| SUTrack: Towards Simple and Unified Single Object Tracking | ✓ Link | 94.6 | 70.8 | SUTrack-L224 | 2024-12-26 |
| []() | | 92.7 | 69.9 | FlexTrack | |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 92.3 | 68.5 | SeqTrackv2-L256 | 2023-04-27 |
| []() | | 91.7 | 67.2 | PromptTrack | |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 91.3 | 68.0 | SeqTrackv2-L384 | 2023-04-27 |
| MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking | ✓ Link | 90.7 | 67.5 | MambaVT-M256 | 2024-08-15 |
| Adaptive Perception for Unified Visual Multi-modal Object Tracking | | 90.6 | 67.2 | APTrack | 2025-02-10 |
| AFter: Attention-based Fusion Router for RGBT Tracking | ✓ Link | 90.1 | 66.7 | AFter | 2024-05-04 |
| Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation | ✓ Link | 90.0 | 67.4 | CKD | 2024-10-15 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 90.0 | 66.3 | SeqTrackv2-B384 | 2023-04-27 |
| Cross Fusion RGB-T Tracking with Bi-directional Adapter | | 89.9 | 65.9 | CFBT | 2024-08-30 |
| Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking | ✓ Link | 89.8 | 66.7 | STTrack | 2024-12-20 |
| Breaking Shallow Limits: Task-Driven Pixel Fusion for Gap-free RGBT Tracking | | 89.7 | 67.1 | TPF | 2025-03-14 |
| RGBT Tracking via All-layer Multimodal Interactions with Progressive Fusion Mamba | | 89.2 | 67.3 | AINet-B384 | 2024-08-16 |
| MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking | ✓ Link | 88.9 | 65.8 | MambaVT-S256 | 2024-08-15 |
| RGB-T Tracking via Multi-Modal Mutual Prompt Learning | ✓ Link | 88.4 | 65.7 | MPLT | 2023-08-31 |
| Transformer-based RGB-T Tracking with Channel and Spatial Feature Fusion | ✓ Link | 88.4 | 65.2 | CSTNet | 2024-05-06 |
| Cross-modulated Attention Transformer for RGBT Tracking | | 88.3 | 66.4 | CAFormer | 2024-08-05 |
| Revisiting RGBT Tracking Benchmarks from the Perspective of Modality Validity: A New Benchmark, Problem, and Method | ✓ Link | 88.1 | 65.1 | MoETrack | 2024-04-30 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 88.0 | 64.7 | SeqTrackv2-B256 | 2023-04-27 |
| Generative-based Fusion Mechanism for Multi-Modal Tracking | ✓ Link | 87.9 | 64.7 | GMMT | 2023-09-04 |
| Unified Single-Stage Transformer Network for Efficient RGB-T Tracking | ✓ Link | 87.4 | 65.8 | USTrack | 2023-08-26 |
| From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and Knowledge Distillation | | 87.3 | 65.1 | MMMP | 2024-03-25 |
| Temporal Adaptive RGBT Tracking with Modality Prompt | | 87.2 | 64.4 | TATrack | 2024-01-02 |
| Bridging Search Region Interaction With Template for RGB-T Tracking | ✓ Link | 87.1 | 63.7 | TBSI | 2023-01-01 |
| Bi-directional Adapter for Multi-modal Tracking | ✓ Link | 86.8 | 64.1 | BAT | 2023-12-17 |
| Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens | | 86.5 | 63.8 | STMT | 2024-01-03 |
| Middle Fusion and Multi-Stage, Multi-Form Prompts for Robust RGB-T Tracking | | 85.9 | 63.4 | M3PT | 2024-03-27 |
| OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning | | 85.7 | 64.2 | OneTracker | 2024-03-14 |
| SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking | ✓ Link | 84.8 | 62.5 | SDSTrack | 2024-03-24 |
| Single-Model and Any-Modality for Video Object Tracking | ✓ Link | 84.2 | 62.5 | Un-Track | 2023-11-27 |
| Duality-Gated Mutual Condition Network for RGBT Tracking | | 83.9 | 59.3 | DMCNet | 2020-11-14 |
| Visual Prompt Multi-Modal Tracking | ✓ Link | 83.5 | 61.7 | ViPT | 2023-03-20 |
| Attribute-Based Progressive Fusion Network for RGBT Tracking | ✓ Link | 82.7 | 57.9 | APFNet | 2022-01-26 |
| Efficient RGB-T Tracking via Cross-Modality Distillation | | 82.4 | 58.4 | CMD | 2023-01-01 |
| Cross-Modal Pattern-Propagation for RGB-T Tracking | | 82.3 | 57.5 | CMPP | 2020-06-01 |
| RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss | | 80.0 | 55.4 | MANet++ | 2020-11-14 |
| Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking | | 79.0 | 57.3 | JMMAC | 2020-07-04 |
| Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline | ✓ Link | 78.8 | 56.8 | HMFT | 2022-04-08 |
| Prompting for Multi-Modal Tracking | | 78.6 | 58.7 | ProTrack | 2022-07-29 |
| Dynamic Fusion Network for RGBT Tracking | | 78.6 | 58.7 | DFNet | 2021-09-16 |
| MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking | ✓ Link | 77.2 | 51.3 | MFGNet | 2021-07-22 |