{"total":320,"rows":[{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158,"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":"2302.11813","title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","created":"2023-02-23","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":"2411.11922","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","created":"2024-11-18","cited_by_count":94,"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":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66,"area":null},{"id":"2303.10404","title":"MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking","created":"2023-03-18","cited_by_count":64,"area":null},{"id":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60,"area":null},{"id":"2403.02075","title":"DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction","created":"2024-03-04","cited_by_count":59,"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":"2308.09905","title":"DiffusionTrack: Diffusion Model For Multi-Object Tracking","created":"2023-08-19","cited_by_count":40,"area":"diffusion"},{"id":"2405.08909","title":"ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association","created":"2024-05-14","cited_by_count":33,"area":null},{"id":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32,"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":"2306.13074","title":"Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports","created":"2023-06-22","cited_by_count":29,"area":null},{"id":"2305.13495","title":"Type-to-Track: Retrieve Any Object via Prompt-based Tracking","created":"2023-05-22","cited_by_count":24,"area":null},{"id":"2406.00429","title":"Towards Generalizable Multi-Object Tracking","created":"2024-06-01","cited_by_count":23,"area":null},{"id":"2304.07500","title":"The 7th AI City Challenge","created":"2023-04-15","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":"2303.12079","title":"OmniTracker: Unifying Object Tracking by Tracking-with-Detection","created":"2023-03-21","cited_by_count":19,"area":null},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2312.07352","title":"CholecTrack20: A Multi-Perspective Tracking Dataset for Surgical Tools","created":"2023-12-12","cited_by_count":17,"area":null},{"id":"2409.16149","title":"MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2404.09432","title":"The 8th AI City Challenge","created":"2024-04-15","cited_by_count":16,"area":null},{"id":"2408.13003","title":"BoostTrack++: using tracklet information to detect more objects in multiple object tracking","created":"2024-08-23","cited_by_count":16,"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":"2405.17698","title":"BaboonLand Dataset: Tracking Primates in the Wild and Automating Behaviour Recognition from Drone Videos","created":"2024-05-27","cited_by_count":14,"area":null},{"id":"2411.06896","title":"BuckTales : A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2401.09942","title":"Multi-task Learning for Joint Re-identification, Team Affiliation, and Role Classification for Sports Visual Tracking","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","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":"2310.17875","title":"Siamese-DETR for Generic Multi-Object Tracking","created":"2023-10-27","cited_by_count":11,"area":null},{"id":"2402.12763","title":"BronchoTrack: Airway Lumen Tracking for Branch-Level Bronchoscopic Localization","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2404.01686","title":"JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments","created":"2024-04-02","cited_by_count":11,"area":null},{"id":"2411.02136","title":"Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery","created":"2024-11-04","cited_by_count":11,"area":null},{"id":"2411.16934","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2502.20678","title":"STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding","created":"2025-02-28","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":"2501.17053","title":"Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding","created":"2025-01-28","cited_by_count":10,"area":null},{"id":"2304.04376","title":"ICDAR 2023 Video Text Reading Competition for Dense and Small Text","created":"2023-04-10","cited_by_count":9,"area":null},{"id":"2304.09471","title":"Enhancing Multi-Camera People Tracking with Anchor-Guided Clustering and Spatio-Temporal Consistency ID Re-Assignment","created":"2023-04-19","cited_by_count":9,"area":null},{"id":"2311.01423","title":"CenterRadarNet: Joint 3D Object Detection and Tracking Framework using 4D FMCW Radar","created":"2023-11-02","cited_by_count":9,"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":"2405.15755","title":"ETTrack: Enhanced Temporal Motion Predictor for Multi-Object Tracking","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2411.08216","title":"GTA: Global Tracklet Association for Multi-Object Tracking in Sports","created":"2024-11-12","cited_by_count":9,"area":null},{"id":"2509.15178","title":"Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding","created":"2025-09-18","cited_by_count":9,"area":"mllm"},{"id":"2311.10361","title":"Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration","created":"2023-11-17","cited_by_count":8,"area":null},{"id":"2402.09865","title":"Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2403.08018","title":"Learning Data Association for Multi-Object Tracking using Only