{"total":113,"rows":[{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131,"area":null},{"id":"2103.16746","title":"Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark","created":"2021-03-31","cited_by_count":126,"area":null},{"id":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126,"area":null},{"id":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70,"area":null},{"id":"2411.17576","title":"A Distractor-Aware Memory for Visual Object Tracking with SAM2","created":"2024-11-26","cited_by_count":66,"area":null},{"id":"2102.04420","title":"The Multi-Temporal Urban Development SpaceNet Dataset","created":"2021-02-08","cited_by_count":62,"area":null},{"id":"2107.02156","title":"Do Different Tracking Tasks Require Different Appearance Models?","created":"2021-07-05","cited_by_count":62,"area":null},{"id":"2108.06455","title":"PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds","created":"2021-08-14","cited_by_count":59,"area":null},{"id":"2111.04426","title":"3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds","created":"2021-11-08","cited_by_count":54,"area":null},{"id":"2104.11221","title":"Opening up Open-World Tracking","created":"2021-04-22","cited_by_count":50,"area":null},{"id":"2112.02838","title":"Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook","created":"2021-12-06","cited_by_count":46,"area":null},{"id":"2108.05630","title":"3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud","created":"2021-08-12","cited_by_count":45,"area":null},{"id":"2207.11995","title":"3D Siamese Transformer Network for Single Object Tracking on Point Clouds","created":"2022-07-25","cited_by_count":44,"area":null},{"id":"2112.07957","title":"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker","created":"2021-12-15","cited_by_count":38,"area":null},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2211.08542","title":"CXTrack: Improving 3D Point Cloud Tracking with Contextual Information","created":"2022-11-12","cited_by_count":28,"area":null},{"id":"2209.00860","title":"Real-time 3D Single Object Tracking with Transformer","created":"2022-09-02","cited_by_count":27,"area":null},{"id":"2301.03213","title":"EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset","created":"2023-01-09","cited_by_count":27,"area":null},{"id":"2201.07425","title":"WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking","created":"2022-01-19","cited_by_count":26,"area":null},{"id":"2403.03493","title":"VastTrack: Vast Category Visual Object Tracking","created":"2024-03-06","cited_by_count":26,"area":null},{"id":"2103.06028","title":"Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences","created":"2021-03-10","cited_by_count":25,"area":null},{"id":"2209.13502","title":"Visual Object Tracking in First Person Vision","created":"2022-09-27","cited_by_count":25,"area":null},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24,"area":null},{"id":"2303.05071","title":"MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors","created":"2023-03-09","cited_by_count":24,"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":"2405.12139","title":"DTLLM-VLT: Diverse Text Generation for Visual Language Tracking Based on LLM","created":"2024-05-20","cited_by_count":24,"area":null},{"id":"2302.06294","title":"CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection","created":"2023-02-13","cited_by_count":23,"area":null},{"id":"2404.09857","title":"Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL","created":"2024-04-15","cited_by_count":23,"area":"offlinerl"},{"id":"2103.06533","title":"Triple-cooperative Video Shadow Detection","created":"2021-03-11","cited_by_count":22,"area":null},{"id":"2208.06888","title":"AVisT: A Benchmark for Visual Object Tracking in Adverse Visibility","created":"2022-08-14","cited_by_count":22,"area":null},{"id":"2108.13665","title":"Is First Person Vision Challenging for Object Tracking?","created":"2021-08-31","cited_by_count":21,"area":null},{"id":"2208.05216","title":"Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer","created":"2022-08-10","cited_by_count":18,"area":null},{"id":"2412.09754","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","created":"2024-12-12","cited_by_count":17,"area":"mllm"},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2302.03022","title":"SurgT challenge: Benchmark of Soft-Tissue Trackers for Robotic Surgery","created":"2023-02-06","cited_by_count":14,"area":null},{"id":"2207.02088","title":"SiamMask: A Framework for Fast Online Object Tracking and Segmentation","created":"2022-07-05","cited_by_count":13,"area":null},{"id":"2410.02492","title":"DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM","created":"2024-10-03","cited_by_count":12,"area":null},{"id":"2111.14465","title":"Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2202.05659","title":"Tiny Object Tracking: A Large-scale Dataset and A Baseline","created":"2022-02-11","cited_by_count":11,"area":"distill"},{"id":"2209.04284","title":"Tracking Small and Fast Moving Objects: A Benchmark","created":"2022-09-09","cited_by_count":11,"area":null},{"id":"2212.11920","title":"Beyond SOT: Tracking Multiple Generic Objects at Once","created":"2022-12-22","cited_by_count":11,"area":null},{"id":"2307.14630","title":"360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking","created":"2023-07-27","cited_by_count":11,"area":null},{"id":"2406.09754","title":"LAVIB: A Large-scale Video Interpolation Benchmark","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2102.11958","title":"The SpaceNet Multi-Temporal Urban Development Challenge","created":"2021-02-23","cited_by_count":10,"area":null},{"id":"2106.08762","title":"Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects","created":"2021-06-16","cited_by_count":10,"area":null},{"id":"2204.07414","title":"SOTVerse: A User-defined Task Space of Single Object Tracking","created":"2022-04-15","cited_by_count":10,"area":null},{"id":"2412.02734","title":"MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues","created":"2024-12-03","cited_by_count":10,"area":null},{"id":"2508.05221","title":"ReasoningTrack: Chain-of-Thought Reasoning for Long-term Vision-Language Tracking","created":"2025-08-07","cited_by_count":9,"area":"lr"},{"id":"2511.15580","title":"CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Tracking","created":"2025-11-19","cited_by_count":9,"area":null},{"id":"2303.07605","title":"Modeling Continuous Motion for 3D Point Cloud Object Tracking","created":"2023-03-14","cited_by_count":8,"area":null},{"id":"2404.13953","title":"360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos","created":"2024-04-22","cited_by_count":8,"area":null},{"id":"2203.08581","title":"A