{"total":136,"rows":[{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315,"area":null},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","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":"2403.15951","title":"MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping","created":"2024-03-23","cited_by_count":68,"area":null},{"id":"2308.00783","title":"Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking","created":"2023-08-01","cited_by_count":67,"area":null},{"id":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60,"area":null},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50,"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":"2306.06211","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","created":"2023-05-12","cited_by_count":45,"area":null},{"id":"2312.08952","title":"UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation","created":"2023-12-14","cited_by_count":44,"area":null},{"id":"2305.14298","title":"MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking","created":"2023-05-23","cited_by_count":42,"area":null},{"id":"2310.06753","title":"TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning","created":"2023-10-10","cited_by_count":41,"area":null},{"id":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32,"area":null},{"id":"2406.00429","title":"Towards Generalizable Multi-Object Tracking","created":"2024-06-01","cited_by_count":23,"area":null},{"id":"2406.05039","title":"Bootstrapping Referring Multi-Object Tracking","created":"2024-06-07","cited_by_count":22,"area":null},{"id":"2410.01806","title":"Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking","created":"2024-10-02","cited_by_count":21,"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":"2309.06006","title":"SoccerNet 2023 Challenges Results","created":"2023-09-12","cited_by_count":20,"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":"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":"2504.04519","title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","created":"2025-04-06","cited_by_count":17,"area":null},{"id":"2405.12070","title":"AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements","created":"2024-05-20","cited_by_count":15,"area":null},{"id":"2405.06600","title":"Multi-Object Tracking in the Dark","created":"2024-05-10","cited_by_count":14,"area":null},{"id":"2403.12455","title":"CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2408.00969","title":"Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach","created":"2024-08-02","cited_by_count":13,"area":null},{"id":"2503.04565","title":"Omnidirectional Multi-Object Tracking","created":"2025-03-06","cited_by_count":13,"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":"2401.07080","title":"GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching","created":"2024-01-13","cited_by_count":12,"area":null},{"id":"2403.05021","title":"Beyond MOT: Semantic Multi-Object Tracking","created":"2024-03-08","cited_by_count":12,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2404.13868","title":"TeamTrack: A Dataset for Multi-Sport Multi-Object Tracking in Full-pitch Videos","created":"2024-04-22","cited_by_count":11,"area":null},{"id":"2503.10616","title":"OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer","created":"2025-03-13","cited_by_count":11,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2403.02767","title":"DeconfuseTrack:Dealing with Confusion for Multi-Object Tracking","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2405.11536","title":"RobMOT: Robust 3D Multi-Object Tracking by Observational Noise and State Estimation Drift Mitigation on LiDAR PointCloud","created":"2024-05-19","cited_by_count":9,"area":null},{"id":"2405.15755","title":"ETTrack: Enhanced Temporal Motion Predictor for Multi-Object Tracking","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2406.08324","title":"LaMOT: Language-Guided Multi-Object Tracking","created":"2024-06-12","cited_by_count":9,"area":null},{"id":"2410.11187","title":"Multiview Scene Graph","created":"2024-10-15","cited_by_count":9,"area":null},{"id":"2408.13243","title":"MCTR: Multi Camera Tracking Transformer","created":"2024-08-23","cited_by_count":8,"area":null},{"id":"2305.17648","title":"Z-GMOT: Zero-shot Generic Multiple Object Tracking","created":"2023-05-28","cited_by_count":7,"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":"2409.00487","title":"TrackSSM: A General Motion Predictor by State-Space Model","created":"2024-08-31","cited_by_count":6,"area":null},{"id":"2410.13437","title":"Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2501.11288","title":"PD-SORT: Occlusion-Robust Multi-Object Tracking Using Pseudo-Depth Cues","created":"2025-01-20","cited_by_count":6,"area":null},{"id":"2503.11496","title":"Cognitive Disentanglement for Referring Multi-Object Tracking","created":"2025-03-14","cited_by_count":6,"area":null},{"id":"2506.01373","title":"No Train Yet Gain: Towards Generic Multi-Object Tracking in Sports and Beyond","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2511.12389","title":"Calibrated Decomposition of Aleatoric and Epistemic Uncertainty in Deep Features for Inference-Time Adaptation","created":"2025-11-15","cited_by_count":6,"area":null},{"id":"2306.16772","title":"M3Act: Learning from Synthetic Human Group Activities","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2409.09293","title":"Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown","created":"2024-09-14","cited_by_count":5,"area":null},{"id":"2411.00553","title":"Is Multiple Object Tracking a Matter of Specialization?","created":"2024-11-01","cited_by_count":5,"area":null},{"id":"2505.22228","title":"GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2407.04926","title":"JDT3D: Addressing the Gaps in LiDAR-Based Tracking-by-Attention","created":"2024-07-06","cited_by_count":4,"area":null},{"id":"2411.14927","title":"LiDAR-based End-to-end Temporal Perception for Vehicle-Infrastructure Cooperation","created":"2024-11-22","cited_by_count":4,"area":null},{"id":"2502.13875","title":"MEX: Memory-efficient Approach to Referring Multi-Object