| Parameter-Dynamic Adaptive Fusion and Calibration Network for RGBT Tracking | | 80.3 | 63.9 | PAFCNet-384 | 2026-08-03 |
| Parameter-Dynamic Adaptive Fusion and Calibration Network for RGBT Tracking | | 79.8 | 63.4 | PAFCNet-256 | 2026-08-03 |
| Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking | | 79.5 | 62.9 | SDMoEA-L (FFT) | 2026-03-14 |
| TGTrack: Temporal Generative Learning for Unified Single Object Tracking | ✓ Link | 79.5 | 63.3 | TGTrack-L384 (extra data) | 2026-06-03 |
| Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking | | 79.4 | 63.7 | ACTrack-EM | 2026-08-01 |
| Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality | | 77.9 | 62.1 | Uni-MDTrack-L | 2026-03-15 |
| Tracking and Segmenting Anything in Any Modality | | 77.8 | 61.7 | SATA | 2025-11-22 |
| CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking | | 77.7 | 61.3 | CADTrack (DropMAE) | 2025-11-22 |
| Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking | | 77.7 | 60.9 | SDMoEA-L (PEFT) | 2026-03-14 |
| | 77.3 | 62.0 | FlexTrack | |
| Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking | | 77.3 | 61.0 | SDMoEA-B (FFT) | 2026-03-14 |
| SUTrack: Towards Simple and Unified Single Object Tracking | ✓ Link | 76.9 | 61.9 | SUTrack-L384 | 2024-12-26 |
| RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation | ✓ Link | 76.8 | 61.1 | RAGTrack | 2026-03-04 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 76.7 | 61.0 | SeqTrackv2-L384 | 2023-04-27 |
| Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality | | 76.7 | 61.2 | Uni-MDTrack-B | 2026-03-15 |
| Exploring Modality-Aware Fusion and Decoupled Temporal Propagation for Multi-Modal Object Tracking | | 76.5 | 61.4 | MDTrack-S | 2026-03-10 |
| Sparse-Dense Mixture of Experts Adapter for Multi-Modal Tracking | | 76.5 | 60.3 | SDMoEA-B (PEFT) | 2026-03-14 |
| Progressively Spiral Mamba Fusion for Multimodal Tracking | | 76.5 | 61.2 | PSMTrack | 2026-09-08 |
| | 76.2 | 60.7 | PromptTrack | |
| DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter | ✓ Link | 76.1 | 60.3 | DMTrack | 2025-08-03 |
| Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking | ✓ Link | 76.0 | 60.3 | STTrack | 2024-12-20 |
| CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking | | 75.8 | 60.2 | CADTrack (SOT) | 2025-11-22 |
| AnyTrack: Unifying Visual Object Tracking with Any Modalities | ✓ Link | 75.5 | 59.7 | AnyTrack | 2026-08-07 |
| Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking | | 75.1 | 59.5 | TPF | 2025-03-14 |
| RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba | | 74.2 | 59.1 | AINet-B384 | 2024-08-16 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 74.1 | 58.8 | SeqTrackv2-L256 | 2023-04-27 |
| Adaptive Perception for Unified Visual Multi-modal Object Tracking | | 74.1 | 58.9 | APTrack | 2025-02-10 |
| Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation | | 73.5 | 58.5 | VFPTrack | 2025-09-24 |
| Cross Fusion RGB-T Tracking with Bi-directional Adapter | | 73.2 | 58.4 | CFBT | 2024-08-30 |
| Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation | ✓ Link | 73.2 | 58.1 | CKD | 2024-10-15 |
| | 73.0 | 58.8 | MST | |
| MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking | ✓ Link | 73.0 | 57.9 | MambaVT-S256 | 2024-08-15 |
| MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking | ✓ Link | 72.7 | 57.5 | MambaVT-M256 | 2024-08-15 |
| Revisiting RGBT Tracking Benchmarks from the Perspective of Modality Validity: A New Benchmark, Problem, and Method | ✓ Link | 72.1 | 57.8 | MoETrack | 2024-04-30 |
| RGB-T Tracking via Multi-Modal Mutual Prompt Learning | ✓ Link | 72.0 | 57.1 | MPLT | 2023-08-31 |
| GAP-Track: Bridging the Resolution Gap for Cross-Resolution RGBT Tracking | | 71.8 | 57.1 | GAP-Track | 2026-09-08 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 71.5 | 56.2 | SeqTrackv2-B384 | 2023-04-27 |
| Transformer-based RGB-T Tracking with Channel and Spatial Feature Fusion | ✓ Link | 71.5 | 57.2 | CSTNet | 2024-05-06 |
| From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and Knowledge Distillation | | 71.4 | 56.7 | MMMP | 2024-03-25 |
| Generative-based Fusion Mechanism for Multi-Modal Tracking | ✓ Link | 70.7 | 56.6 | GMMT | 2023-09-04 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 70.4 | 55.8 | SeqTrackv2-B256 | 2023-04-27 |
| AFter: Attention-based Fusion Router for RGBT Tracking | ✓ Link | 70.3 | 55.1 | AFter | 2024-05-04 |
| Bridging Search Region Interaction With Template for RGB-T Tracking | ✓ Link | 70.2 | 56.5 | TBSI | 2023-01-01 |
| Bi-directional Adapter for Multi-modal Tracking | ✓ Link | 70.2 | 56.3 | BAT | 2023-12-17 |
| Temporal Adaptive RGBT Tracking with Modality Prompt | | 70.2 | 56.1 | TATrack | 2024-01-02 |
| Cross-modulated Attention Transformer for RGBT Tracking | | 70.0 | 55.6 | CAFormer | 2024-08-05 |
| Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens | | 67.4 | 53.7 | STMT | 2024-01-03 |
| Exploring Historical Information for RGBE Visual Tracking with Mamba | ✓ Link | 67.4 | 54.2 | MamTrack | 2025-06-11 |
| Middle Fusion and Multi-Stage, Multi-Form Prompts for Robust RGB-T Tracking | | 67.3 | 54.2 | M3PT | 2024-03-27 |
| OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning | | 67.2 | 53.8 | OneTracker | 2024-03-14 |
| Single-Model and Any-Modality for Video Object Tracking | ✓ Link | 66.7 | 53.6 | Un-Track | 2023-11-27 |
| SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking | ✓ Link | 66.5 | 53.1 | SDSTrack | 2024-03-24 |
| Visual Prompt Multi-Modal Tracking | ✓ Link | 65.1 | 52.5 | ViPT | 2023-03-20 |
| Efficient RGB-T Tracking via Cross-Modality Distillation | | 59.0 | 46.6 | CMD | 2023-01-01 |
| Prompting for Multi-Modal Tracking | | 50.9 | 42.1 | ProTrack | 2022-07-29 |
| Attribute-Based Progressive Fusion Network for RGBT Tracking | ✓ Link | 50.0 | 36.2 | APFNet | 2022-01-26 |
| Duality-Gated Mutual Condition Network for RGBT Tracking | | 49.0 | 35.5 | DMCNet | 2020-11-14 |
| RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss | | 46.7 | 31.4 | MANet++ | 2020-11-14 |
| Challenge-Aware RGBT Tracking | | 45.0 | 31.4 | CAT | 2020-07-26 |
| Multi-Modal Fusion for End-to-End RGB-T Tracking | ✓ Link | 44.7 | 34.3 | mfDiMP | 2019-08-30 |