{"total":209,"rows":[{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412,"area":null},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350,"area":null},{"id":"2203.11991","title":"Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework","created":"2022-03-22","cited_by_count":330,"area":null},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281,"area":null},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220,"area":null},{"id":"2104.01538","title":"Hypercorrelation Squeeze for Few-Shot Segmentation","created":"2021-04-04","cited_by_count":193,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"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":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129,"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":"2203.11192","title":"Transforming Model Prediction for Tracking","created":"2022-03-21","cited_by_count":117,"area":null},{"id":"2204.00895","title":"Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation","created":"2022-04-02","cited_by_count":113,"area":"distill"},{"id":"2104.13202","title":"LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking","created":"2021-04-27","cited_by_count":96,"area":null},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84,"area":null},{"id":"2104.14545","title":"LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search","created":"2021-04-29","cited_by_count":82,"area":null},{"id":"2308.05140","title":"Robust Object Modeling for Visual Tracking","created":"2023-08-09","cited_by_count":80,"area":null},{"id":"2403.10574","title":"Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers","created":"2024-03-15","cited_by_count":76,"area":null},{"id":"2205.03806","title":"Transformer Tracking with Cyclic Shifting Window Attention","created":"2022-05-08","cited_by_count":75,"area":null},{"id":"2309.14611","title":"Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline","created":"2023-09-26","cited_by_count":73,"area":"distill"},{"id":"2108.00803","title":"Learn to Match: Automatic Matching Network Design for Visual Tracking","created":"2021-08-02","cited_by_count":67,"area":null},{"id":"2108.13962","title":"DepthTrack : Unveiling the Power of RGBD Tracking","created":"2021-08-31","cited_by_count":67,"area":null},{"id":"2403.09634","title":"OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning","created":"2024-03-14","cited_by_count":65,"area":null},{"id":"2304.01663","title":"On the Stability-Plasticity Dilemma of Class-Incremental Learning","created":"2023-04-04","cited_by_count":56,"area":null},{"id":"2211.11010","title":"Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric","created":"2022-11-20","cited_by_count":52,"area":null},{"id":"2301.10938","title":"Compact Transformer Tracker with Correlative Masked Modeling","created":"2023-01-26","cited_by_count":50,"area":null},{"id":"2401.03142","title":"Explicit Visual Prompts for Visual Object Tracking","created":"2024-01-06","cited_by_count":50,"area":null},{"id":"2403.16002","title":"SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking","created":"2024-03-24","cited_by_count":44,"area":"distill"},{"id":"2305.15688","title":"Frame-Event Alignment and Fusion Network for High Frame Rate Tracking","created":"2023-05-25","cited_by_count":43,"area":null},{"id":"2307.04129","title":"Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers","created":"2023-07-09","cited_by_count":43,"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":"2202.03630","title":"Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities","created":"2022-02-08","cited_by_count":38,"area":null},{"id":"2111.13394","title":"Non-IID data and Continual Learning processes in Federated Learning: A long road ahead","created":"2021-11-26","cited_by_count":36,"area":null},{"id":"2112.05752","title":"Specificity-Preserving Federated Learning for MR Image Reconstruction","created":"2021-12-09","cited_by_count":35,"area":null},{"id":"2107.10433","title":"MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking","created":"2021-07-22","cited_by_count":32,"area":null},{"id":"2101.08466","title":"Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking","created":"2021-01-21","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":"2104.02921","title":"Unsupervised Visual Attention and Invariance for Reinforcement Learning","created":"2021-04-07","cited_by_count":30,"area":null},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2108.03637","title":"Saliency-Associated Object Tracking","created":"2021-08-08","cited_by_count":30,"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":"2103.14938","title":"IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking","created":"2021-03-27","cited_by_count":25,"area":null},{"id":"2201.02526","title":"Learning Target-aware Representation for Visual Tracking via Informative Interactions","created":"2022-01-07","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":"2203.13537","title":"Efficient Visual Tracking via Hierarchical Cross-Attention Transformer","created":"2022-03-25","cited_by_count":24,"area":null},{"id":"2507.21606","title":"Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking","created":"2025-07-29","cited_by_count":23,"area":null},{"id":"2101.12159","title":"Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking","created":"2021-01-28","cited_by_count":22,"area":null},{"id":"2304.00571","title":"DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks","created":"2023-04-02","cited_by_count":22,"area":null},{"id":"2404.18174","title":"Mamba-FETrack: Frame-Event Tracking via State Space Model","created":"2024-04-28","cited_by_count":22,"area":"ssm"},{"id":"2108.12711","title":"Learning to Track Objects from Unlabeled Videos","created":"2021-08-28","cited_by_count":21,"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":"2304.14394","title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking","created":"2023-04-27","cited_by_count":21,"area":null},{"id":"2405.17773","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2306.17000","title":"MotionTrack: End-to-End Transformer-based