{"total":59,"rows":[{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142,"area":null},{"id":"2303.03369","title":"Multimodal Prompting with Missing Modalities for Visual Recognition","created":"2023-03-06","cited_by_count":121,"area":null},{"id":"2311.15851","title":"Single-Model and Any-Modality for Video Object Tracking","created":"2023-11-27","cited_by_count":65,"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":"2208.08340","title":"Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model","created":"2022-08-17","cited_by_count":52,"area":"mllm"},{"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":"2507.20177","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","created":"2025-07-27","cited_by_count":30,"area":null},{"id":"2312.00360","title":"Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning","created":"2023-12-01","cited_by_count":25,"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":"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":"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":"2407.20730","title":"Autogenic Language Embedding for Coherent Point Tracking","created":"2024-07-30","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":"2408.07889","title":"MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking","created":"2024-08-15","cited_by_count":14,"area":"ssm"},{"id":"2410.11586","title":"Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation","created":"2024-10-15","cited_by_count":11,"area":"distill"},{"id":"2502.06583","title":"Adaptive Perception for Unified Visual Multi-modal Object Tracking","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2403.05856","title":"POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-View World","created":"2024-03-09","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":"2307.13958","title":"Visual Prompt Flexible-Modal Face Anti-Spoofing","created":"2023-07-26","cited_by_count":9,"area":null},{"id":"2405.05004","title":"TENet: Targetness Entanglement Incorporating with Multi-Scale Pooling and Mutually-Guided Fusion for RGB-E Object Tracking","created":"2024-05-08","cited_by_count":9,"area":null},{"id":"2405.17903","title":"Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion","created":"2024-05-28","cited_by_count":9,"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":"2409.19342","title":"X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation","created":"2024-09-28","cited_by_count":7,"area":null},{"id":"2409.04817","title":"SSFam: Scribble Supervised Salient Object Detection Family","created":"2024-09-07","cited_by_count":6,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2405.03177","title":"Transformer-based RGB-T Tracking with Channel and Spatial Feature Fusion","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2505.16321","title":"Efficient Motion Prompt Learning for Robust Visual Tracking","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2604.12502","title":"SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2409.16491","title":"Proactive Schemes: A Survey of Adversarial Attacks for Social Good","created":"2024-09-24","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":"2505.12606","title":"Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking","created":"2025-05-19","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":"2603.01412","title":"UETrack: A Unified and Efficient Framework for Single Object Tracking","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2312.13330","title":"Towards Subject-Oriented Video Captioning via User-Specified Targets","created":"2023-12-20","cited_by_count":1,"area":null},{"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":"2502.18143","title":"LightFC-X: Lightweight Convolutional Tracker for RGB-X Tracking","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2502.18220","title":"UASTrack: A Unified Adaptive Selection Framework with Modality-Customization in Single Object Tracking","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2503.11218","title":"Towards General Multimodal Visual Tracking","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2505.19990","title":"Progressive Scaling Visual Object Tracking","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.23972","title":"Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Tracking","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2508.01592","title":"DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2511.16227","title":"SwiTrack: Tri-State Switch for Cross-Modal Object Tracking","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2603.14452","title":"Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2607.24701","title":"Spatio-Temporal Conditional Denoising Transformer for Modality-Missing RGBT Tracking","created":"2026-07-27","cited_by_count":1,"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":"2503.22199","title":"Hyperspectral Adapter for Object Tracking based on Hyperspectral Video","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2508.10655","title":"Serial Over Parallel: Learning Continual Unification for Multi-Modal Visual Object Tracking and Benchmarking","created":"2025-08-14","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":"2603.13719","title":"Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking","created":"2026-03-14","cited_by_count":0,"area":"moe"},{"id":"2603.21100","title":"Learning Progressive Adaptation for Multi-Modal Tracking","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2608.00847","title":"Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking","created":"2026-08-01","cited_by_count":0,"area":"agents"},{"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"},{"id":"2608.09575","title":"MSP-Net: Manifold-Guided Spectral Prompt Network for Hyperspectral Object Tracking","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.38637","title":"Template-Search Domain Adaptation via Multi-Stage Feature Alignment for Cross-Modal Object Tracking","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.13053","title":"UniMergeTrack: Hierarchical Model Merging for General RGB-X Visual Object Tracking","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}