_by_count":80,"area":null},{"id":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79,"area":null},{"id":"2302.00673","title":"ADAPT: Action-aware Driving Caption Transformer","created":"2023-02-01","cited_by_count":78,"area":"driving"},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78,"area":"mllm"},{"id":"2408.10845","title":"CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving","created":"2024-08-19","cited_by_count":77,"area":"driving"},{"id":"2204.01446","title":"WildNet: Learning Domain Generalized Semantic Segmentation from the Wild","created":"2022-04-04","cited_by_count":76,"area":null},{"id":"2303.17220","title":"Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys","created":"2023-03-30","cited_by_count":75,"area":null},{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73,"area":"driving"},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2310.19909","title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks","created":"2023-10-30","cited_by_count":72,"area":null},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"id":"2203.03800","title":"Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild","created":"2022-03-08","cited_by_count":70,"area":null},{"id":"2205.15288","title":"Self-Supervised Visual Representation Learning with Semantic Grouping","created":"2022-05-30","cited_by_count":70,"area":null},{"id":"2207.04892","title":"Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation","created":"2022-07-11","cited_by_count":70,"area":null},{"id":"2108.09518","title":"MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?","created":"2021-08-21","cited_by_count":69,"area":null},{"id":"2204.00570","title":"Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation","created":"2022-04-01","cited_by_count":67,"area":null},{"id":"2211.14293","title":"RbA: Segmenting Unknown Regions Rejected by All","created":"2022-11-25","cited_by_count":67,"area":null},{"id":"2403.16996","title":"DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving","created":"2024-03-25","cited_by_count":67,"area":"lr"},{"id":"2209.12118","title":"BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video","created":"2022-09-25","cited_by_count":66,"area":null},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2111.13673","title":"Mask Transfiner for High-Quality Instance Segmentation","created":"2021-11-26","cited_by_count":64,"area":null},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63,"area":"offlinerl"},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62,"area":null},{"id":"2212.03038","title":"Unifying Short and Long-Term Tracking with Graph Hierarchies","created":"2022-12-06","cited_by_count":62,"area":null},{"id":"2303.11749","title":"Detecting Everything in the Open World: Towards Universal Object Detection","created":"2023-03-21","cited_by_count":62,"area":null},{"id":"2210.06984","title":"QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking","created":"2022-10-12","cited_by_count":61,"area":null},{"id":"2311.17138","title":"Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2501.00584","title":"Online Video Understanding: OVBench and VideoChat-Online","created":"2024-12-31","cited_by_count":61,"area":"mllm"},{"id":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60,"area":null},{"id":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60,"area":null},{"id":"2206.07704","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","created":"2022-06-15","cited_by_count":58,"area":null},{"id":"2308.09711","title":"Robust Monocular Depth Estimation under Challenging Conditions","created":"2023-08-18","cited_by_count":58,"area":null},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2403.17749","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","created":"2024-03-26","cited_by_count":58,"area":"moe"},{"id":"2312.14457","title":"QUAR-VLA: Vision-Language-Action Model for Quadruped Robots","created":"2023-12-22","cited_by_count":56,"area":"vla"},{"id":"2203.15793","title":"Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection","created":"2022-03-29","cited_by_count":55,"area":null},{"id":"2103.13318","title":"Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types","created":"2021-03-24","cited_by_count":54,"area":null},{"id":"2111.12780","title":"Transferability Estimation using Bhattacharyya Class Separability","created":"2021-11-24","cited_by_count":54,"area":null},{"id":"2407.00783","title":"Diffusion Models and Representation Learning: A Survey","created":"2024-06-30","cited_by_count":54,"area":"diffusion"},{"id":"2304.08408","title":"OVTrack: Open-Vocabulary Multiple Object Tracking","created":"2023-04-17","cited_by_count":53,"area":null},{"id":"2306.05401","title":"RDumb: A simple approach that questions our progress in continual test-time adaptation","created":"2023-06-08","cited_by_count":53,"area":null}],"next_cursor":"100"}