Multi-Object Tracing with LiDAR-Camera Fusion","created":"2023-06-29","cited_by_count":19,"area":null},{"id":"2208.08829","title":"Learning Spatial-Frequency Transformer for Visual Object Tracking","created":"2022-08-18","cited_by_count":18,"area":null},{"id":"2103.16086","title":"Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking","created":"2021-03-30","cited_by_count":17,"area":null},{"id":"2401.02826","title":"CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras","created":"2024-01-05","cited_by_count":17,"area":null},{"id":"2302.07344","title":"Semi-Supervised Visual Tracking of Marine Animals using Autonomous Underwater Vehicles","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2308.12549","title":"Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking","created":"2023-08-24","cited_by_count":16,"area":null},{"id":"2104.00829","title":"Learning to Filter: Siamese Relation Network for Robust Tracking","created":"2021-04-02","cited_by_count":15,"area":null},{"id":"2112.02571","title":"Learning Tracking Representations via Dual-Branch Fully Transformer Networks","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2507.05899","title":"What You Have is What You Track: Adaptive and Robust Multimodal Tracking","created":"2025-07-08","cited_by_count":15,"area":null},{"id":"2105.03817","title":"TrTr: Visual Tracking with Transformer","created":"2021-05-09","cited_by_count":14,"area":null},{"id":"2203.13533","title":"High-Performance Transformer Tracking","created":"2022-03-25","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":"2208.05810","title":"Towards Sequence-Level Training for Visual Tracking","created":"2022-08-11","cited_by_count":13,"area":null},{"id":"2402.14392","title":"Reading Relevant Feature from Global Representation Memory for Visual Object Tracking","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2103.07302","title":"Siamese Infrared and Visible Light Fusion Network for RGB-T Tracking","created":"2021-03-12","cited_by_count":11,"area":null},{"id":"2104.12041","title":"Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy","created":"2021-04-25","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":"2203.14134","title":"RGBD Object Tracking: An In-depth Review","created":"2022-03-26","cited_by_count":11,"area":null},{"id":"2207.08044","title":"DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking","created":"2022-07-17","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":"2401.01674","title":"Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens","created":"2024-01-03","cited_by_count":11,"area":null},{"id":"2106.08710","title":"Mobile Augmented Reality: User Interfaces, Frameworks, and Intelligence","created":"2021-06-16","cited_by_count":10,"area":null},{"id":"2309.10171","title":"Specification-Driven Video Search via Foundation Models and Formal Verification","created":"2023-09-18","cited_by_count":10,"area":null},{"id":"2402.06187","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2505.19434","title":"CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2103.14496","title":"Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation","created":"2021-03-26","cited_by_count":9,"area":"distill"},{"id":"2105.11237","title":"SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking","created":"2021-05-24","cited_by_count":9,"area":null},{"id":"2109.07662","title":"Dynamic Fusion Network for RGBT Tracking","created":"2021-09-16","cited_by_count":9,"area":null},{"id":"2401.12743","title":"Correlation-Embedded Transformer Tracking: A Single-Branch Framework","created":"2024-01-23","cited_by_count":9,"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":"2101.06977","title":"Semi-Automatic Annotation For Visual Object Tracking","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2203.16092","title":"Global Tracking via Ensemble of Local Trackers","created":"2022-03-30","cited_by_count":8,"area":null},{"id":"2308.16386","title":"RGB-T Tracking via Multi-Modal Mutual Prompt Learning","created":"2023-08-31","cited_by_count":8,"area":null},{"id":"2310.14194","title":"Distractor-aware Event-based Tracking","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2312.14446","title":"Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset","created":"2023-12-22","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":"2507.23473","title":"CST Anti-UAV: A Thermal Infrared Benchmark for Tiny UAV Tracking in Complex Scenes","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2104.00403","title":"Target Transformed Regression for Accurate Tracking","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2106.04840","title":"Tracking by Joint Local and Global Search: A Target-aware Attention based Approach","created":"2021-06-09","cited_by_count":7,"area":null},{"id":"2111.04264","title":"Cross-Modal Object Tracking: Modality-Aware Representations and A Unified Benchmark","created":"2021-11-08","cited_by_count":7,"area":null},{"id":"2202.10881","title":"Coordinate-Aligned Multi-Camera Collaboration for Active Multi-Object Tracking","created":"2022-02-22","cited_by_count":7,"area":null},{"id":"2304.04264","title":"RGB-T Tracking Based on Mixed Attention","created":"2023-04-09","cited_by_count":7,"area":null},{"id":"2312.14471","title":"Prototype-based Cross-Modal Object Tracking","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2104.07303","title":"SiamCorners: Siamese Corner Networks for Visual Tracking","created":"2021-04-15","cited_by_count":6,"area":null},{"id":"2106.13516","title":"Multi-Domain Active Learning: Literature Review and Comparative Study","created":"2021-06-25","cited_by_count":6,"area":null},{"id":"2108.00187","title":"Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking","created":"2021-07-31","cited_by_count":6,"area":null},{"id":"2108.04521","title":"Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking","created":"2021-08-10","cited_by_count":6,"area":null},{"id":"2110.01812","title":"UHP-SOT: An Unsupervised High-Performance Single Object Tracker","created":"2021-10-05","cited_by_count":6,"area":null}],"next_cursor":"100"}