| Exploring Enhanced Contextual Information for Video-Level Object Tracking | ✓ Link | 87.9 | 92.1 | 89.2 | | | MCITrack-L384 | 2024-12-15 |
| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 87.3 | 91.4 | 88.1 | | | SPMTrack-G | 2025-03-24 |
| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 86.9 | 91 | 87.2 | | | SPMTrack-L | 2025-03-24 |
| Exploring Enhanced Contextual Information for Video-Level Object Tracking | ✓ Link | 86.3 | 90.9 | 86.1 | | | MCITrack-B224 | 2024-12-15 |
| ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe | ✓ Link | 86.1 | 90.4 | 86.2 | | | ARTrackV2-L | 2023-12-28 |
| MixFormer: End-to-End Tracking with Iterative Mixed Attention | ✓ Link | 86.1 | 90.3 | 86.0 | | | MixViT-L(ConvMAE) | 2023-02-06 |
| SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking | ✓ Link | 86.1 | 90.2 | 85.6 | | | SPMTrack-B | 2025-03-24 |
| ODTrack: Online Dense Temporal Token Learning for Visual Tracking | ✓ Link | 86.1 | | | | | ODTrack-L | 2024-01-03 |
| Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance | ✓ Link | 86.0 | 90.2 | 86.1 | | | LoRAT-g-378 | 2024-03-08 |
| Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance | ✓ Link | 85.6 | 89.7 | 85.4 | | | LoRAT-L-378 | 2024-03-08 |
| Autoregressive Visual Tracking | ✓ Link | 85.6 | 89.6 | 86.0 | | | ARTrack-L | 2023-01-01 |
| Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking | ✓ Link | 85.5 | 89.8 | 85.8 | | | SeqTrack-L384 | 2023-04-27 |
| Universal Instance Perception as Object Discovery and Retrieval | ✓ Link | 85.4 | 89.0 | 86.4 | | | UNINEXT-H | 2023-03-12 |
| SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory | ✓ Link | 85.3 | | | | | SAMURAI-L | 2024-11-18 |
| ODTrack: Online Dense Temporal Token Learning for Visual Tracking | ✓ Link | 85.1 | | | | | ODTrack-B | 2024-01-03 |
| Target-Aware Tracking with Long-term Context Attention | ✓ Link | 85.0 | 89.3 | 84.5 | | | TATrack-L | 2023-02-27 |
| HIPTrack: Visual Tracking with Historical Prompts | ✓ Link | 84.5 | 89.1 | 83.8 | | | HIPTrack | 2023-11-03 |
| SwinTrack: A Simple and Strong Baseline for Transformer Tracking | ✓ Link | 84 | 88.2 | 83.2 | | | SwinTrack-B-384 | 2021-12-02 |
| MixFormer: End-to-End Tracking with Iterative Mixed Attention | ✓ Link | 83.9 | 88.9 | 83.1 | | | MixFormer-L | 2022-03-21 |
| Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework | ✓ Link | 83.9 | 88.5 | 83.2 | | | OSTrack-384 | 2022-03-22 |
| NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets | ✓ Link | 83.79 | 88.30 | | | | NeighborTrack-OSTrack | 2022-11-12 |
| Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation | ✓ Link | 83.4 | 88.9 | 84.6 | | | MITS | 2023-08-25 |
| []() | | 83.4 | 88.1 | 81.6 | | | MixFormerV2-B | |
| Towards Grand Unification of Object Tracking | ✓ Link | 83 | 86.4 | 82.2 | | | Unicorn | 2022-07-14 |
| Towards Sequence-Level Training for Visual Tracking | ✓ Link | 82.8 | 87.5 | 81.4 | | | SLT-TransT | 2022-08-11 |
| AiATrack: Attention in Attention for Transformer Visual Tracking | ✓ Link | 82.7 | 87.8 | 80.4 | | | AiATrack | 2022-07-20 |
| Learning Spatio-Temporal Transformer for Visual Tracking | ✓ Link | 82.0 | 86.9 | 79.1 | | | STARK | 2021-03-31 |
| Siam R-CNN: Visual Tracking by Re-Detection | ✓ Link | 81.2 | 85.4 | 80.0 | | | Siam R-CNN | 2019-11-28 |
| Target Transformed Regression for Accurate Tracking | ✓ Link | 78.5 | 83.8 | 75 | | | TREG | 2021-04-01 |
| Learning to Fuse Asymmetric Feature Maps in Siamese Trackers | ✓ Link | 75.3 | 81.0 | 71.2 | | | SiamBAN-ACM | 2020-12-04 |
| SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines | ✓ Link | 74.5 | 79.8 | 68.5 | | | SiamFC++ | 2019-11-14 |
| Learning Discriminative Model Prediction for Tracking | ✓ Link | 74.0 | 80.1 | | | | DiMP-50 | 2019-04-15 |
| ATOM: Accurate Tracking by Overlap Maximization | ✓ Link | 70.34 | 77.11 | 64.84 | | | ATOM | 2018-11-19 |
| SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks | ✓ Link | 70 | 79.98 | 69.38 | | | SiamRPN++ | 2018-12-31 |
| Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking | ✓ Link | 60.9 | 71.79 | 56.57 | | | GFS-DCF | 2019-07-30 |
| ECO: Efficient Convolution Operators for Tracking | ✓ Link | 56.13 | 62.14 | 48.86 | | | ECO | 2016-11-28 |
| Staple: Complementary Learners for Real-Time Tracking | ✓ Link | 53.59 | 60.84 | 46.72 | | | STAPLE_CA | 2015-12-04 |
| DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks | ✓ Link | | 88.9 | | | 0.841 | DropTrack | 2023-04-02 |
| How to Train Your Energy-Based Model for Regression | ✓ Link | | 83.7 | 73.7 | 0.787 | 0.787 | DiMP-NCE+ | 2020-05-04 |
| Energy-Based Models for Deep Probabilistic Regression | ✓ Link | | 80.1 | 69.7 | 74.5 | | ATOM(Resnet18)+EnergyRegression | 2019-09-26 |