Coordinates","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2403.10826","title":"MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking","created":"2024-03-16","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":"2305.17648","title":"Z-GMOT: Zero-shot Generic Multiple Object Tracking","created":"2023-05-28","cited_by_count":7,"area":null},{"id":"2309.13393","title":"AgriSORT: A Simple Online Real-time Tracking-by-Detection framework for robotics in precision agriculture","created":"2023-09-23","cited_by_count":7,"area":null},{"id":"2311.14762","title":"The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024","created":"2023-11-23","cited_by_count":7,"area":null},{"id":"2408.16638","title":"3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach","created":"2024-08-29","cited_by_count":7,"area":null},{"id":"2406.05810","title":"ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Driving","created":"2024-06-09","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":"2501.07360","title":"TimberVision: A Multi-Task Dataset and Framework for Log-Component Segmentation and Tracking in Autonomous Forestry Operations","created":"2025-01-13","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":"2510.00405","title":"EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observations","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2211.07173","title":"SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenes","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2309.09765","title":"Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections","created":"2023-09-18","cited_by_count":5,"area":null},{"id":"2311.10382","title":"Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking","created":"2023-11-17","cited_by_count":5,"area":null},{"id":"2312.05923","title":"Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting","created":"2023-12-10","cited_by_count":5,"area":null},{"id":"2312.08764","title":"CattleEyeView: A Multi-task Top-down View Cattle Dataset for Smarter Precision Livestock Farming","created":"2023-12-14","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":"2404.05518","title":"DepthMOT: Depth Cues Lead to a Strong Multi-Object Tracker","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2408.09860","title":"3D-Aware Instance Segmentation and Tracking in Egocentric Videos","created":"2024-08-19","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":"2410.17534","title":"OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking","created":"2024-10-23","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":"2506.17590","title":"DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For Driving","created":"2025-06-21","cited_by_count":5,"area":"lr"},{"id":"2509.01157","title":"MVTrajecter: Multi-View Pedestrian Tracking with Trajectory Motion Cost and Trajectory Appearance Cost","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2305.16555","title":"CVB: A Video Dataset of Cattle Visual Behaviors","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2310.03006","title":"COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking","created":"2023-10-04","cited_by_count":4,"area":null},{"id":"2311.03561","title":"Sea You Later: Metadata-Guided Long-Term Re-Identification for UAV-Based Multi-Object Tracking","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2311.10261","title":"Vision meets mmWave Radar: 3D Object Perception Benchmark for Autonomous Driving","created":"2023-11-17","cited_by_count":4,"area":null},{"id":"2403.11978","title":"Pedestrian Tracking with Monocular Camera using Unconstrained 3D Motion Model","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2406.19655","title":"Basketball-SORT: An Association Method for Complex Multi-object Occlusion Problems in Basketball Multi-object Tracking","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2407.00738","title":"Engineering an Efficient Object Tracker for Non-Linear Motion","created":"2024-06-30","cited_by_count":4,"area":null},{"id":"2409.17221","title":"Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2411.06702","title":"Track Any Peppers: Weakly Supervised Sweet Pepper Tracking Using VLMs","created":"2024-11-11","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":"2503.10701","title":"Video Individual Counting for Moving Drones","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2503.17237","title":"Strong Baseline: Multi-UAV Tracking via YOLOv12 with BoT-SORT-ReID","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2503.18282","title":"TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2505.01257","title":"CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking","created":"2025-05-02","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":"2508.19182","title":"SoccerNet 2025 Challenges Results","created":"2025-08-26","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":"2512.07776","title":"GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring","created":"2025-12-08","cited_by_count":4,"area":null},{"id":"2604.22506","title":"ICPR 2026 Competition on Low-Resolution License Plate Recognition","created":"2026-04-24","cited_by_count":4,"area":null},{"id":"2212.03586","title":"Multiple Object Tracking Challenge Technical Report for Team MT_IoT","created":"2022-12-07","cited_by_count":3,"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":"2405.20333","title":"SurgiTrack: Fine-Grained Multi-Class Multi-Tool Tracking in Surgical Videos","created":"2024-05-30","cited_by_count":3,"area":null}],"next_cursor":"100"}