{"total":53,"rows":[{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142,"area":null},{"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":"2204.04120","title":"Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline","created":"2022-04-08","cited_by_count":91,"area":null},{"id":"2304.05172","title":"LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images","created":"2023-04-11","cited_by_count":87,"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":"2412.15691","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","created":"2024-12-20","cited_by_count":57,"area":null},{"id":"2312.10611","title":"Bi-directional Adapter for Multi-modal Tracking","created":"2023-12-17","cited_by_count":46,"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":"2309.01728","title":"Generative-based Fusion Mechanism for Multi-Modal Tracking","created":"2023-09-04","cited_by_count":33,"area":null},{"id":"2401.01244","title":"Temporal Adaptive RGBT Tracking with Modality Prompt","created":"2024-01-02","cited_by_count":30,"area":null},{"id":"2507.20177","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","created":"2025-07-27","cited_by_count":30,"area":null},{"id":"2201.08673","title":"Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking","created":"2022-01-21","cited_by_count":26,"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":"2312.16244","title":"Modality-missing RGBT Tracking: Invertible Prompt Learning and High-quality Benchmarks","created":"2023-12-25","cited_by_count":17,"area":null},{"id":"2408.08827","title":"RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba","created":"2024-08-16","cited_by_count":17,"area":"ssm"},{"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":"2408.02222","title":"Cross-modulated Attention Transformer for RGBT Tracking","created":"2024-08-05","cited_by_count":14,"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":"2401.01674","title":"Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens","created":"2024-01-03","cited_by_count":11,"area":null},{"id":"2410.11586","title":"Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation","created":"2024-10-15","cited_by_count":11,"area":"distill"},{"id":"2511.17967","title":"CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking","created":"2025-11-22","cited_by_count":11,"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":"2109.07662","title":"Dynamic Fusion Network for RGBT Tracking","created":"2021-09-16","cited_by_count":9,"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":"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":"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":"2304.04264","title":"RGB-T Tracking Based on Mixed Attention","created":"2023-04-09","cited_by_count":7,"area":null},{"id":"2405.02717","title":"AFter: Attention-based Fusion Router for RGBT Tracking","created":"2024-05-04","cited_by_count":7,"area":null},{"id":"2201.08949","title":"Temporal Aggregation for Adaptive RGBT Tracking","created":"2022-01-22","cited_by_count":6,"area":null},{"id":"2201.09296","title":"A Survey for Deep RGBT Tracking","created":"2022-01-23","cited_by_count":6,"area":null},{"id":"2308.13764","title":"Unified Single-Stage Transformer Network for Efficient RGB-T Tracking","created":"2023-08-26","cited_by_count":6,"area":null},{"id":"2303.14778","title":"RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning","created":"2023-03-26","cited_by_count":5,"area":null},{"id":"2308.01630","title":"Erasure-based Interaction Network for RGBT Video Object Detection and A Unified Benchmark","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2312.17273","title":"X Modality Assisting RGBT Object Tracking","created":"2023-12-27","cited_by_count":2,"area":null},{"id":"2403.16834","title":"From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and Knowledge Distillation","created":"2024-03-25","cited_by_count":2,"area":"distill"},{"id":"2408.16979","title":"Cross Fusion RGB-T Tracking with Bi-directional Adapter","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2503.11247","title":"Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2508.13000","title":"Omni Survey for Multimodality Analysis in Visual Object Tracking","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2511.01427","title":"UniSOT: A Unified Framework for Multi-Modality Single Object Tracking","created":"2025-11-03","cited_by_count":2,"area":null},{"id":"2603.03617","title":"RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation","created":"2026-03-04","cited_by_count":2,"area":"mllm"},{"id":"2403.18193","title":"Middle Fusion and Multi-Stage, Multi-Form Prompts for Robust RGB-T Tracking","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2412.10861","title":"Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos","created":"2024-12-14","cited_by_count":1,"area":null},{"id":"2301.11274","title":"Self-Supervised RGB-T Tracking with Cross-Input Consistency","created":"2023-01-26","cited_by_count":0,"area":null},{"id":"2307.01893","title":"EANet: Enhanced Attribute-based RGBT Tracker Network","created":"2023-07-04","cited_by_count":0,"area":null},{"id":"2307.04100","title":"Visible and infrared self-supervised fusion trained on a single example","created":"2023-07-09","cited_by_count":0,"area":null},{"id":"2405.00168","title":"Revisiting RGBT Tracking Benchmarks from the Perspective of Modality Validity: A New Benchmark, Problem, and Solution","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2508.17488","title":"Optimizing Multi-Modality Trackers via Significance-Regularized Tuning","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2509.19733","title":"Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2601.14799","title":"UBATrack: Spatio-Temporal State Space Model for General Multi-Modal Tracking","created":"2026-01-21","cited_by_count":0,"area":"ssm"},{"id":"2602.23559","title":"No Calibration, No Depth, No Problem: Cross-Sensor View Synthesis with 3D Consistency","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2606.15104","title":"Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.18768","title":"Cross-Modal UAV Object Tracking: State-Aware Representation Learning and A Unified Benchmark","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.01488","title":"Towards Compact Unified Multimodal Tracking: Synergizing Knowledge Distillation with Structural Pruning","created":"2026-08-02","cited_by_count":0,"area":"distill"}],"next_cursor":null}