{"total":265,"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":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518,"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":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381,"area":null},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320,"area":null},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213,"area":null},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"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":"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":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128,"area":null},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127,"area":null},{"id":"2103.14258","title":"Learning to Track with Object Permanence","created":"2021-03-26","cited_by_count":119,"area":null},{"id":"2203.16761","title":"MeMOT: Multi-Object Tracking with Memory","created":"2022-03-31","cited_by_count":114,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2403.14610","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","created":"2024-03-21","cited_by_count":94,"area":null},{"id":"2104.00194","title":"TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking","created":"2021-04-01","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":"2307.15700","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","created":"2023-07-28","cited_by_count":88,"area":null},{"id":"2204.06918","title":"SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos","created":"2022-04-14","cited_by_count":80,"area":null},{"id":"2303.12776","title":"Dense Distinct Query for End-to-End Object Detection","created":"2023-03-22","cited_by_count":77,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"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":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2104.03541","title":"Multiple Object Tracking with Correlation Learning","created":"2021-04-08","cited_by_count":67,"area":null},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","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":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60,"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":"2105.04322","title":"RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation","created":"2021-05-10","cited_by_count":52,"area":null},{"id":"2207.02541","title":"Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection","created":"2022-07-06","cited_by_count":48,"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":"2206.04656","title":"Simple Cues Lead to a Strong Multi-Object Tracker","created":"2022-06-09","cited_by_count":44,"area":null},{"id":"2103.13516","title":"Tracking Pedestrian Heads in Dense Crowd","created":"2021-03-24","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":"2412.09586","title":"Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders","created":"2024-12-12","cited_by_count":36,"area":null},{"id":"2503.07465","title":"YOLOE: Real-Time Seeing Anything","created":"2025-03-10","cited_by_count":36,"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":"2111.11892","title":"LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking","created":"2021-11-23","cited_by_count":34,"area":null},{"id":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"area":null},{"id":"2203.14208","title":"Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking","created":"2022-03-27","cited_by_count":33,"area":null},{"id":"2212.06137","title":"NMS Strikes Back","created":"2022-12-12","cited_by_count":33,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","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":"2203.15175","title":"Unified Transformer Tracker for Object Tracking","created":"2022-03-29","cited_by_count":31,"area":null},{"id":"2203.16089","title":"Omni-DETR: Omni-Supervised Object Detection with Transformers","created":"2022-03-30","cited_by_count":29,"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":"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":"2304.09502","title":"Sampling is Matter: Point-guided 3D Human Mesh Reconstruction","created":"2023-04-19","cited_by_count":24,"area":null},{"id":"2107.02396","title":"Semi-TCL: Semi-Supervised Track Contrastive Representation Learning","created":"2021-07-06","cited_by_count":23,"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":"2103.14829","title":"Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers","created":"2021-03-27","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":"2305.12724","title":"Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking","created":"2023-05-22","cited_by_count":20,"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":"2207.11169","title":"Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark","created":"2022-07-22","cited_by_count":17,"area":null},{"id":"2212.01568","title":"Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation","created":"2022-12-03","cited_by_count":17,"area":null},{"id":"2106.10506","title":"Exploring Visual Context for Weakly Supervised Person Search","created":"2021-06-19","cited_by_count":16,"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":"2310.01926","title":"DARTH: Holistic Test-time Adaptation for Multiple Object Tracking","created":"2023-10-03","cited_by_count":15,"area":null},{"id":"2211.02175","title":"Large Scale Real-World Multi-Person Tracking","created":"2022-11-03","cited_by_count":14,"area":null},{"id":"2306.03597","title":"Human-Object Interaction Prediction in Videos through Gaze Following","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2308.11513","title":"TrackFlow: Multi-Object Tracking with Normalizing Flows","created":"2023-08-22","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":"2109.15068","title":"iShape: A First Step Towards Irregular Shape Instance Segmentation","created":"2021-09-30","cited_by_count":12,"area":null},{"id":"2304.06354","title":"ODAM: Gradient-based instance-specific visual explanations for object detection","created":"2023-04-13","cited_by_count":12,"area":null},{"id":"2307.15409","title":"Uncertainty-aware Unsupervised Multi-Object Tracking","created":"2023-07-28","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":"2411.13842","title":"Detecting Human Artifacts from Text-to-Image Models","created":"2024-11-21","cited_by_count":12,"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":"2303.17228","title":"Streaming Video Model","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2308.05911","title":"Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object Tracking","created":"2023-08-11","cited_by_count":10,"area":null},{"id":"2311.01025","title":"Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection","created":"2023-11-02","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":"2207.07454","title":"Multi-Object Tracking and Segmentation via Neural Message Passing","created":"2022-07-15","cited_by_count":9,"area":null},{"id":"2302.09043","title":"Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences","created":"2023-02-17","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":"2502.20249","title":"Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels","created":"2025-02-27","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":"2210.09455","title":"Track Targets by Dense Spatio-Temporal Position Encoding","created":"2022-10-17","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":"2303.11567","title":"One-to-Few Label Assignment for End-to-End Dense Detection","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2309.00942","title":"Tracking without Label: Unsupervised Multiple Object Tracking via Contrastive Similarity Learning","created":"2023-09-02","cited_by_count":8,"area":null},{"id":"2312.11716","title":"Squeezed Edge YOLO: Onboard Object Detection on Edge Devices","created":"2023-12-18","cited_by_count":8,"area":null},{"id":"2407.04249","title":"FeatureSORT: Essential Features for Effective Tracking","created":"2024-07-05","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":"2208.03727","title":"Robust Multi-Object Tracking by Marginal Inference","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2402.15297","title":"Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling","created":"2024-02-23","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":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2108.08836","title":"Multi-Object Tracking with Hallucinated and Unlabeled Videos","created":"2021-08-19","cited_by_count":6,"area":null}],"next_cursor":"100"}