{"total":172,"rows":[{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823,"area":null},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354,"area":"diffusion"},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"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":"2303.17602","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","created":"2023-03-30","cited_by_count":96,"area":null},{"id":"2207.07078","title":"Towards Grand Unification of Object Tracking","created":"2022-07-14","cited_by_count":93,"area":null},{"id":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91,"area":null},{"id":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80,"area":null},{"id":"2408.10845","title":"CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving","created":"2024-08-19","cited_by_count":77,"area":"driving"},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67,"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":"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":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54,"area":null},{"id":"2105.04322","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","created":"2021-05-10","cited_by_count":52,"area":null},{"id":"2306.05238","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2106.11118","title":"SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving","created":"2021-06-21","cited_by_count":43,"area":null},{"id":"2103.11617","title":"Anchor-Free Person Search","created":"2021-03-22","cited_by_count":42,"area":null},{"id":"2103.15145","title":"TransCenter: Transformers with Dense Representations for Multiple-Object Tracking","created":"2021-03-28","cited_by_count":42,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2207.05518","title":"Tracking Objects as Pixel-wise Distributions","created":"2022-07-12","cited_by_count":37,"area":null},{"id":"2204.01026","title":"STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes","created":"2022-04-03","cited_by_count":35,"area":null},{"id":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33,"area":null},{"id":"2203.07669","title":"Progressive End-to-End Object Detection in Crowded Scenes","created":"2022-03-15","cited_by_count":31,"area":null},{"id":"2211.08824","title":"SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking","created":"2022-11-16","cited_by_count":29,"area":null},{"id":"2106.11346","title":"GAIA: A Transfer Learning System of Object Detection that Fits Your Needs","created":"2021-06-21","cited_by_count":27,"area":null},{"id":"2204.09848","title":"Weakly Aligned Feature Fusion for Multimodal Object Detection","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2212.08914","title":"Are We Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark","created":"2022-12-17","cited_by_count":26,"area":null},{"id":"2104.09441","title":"One More Check: Making \"Fake Background\" Be Tracked Again","created":"2021-04-19","cited_by_count":25,"area":null},{"id":"2302.14589","title":"Focus On Details: Online Multi-object Tracking with Diverse Fine-grained Representation","created":"2023-02-28","cited_by_count":25,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2203.07845","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","created":"2022-03-15","cited_by_count":21,"area":null},{"id":"2303.15334","title":"ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box","created":"2023-03-27","cited_by_count":20,"area":null},{"id":"2203.09338","title":"Object Localization under Single Coarse Point Supervision","created":"2022-03-17","cited_by_count":19,"area":null},{"id":"2303.12079","title":"OmniTracker: Unifying Object Tracking by Tracking-with-Detection","created":"2023-03-21","cited_by_count":19,"area":null},{"id":"2304.03135","title":"VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision","created":"2023-04-06","cited_by_count":19,"area":null},{"id":"2403.04700","title":"Delving into the Trajectory Long-tail Distribution for Muti-object Tracking","created":"2024-03-07","cited_by_count":18,"area":null},{"id":"2201.01297","title":"Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation","created":"2022-01-04","cited_by_count":16,"area":null},{"id":"2203.14387","title":"Towards Domain Generalization in Object Detection","created":"2022-03-27","cited_by_count":16,"area":null},{"id":"2205.00968","title":"Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker","created":"2022-05-02","cited_by_count":15,"area":null},{"id":"2103.10621","title":"Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement","created":"2021-03-19","cited_by_count":13,"area":null},{"id":"2203.10939","title":"Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2407.11464","title":"Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2206.00527","title":"Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baseline","created":"2022-06-01","cited_by_count":12,"area":null},{"id":"2309.04682","title":"DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions","created":"2023-09-09","cited_by_count":12,"area":null},{"id":"2110.04119","title":"A Multi-viewpoint Outdoor Dataset for Human Action Recognition","created":"2021-10-07","cited_by_count":11,"area":null},{"id":"2312.02878","title":"Towards More Practical Group Activity Detection: A New Benchmark and Model","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2505.23179","title":"DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes","created":"2025-05-29","cited_by_count":11,"area":null},{"id":"2104.12389","title":"Variational Pedestrian Detection","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2407.10125","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","created":"2024-07-14","cited_by_count":10,"area":null},{"id":"2108.09376","title":"BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies","created":"2021-08-20","cited_by_count":9,"area":null},{"id":"2310.09668","title":"Beyond Testers' Biases: Guiding Model Testing with Knowledge Bases using LLMs","created":"2023-10-14","cited_by_count":9,"area":null},{"id":"2312.05525","title":"You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-Person Multi-Task Human-Centric