Survey on Infrared Image and Video Sets","created":"2022-03-16","cited_by_count":7,"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":"2505.20718","title":"VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2108.00187","title":"Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking","created":"2021-07-31","cited_by_count":6,"area":null},{"id":"2402.16249","title":"SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Tracking","created":"2024-02-26","cited_by_count":6,"area":null},{"id":"2412.00744","title":"Open-World Drone Active Tracking with Goal-Centered Rewards","created":"2024-12-01","cited_by_count":6,"area":"deeprl"},{"id":"2504.00848","title":"Zero-Shot 4D Lidar Panoptic Segmentation","created":"2025-04-01","cited_by_count":6,"area":null},{"id":"2505.04147","title":"R^3-VQA: \"Read the Room\" by Video Social Reasoning","created":"2025-05-07","cited_by_count":6,"area":"lr"},{"id":"2210.08518","title":"OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds","created":"2022-10-16","cited_by_count":5,"area":null},{"id":"2302.00930","title":"Adaptive Siamese Tracking with a Compact Latent Network","created":"2023-02-02","cited_by_count":5,"area":null},{"id":"2304.06419","title":"Tracking by 3D Model Estimation of Unknown Objects in Videos","created":"2023-04-13","cited_by_count":5,"area":null},{"id":"2502.20111","title":"MITracker: Multi-View Integration for Visual Object Tracking","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2203.13048","title":"Benchmarking Visual Localization for Autonomous Navigation","created":"2022-03-24","cited_by_count":4,"area":null},{"id":"2210.03436","title":"Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking","created":"2022-10-07","cited_by_count":4,"area":null},{"id":"2401.03872","title":"A New Dataset and a Distractor-Aware Architecture for Transparent Object Tracking","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2404.18143","title":"Tracking Transforming Objects: A Benchmark","created":"2024-04-28","cited_by_count":4,"area":null},{"id":"2501.10343","title":"3rd Workshop on Maritime Computer Vision (MaCVi) 2025: Challenge Results","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2509.11453","title":"Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Tracking","created":"2025-09-14","cited_by_count":4,"area":null},{"id":"2206.02619","title":"VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images","created":"2022-06-06","cited_by_count":3,"area":null},{"id":"2211.06663","title":"NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2303.12304","title":"SiamTHN: Siamese Target Highlight Network for Visual Tracking","created":"2023-03-22","cited_by_count":3,"area":null},{"id":"2309.02185","title":"BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye View","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2403.06479","title":"Ada-Tracker: Soft Tissue Tracking via Inter-Frame and Adaptive-Template Matching","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2407.01959","title":"FlowTrack: Point-level Flow Network for 3D Single Object Tracking","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2410.20421","title":"NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking","created":"2024-10-27","cited_by_count":3,"area":null},{"id":"2503.08208","title":"Explaining Human Preferences via Metrics for Structured 3D Reconstruction","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2604.21453","title":"Instance-level Visual Active Tracking with Occlusion-Aware Planning","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2201.02280","title":"Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping","created":"2022-01-07","cited_by_count":2,"area":null},{"id":"2204.11410","title":"Single Object Tracking Research: A Survey","created":"2022-04-25","cited_by_count":2,"area":null},{"id":"2206.02116","title":"Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos","created":"2022-06-05","cited_by_count":2,"area":null},{"id":"2303.07625","title":"PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking","created":"2023-03-14","cited_by_count":2,"area":null},{"id":"2404.07495","title":"PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Clouds","created":"2024-04-11","cited_by_count":2,"area":null},{"id":"2408.11463","title":"Low-Light Object Tracking: A Benchmark","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2408.13877","title":"Camouflaged Object Tracking: A Benchmark","created":"2024-08-25","cited_by_count":2,"area":null},{"id":"2412.02129","title":"GSOT3D: Towards Generic 3D Single Object Tracking in the Wild","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2504.01321","title":"COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2509.13864","title":"Distractor-Aware Memory-Based Visual Object Tracking","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2609.07738","title":"TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Tracking","created":"2026-09-07","cited_by_count":2,"area":null},{"id":"2103.15970","title":"Does it work outside this benchmark? Introducing the Rigid Depth Constructor tool, depth validation dataset construction in rigid scenes for the masses","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2110.10206","title":"Evaluating and Improving Interactions with Hazy Oracles","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2111.06994","title":"Learning Online for Unified Segmentation and Tracking Models","created":"2021-11-12","cited_by_count":1,"area":null},{"id":"2401.13285","title":"Small Object Tracking in LiDAR Point Cloud: Learning the Target-awareness Prototype and Fine-grained Search Region","created":"2024-01-24","cited_by_count":1,"area":null},{"id":"2407.05235","title":"Tracking Reflected Objects: A Benchmark","created":"2024-07-07","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":"2507.16015","title":"Is Tracking really more challenging in First Person Egocentric Vision?","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2102.06733","title":"Revisiting the details when evaluating a visual tracker","created":"2021-01-25","cited_by_count":0,"area":null},{"id":"2103.01222","title":"Multiple Convolutional Features in Siamese Networks for Object Tracking","created":"2021-03-01","cited_by_count":0,"area":null},{"id":"2105.12661","title":"Detecting Biological Locomotion in Video: A Computational Approach","created":"2021-05-26","cited_by_count":0,"area":null},{"id":"2202.03695","title":"Network Comparison Study of Deep Activation Feature Discriminability with Novel Objects","created":"2022-02-08","cited_by_count":0,"area":null}],"next_cursor":"100"}