Tracking","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2504.03258","title":"TQD-Track: Temporal Query Denoising for 3D Multi-Object Tracking","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2506.13457","title":"Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2506.18737","title":"USVTrack: USV-Based 4D Radar-Camera Tracking Dataset for Autonomous Driving in Inland Waterways","created":"2025-06-23","cited_by_count":4,"area":null},{"id":"2508.14370","title":"FastTracker: Real-Time and Accurate Visual Tracking","created":"2025-08-20","cited_by_count":4,"area":null},{"id":"2511.00510","title":"OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback","created":"2025-11-01","cited_by_count":4,"area":null},{"id":"2511.21053","title":"AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2309.10360","title":"OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking","created":"2023-09-19","cited_by_count":3,"area":null},{"id":"2403.16244","title":"On the Equivalency, Substitutability, and Flexibility of Synthetic Data","created":"2024-03-24","cited_by_count":3,"area":null},{"id":"2408.09191","title":"GSLAMOT: A Tracklet and Query Graph-based Simultaneous Locating, Mapping, and Multiple Object Tracking System","created":"2024-08-17","cited_by_count":3,"area":null},{"id":"2506.12105","title":"Multiple Object Tracking in Video SAR: A Benchmark and Tracking Baseline","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2509.02111","title":"NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2603.08128","title":"TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Same","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2604.18326","title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2310.17170","title":"DecoderTracker: Decoder-Only Method for Multiple-Object Tracking","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2405.14119","title":"Is a Pure Transformer Effective for Separated and Online Multi-Object Tracking?","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2406.04844","title":"Multi-Granularity Language-Guided Training for Multi-Object Tracking","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2407.01007","title":"GMT: Effective Global Framework for Multi-Camera Multi-Target Tracking","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2409.02490","title":"TP-GMOT: Tracking Generic Multiple Object by Textual Prompt with Motion-Appearance Cost (MAC) SORT","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2411.06780","title":"SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2412.12561","title":"Tell Me What to Track: Infusing Robust Language Guidance for Enhanced Referring Multi-Object Tracking","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2503.12562","title":"History-Aware Transformation of ReID Features for Multiple Object Tracking","created":"2025-03-16","cited_by_count":2,"area":null},{"id":"2511.18344","title":"A Tri-Modal Dataset and a Baseline System for Tracking Unmanned Aerial Vehicles","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2601.01925","title":"AR-MOT: Autoregressive Multi-object Tracking","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2603.01485","title":"SCATR: Mitigating New Instance Suppression in LiDAR-based Tracking-by-Attention via Second Chance Assignment and Track Query Dropout","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.21629","title":"Dual-level Adaptation for Multi-Object Tracking: Building Test-Time Calibration from Experience and Intuition","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2604.12665","title":"Hypergraph-State Collaborative Reasoning for Multi-Object Tracking","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2307.01013","title":"A Synthetic Benchmarking Pipeline to Compare Camera Calibration Algorithms","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2309.12035","title":"BASE: Probably a Better Approach to Multi-Object Tracking","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2312.17641","title":"Motion State: A New Benchmark Multiple Object Tracking","created":"2023-12-29","cited_by_count":1,"area":null},{"id":"2404.02562","title":"Representation Alignment Contrastive Regularization for Multi-Object Tracking","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2407.14086","title":"Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2409.14220","title":"Temporally Propagated Masks and Bounding Boxes: Combining the Best of Both Worlds for Multi-Object Tracking","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2410.09243","title":"Enhanced Kalman with Adaptive Appearance Motion SORT for Grounded Generic Multiple Object Tracking","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2410.23907","title":"IP-MOT: Instance Prompt Learning for Cross-Domain Multi-Object Tracking","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2411.11514","title":"Learning a Neural Association Network for Self-supervised Multi-Object Tracking","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2411.15811","title":"FastTrackTr:Towards Fast Multi-Object Tracking with Transformers","created":"2024-11-24","cited_by_count":1,"area":null},{"id":"2503.08145","title":"Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2506.00774","title":"Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Tracking","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2508.20892","title":"To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.21715","title":"Motion-Aware Transformer for Multi-Object Tracking","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2511.19475","title":"Tracking and Segmenting Anything in Any Modality","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2512.02392","title":"From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2602.17231","title":"HiMAP: History-aware Map-occupancy Prediction with Fallback","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2603.17889","title":"Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2604.13571","title":"Radar-Informed 3D Multi-Object Tracking under Adverse Conditions","created":"2026-04-15","cited_by_count":1,"area":null}],"next_cursor":"100"}