| Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking | | 77.2 | 84.7 | | ACTrack-EM | 2026-08-01 |
| Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality | | 70.4 | | | Uni-MDTrack-L | 2026-03-15 |
| TGTrack: Temporal Generative Learning for Unified Single Object Tracking | ✓ Link | 68.6 | 72.8 | | TGTrack-L384 (extra data) | 2026-06-03 |
| Uni-MDTrack: Learning Decoupled Memory and Dynamic States for Parameter-Efficient Visual Tracking in All Modality | | 67.6 | | | Uni-MDTrack-B | 2026-03-15 |
| ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking | ✓ Link | 67.5 | 73.6 | | ATCTrack-B | 2025-07-26 |
| ATSTrack: Enhancing Visual-Language Tracking by Aligning Temporal and Spatial Scales | | 66.2 | | | ATSTrack | 2025-07-01 |
| Exploring Enhanced Contextual Information for Video-Level Object Tracking | ✓ Link | 65.3 | | | MCITrack-L384 | 2024-12-15 |
| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 64.7 | 70.6 | 82.6 | SPMTrack-G | 2025-03-24 |
| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 63.7 | 69.2 | 81.5 | SPMTrack-L | 2025-03-24 |
| Drift-Resilient Temporal Priors for Visual Tracking | | 63.7 | | | DTPTrack-L 378 | 2026-04-03 |
| TR-MoE: Temporal Reliability-Aware Mixture-of-Experts for Robust Tracking | ✓ Link | 63.6 | 69.9 | | TR-MoE | 2026-09-08 |
| ODONet: Online Dynamic Offset Network for Visual Object Tracking | ✓ Link | 63.1 | | | ODONet-B384 | 2026-09-08 |
| An Efficient Token Compression Framework for Visual Object Tracking | | 63.0 | 68.4 | | ETCTrack-B384 | 2026-05-08 |
| Exploring Enhanced Contextual Information for Video-Level Object Tracking | ✓ Link | 62.9 | | | MCITrack-B224 | 2024-12-15 |
| Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance | ✓ Link | 62.7 | 67.8 | | LoRAT-g-378 | 2024-03-08 |
| Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance | ✓ Link | 62.3 | 67.0 | | LoRAT-L-378 | 2024-03-08 |
| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 62.0 | 66.7 | 79.7 | SPMTrack-B | 2025-03-24 |
| ODTrack: Online Dense Temporal Token Learning for Visual Tracking | ✓ Link | 61.7 | | | ODTrack-L | 2024-01-03 |
| ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe | ✓ Link | 61.6 | | | ARTrackV2-L | 2023-12-28 |
| ODTrack: Online Dense Temporal Token Learning for Visual Tracking | ✓ Link | 60.9 | | | ODTrack-B | 2024-01-03 |
| RTracker: Recoverable Tracking via PN Tree Structured Memory | ✓ Link | 60.6 | 63.7 | | RTracker-L | 2024-03-28 |
| Autoregressive Visual Tracking | ✓ Link | 60.3 | | | ARTrack-L | 2023-01-01 |
| Drift-Resilient Temporal Priors for Visual Tracking | | 60.3 | | | DTPTrack-B 224 | 2026-04-03 |
| Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers | | 59.3 | 62.3 | | AQATrack-384 (extra data) | 2024-03-15 |
| OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning | | 58.0 | 59.1 | | OneTracker | 2024-03-14 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 57.8 | | | SeqTrack-L384 | 2023-04-27 |
| MVLM: Template-Free Tracking via Vision-Language Margin Confidence and Memory-Gated Tracking | ✓ Link | 57.8 | 60.9 | | MVLM (language-only) | 2026-06-03 |
| | 57.4 | 58.4 | | MixFormerV2-B | |
| DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks | ✓ Link | 56.9 | 57.9 | | DropTrack | 2023-04-02 |
| Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark | ✓ Link | | 0.42|0.50|0.42 | | AdaSwitcher | 2021-03-31 |
| DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking | ✓ Link | 56.8 | 72.8 | | DiffusionTrack-L256 (1) | 2024-01-01 |
| Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework | ✓ Link | 55.9 | | | OSTrack-384 (extra data) | 2022-03-22 |
| Transformer Tracking | ✓ Link | 51.0 | | | TransT-N4 (extra data) | 2021-03-29 |
| DreamTrack: Dreaming the Future for Multimodal Visual Object Tracking | | | 67.4 | | DreamTrack-L 384 | 2025-06-11 |