Perception","created":"2023-12-09","cited_by_count":9,"area":null},{"id":"2201.03176","title":"Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond","created":"2022-01-10","cited_by_count":8,"area":null},{"id":"2205.10766","title":"Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2210.12758","title":"Beta R-CNN: Looking into Pedestrian Detection from Another Perspective","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2304.11805","title":"OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2401.07801","title":"Pedestrian Detection in Low-Light Conditions: A Comprehensive Survey","created":"2024-01-15","cited_by_count":8,"area":null},{"id":"2101.04307","title":"LLA: Loss-aware Label Assignment for Dense Pedestrian Detection","created":"2021-01-12","cited_by_count":7,"area":null},{"id":"2104.14805","title":"Few-Shot Video Object Detection","created":"2021-04-30","cited_by_count":7,"area":null},{"id":"2106.02426","title":"NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2308.02935","title":"Bias Behind the Wheel: Fairness Testing of Autonomous Driving Systems","created":"2023-08-05","cited_by_count":7,"area":null},{"id":"2404.11426","title":"SPAMming Labels: Efficient Annotations for the Trackers of Tomorrow","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2203.03985","title":"SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking","created":"2022-03-08","cited_by_count":6,"area":null},{"id":"2204.02081","title":"Real-time Online Multi-Object Tracking in Compressed Domain","created":"2022-04-05","cited_by_count":6,"area":null},{"id":"2211.07501","title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2211.12110","title":"Improving Crowded Object Detection via Copy-Paste","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2308.07537","title":"AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes","created":"2023-08-15","cited_by_count":6,"area":null},{"id":"2311.08043","title":"Contrastive Learning for Multi-Object Tracking with Transformers","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2403.13803","title":"Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2106.10309","title":"Towards Single Stage Weakly Supervised Semantic Segmentation","created":"2021-06-18","cited_by_count":5,"area":null},{"id":"2109.00211","title":"Efficient Person Search: An Anchor-Free Approach","created":"2021-09-01","cited_by_count":5,"area":null},{"id":"2205.10184","title":"E-Scooter Rider Detection and Classification in Dense Urban Environments","created":"2022-05-20","cited_by_count":5,"area":null},{"id":"2212.07652","title":"Body-Part Joint Detection and Association via Extended Object Representation","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2212.09408","title":"Universal Object Detection with Large Vision Model","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2309.08771","title":"Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors","created":"2023-09-15","cited_by_count":5,"area":null},{"id":"2403.20225","title":"MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2108.10543","title":"Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting","created":"2021-08-24","cited_by_count":4,"area":null},{"id":"2206.07510","title":"Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2212.04111","title":"Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Framework","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2212.05717","title":"Feature Calibration Network for Occluded Pedestrian Detection","created":"2022-12-12","cited_by_count":4,"area":null},{"id":"2303.02575","title":"MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition","created":"2023-03-05","cited_by_count":4,"area":null},{"id":"2504.09361","title":"PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking","created":"2025-04-12","cited_by_count":4,"area":null},{"id":"2102.00595","title":"Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detection","created":"2021-02-01","cited_by_count":3,"area":null},{"id":"2102.11730","title":"RGB-D Railway Platform Monitoring and Scene Understanding for Enhanced Passenger Safety","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2208.02580","title":"SOMPT22: A Surveillance Oriented Multi-Pedestrian Tracking Dataset","created":"2022-08-04","cited_by_count":3,"area":null},{"id":"2210.15586","title":"Joint Multi-Person Body Detection and Orientation Estimation via One Unified Embedding","created":"2022-10-27","cited_by_count":3,"area":null},{"id":"2212.06218","title":"Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Dataset","created":"2022-12-12","cited_by_count":3,"area":null},{"id":"2305.09401","title":"Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian Detection","created":"2023-05-16","cited_by_count":3,"area":"diffusion"},{"id":"2305.10801","title":"Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2307.05874","title":"Multi-Object Tracking as Attention Mechanism","created":"2023-07-12","cited_by_count":3,"area":null},{"id":"2309.08036","title":"BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture","created":"2023-09-14","cited_by_count":3,"area":null},{"id":"2312.06306","title":"Attribute Annotation and Bias Evaluation in Visual Datasets for Autonomous Driving","created":"2023-12-11","cited_by_count":3,"area":null},{"id":"2404.19299","title":"Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bank","created":"2024-04-30","cited_by_count":3,"area":null},{"id":"2501.13710","title":"YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2104.03106","title":"V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection","created":"2021-04-07","cited_by_count":2,"area":null},{"id":"2111.08974","title":"Pedestrian Detection by Exemplar-Guided Contrastive Learning","created":"2021-11-17","cited_by_count":2,"area":null},{"id":"2205.04812","title":"The Impact of Partial Occlusion on Pedestrian Detectability","created":"2022-05-10","cited_by_count":2,"area":null},{"id":"2206.08172","title":"RefCrowd: Grounding the Target in Crowd with Referring Expressions","created":"2022-06-16","cited_by_count":2,"area":null}],"next_cursor":"100"}