| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 77.4 | 86.6 | 85 | SPMTrack-G | 2025-03-24 |
| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 76.8 | 85.9 | 84 | SPMTrack-L | 2025-03-24 |
| Exploring Enhanced Contextual Information for Video-Level Object Tracking | ✓ Link | 76.6 | 86.1 | 85.0 | MCITrack-L384 | 2024-12-15 |
| Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance | ✓ Link | 76.2 | 85.3 | 83.5 | LoRAT-g-378 | 2024-03-08 |
| Exploring Enhanced Contextual Information for Video-Level Object Tracking | ✓ Link | 75.3 | 85.6 | 83.3 | MCITrack-B224 | 2024-12-15 |
| Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance | ✓ Link | 75.1 | 84.1 | 82.0 | LoRAT-L-378 | 2024-03-08 |
| A Distractor-Aware Memory for Visual Object Tracking with SAM2 | ✓ Link | 75.1 | | | DAM4SAM | 2024-11-26 |
| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 74.9 | 84 | 81.7 | SPMTrack-B | 2025-03-24 |
| RTracker: Recoverable Tracking via PN Tree Structured Memory | ✓ Link | 74.7 | 84.5 | | RTracker-L | 2024-03-28 |
| SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory | ✓ Link | 74.2 | 82.7 | 80.2 | SAMURAI-L | 2024-11-18 |
| ODTrack: Online Dense Temporal Token Learning for Visual Tracking | ✓ Link | 74.0 | | | ODTrack-L | 2024-01-03 |
| ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe | ✓ Link | 73.6 | 82.8 | 81.1 | ARTrackV2-L | 2023-12-28 |
| Improving Visual Object Tracking through Visual Prompting | ✓ Link | 73.4 | 84.7 | 82.1 | PiVOT-L | 2024-09-27 |
| MixFormer: End-to-End Tracking with Iterative Mixed Attention | ✓ Link | 73.3 | 82.8 | 80.3 | MixViT-L(ConvMAE) | 2023-02-06 |
| ODTrack: Online Dense Temporal Token Learning for Visual Tracking | ✓ Link | 73.2 | | | ODTrack-B | 2024-01-03 |
| Autoregressive Visual Tracking | ✓ Link | 73.1 | 82.2 | 80.3 | ARTrack-L | 2023-01-01 |
| HIPTrack: Visual Tracking with Historical Prompts | ✓ Link | 72.7 | 82.9 | 79.5 | HIPTrack | 2023-11-03 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 72.5 | 81.5 | 79.3 | SeqTrack-L384 | 2023-04-27 |
| Universal Instance Perception as Object Discovery and Retrieval | ✓ Link | 72.4 | 80.7 | 78.9 | UNINEXT-L | 2023-03-12 |
| NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets | ✓ Link | 72.2 | 81.8 | 78.0 | NeighborTrack-OSTrack | 2022-11-12 |
| Universal Instance Perception as Object Discovery and Retrieval | ✓ Link | 72.2 | 80.8 | 79.4 | UNINEXT-H | 2023-03-12 |
| Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation | ✓ Link | 72.0 | 80.1 | 78.5 | MITS | 2023-08-25 |
| DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks | ✓ Link | 71.8 | 81.8 | 78.1 | DropTrack | 2023-04-02 |
| Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework | ✓ Link | 71.1 | 81.1 | 77.6 | OSTrack-384 | 2022-03-22 |
| Target-Aware Tracking with Long-term Context Attention | ✓ Link | 71.1 | 79.1 | 76.1 | TATrack-L | 2023-02-27 |
| Revealing the Dark Secrets of Masked Image Modeling | ✓ Link | 70.7 | | | SwinV2-L 1K-MIM | 2022-05-26 |
| []() | | 70.6 | 80.8 | 76.2 | MixFormerV2-B | |
| LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking | ✓ Link | 70.3 | | 76.2 | LoReTrack | 2024-05-27 |
| SwinTrack: A Simple and Strong Baseline for Transformer Tracking | ✓ Link | 70.2 | 78.4 | 75.3 | SwinTrack-B-384 | 2021-12-02 |
| MixFormer: End-to-End Tracking with Iterative Mixed Attention | ✓ Link | 70.1 | 79.9 | 76.3 | MixFormer-L | 2022-03-21 |
| Revealing the Dark Secrets of Masked Image Modeling | ✓ Link | 70 | | | SwinV2-B 1K-MIM | 2022-05-26 |
| AiATrack: Attention in Attention for Transformer Visual Tracking | ✓ Link | 69.0 | 79.4 | 73.8 | AiATrack | 2022-07-20 |
| Towards Grand Unification of Object Tracking | ✓ Link | 68.5 | 76.6 | 74.1 | Unicorn | 2022-07-14 |
| Learning Target Candidate Association to Keep Track of What Not to Track | ✓ Link | 67.1 | 77.2 | 70.2 | KeepTrack | 2021-03-30 |
| Learning Spatio-Temporal Transformer for Visual Tracking | ✓ Link | 67.1 | 77.0 | | STARK | 2021-03-31 |
| Towards Sequence-Level Training for Visual Tracking | ✓ Link | 66.8 | 75.5 | | SLT-TransT | 2022-08-11 |
| Transformer Tracking | ✓ Link | 64.9 | 73.8 | 69.0 | TransT | 2021-03-29 |
| Siam R-CNN: Visual Tracking by Re-Detection | ✓ Link | 64.8 | 72.2 | | Siam R-CNN | 2019-11-28 |
| Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking | ✓ Link | 63.7 | | 61.4 | TrDiMP | 2021-03-22 |
| How to Train Your Energy-Based Model for Regression | ✓ Link | 63.7 | | | DiMP-NCE+ | 2020-05-04 |
| Tracking-by-Trackers with a Distilled and Reinforced Model | ✓ Link | 57.6 | | | TRASFUST | 2020-07-08 |
| Learning to Fuse Asymmetric Feature Maps in Siamese Trackers | ✓ Link | 57.2 | 65.3 | 58.7 | SiamBAN-ACM | 2020-12-04 |
| Learning Discriminative Model Prediction for Tracking | ✓ Link | 56.8 | 65.0 | 56.7 | DiMP | 2019-04-15 |
| ATOM: Accurate Tracking by Overlap Maximization | ✓ Link | 51.4 | 57.6 | 50.5 | ATOM | 2018-11-19 |
| Learning Discriminative Model Prediction for Tracking | ✓ Link | | | 68.7 | DiMP-50 | 2019-04-15 |
| Transforming Model Prediction for Tracking | ✓ Link | | | 67.1 | ToMP | 2022-03-21 |