Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
This repository is a paper digest of Transformer-related approaches in visual tracking tasks.
| Date | Stars |
|---|---|
| 2026-07-24 | 389 |
| 2026-07-25 | 389 |
| 2026-07-28 | 389 |
| 2026-07-30 | 389 |
| 2026-08-06 | 389 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Transformer Tracking
This repository is a paper digest of [Transformer](https://arxiv.org/abs/1706.03762)-related approaches in visual tracking tasks. Currently, tasks in this repository include **Unified Tracking (UT)**, **Single Object Tracking (SOT)** and **3D Single Object Tracking (3DSOT)**. Note that some trackers involving a [Non-Local](https://arxiv.org/abs/1711.07971) attention mechanism are also collected. Papers are listed in alphabetical order of the first character.
### :link:Jump to:
- ### [[Unified Tracking](https://github.com/Little-Podi/Transformer_Tracking#bookmarkunified-tracking-ut)]
- ### [[Single Object Tracking](https://github.com/Little-Podi/Transformer_Tracking#bookmarksingle-object-tracking-sot)]
- ### [[3D Single Object Tracking](https://github.com/Little-Podi/Transformer_Tracking#bookmark3d-single-object-tracking-3dsot)]
> [!NOTE]
> I find it hard to trace all tasks that are related to tracking, including Video Object Segmentation (VOS), Multiple Object Tracking (MOT), Video Instance Segmentation (VIS), Video Object Detection (VOD) and Object Re-Identification (ReID). Hence, I discard all other tracking tasks in a previous update. If you are interested, you can find plenty of collections in [this archived version](https://github.com/Little-Podi/Transformer_Tracking/tree/4cc6050c07dfd4ecbc9f6aa584601a457ed84eb3). Besides, the most recent trend shows that different tracking tasks are coming to the same avenue.
## :star2:Recommendation
### Game Over???
- **[SAM 2](https://ai.meta.com/SAM2)** [[paper](https://arxiv.org/abs/2408.00714)] [[code](https://github.com/facebookresearch/segment-anything-2)]
- **[EfficientTAM](https://yformer.github.io/efficient-track-anything)** [[paper](https://arxiv.org/abs/2411.18933)] [[code](https://github.com/yformer/EfficientTAM)]
### State-of-the-Art Transformer Tracker:two_hearts::two_hearts::two_hearts:
- **GRM** (Generalized Relation Modeling for Transformer Tracking) [[paper](https://arxiv.org/abs/2303.16580)] [[code](https://github.com/Little-Podi/GRM)] [[video](https://youtu.be/bQKN3HV-8XI)]
- **AiATrack** (AiATrack: Attention in Attention for Transformer Visual Tracking) [[paper](https://arxiv.org/abs/2207.09603)] [[code](https://github.com/Little-Podi/AiATrack)] [[video](https://youtu.be/TqNiOWx9cnI)]
### Up-to-Date Benchmark Results:rocket::rocket::rocket:
- Image courtesy: https://arxiv.org/abs/2302.11867
### Helpful Learning Resource for Tracking:thumbsup::thumbsup::thumbsup:
- **(Survey)** A Deep Dive into Generic Object Tracking: A Survey [[paper](https://arxiv.org/abs/2507.23251)], Transformers in Single Object Tracking: An Experimental Survey [[paper](https://arxiv.org/abs/2302.11867)], Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook [[paper](https://arxiv.org/abs/2112.02838)]
- **(Talk)** Discriminative Appearance-Based Tracking and Segmentation [[video](https://youtu.be/ILVnBhFq2Ds)], Deep Visual Reasoning with Optimization-Based Network Modules [[video](https://youtu.be/UR2TlFCrYac)]
- **(Library)** PyTracking: Visual Tracking Library Based on PyTorch [[code](https://github.com/visionml/pytracking)]
- **(People)** Martin Danelljan@ETH [[web](https://martin-danelljan.github.io)], Bin Yan@DLUT [[web](https://masterbin-iiau.github.io)]
### Recent Trends:fire::fire::fire:
- ### Target Head: Autoregressive Temporal Modeling
- #### Representative
- Bounding box as coordinate sequence.
- **ARTrackV2** [[CVPR'24](https://github.com/Little-Podi/Transformer_Tracking#cvpr-2024-1)] **ARTrack** [[CVPR'23](https://github.com/Little-Podi/Transformer_Tracking#cvpr-2023-1)], **SeqTrack** [[CVPR'23](https://github.com/Little-Podi/Transformer_Tracking#cvpr-2023-1)]
- ### Feature Backbone: Joint Feature Extraction and Interaction
- #### Advantage
- Benefit from pre-trained vision Transformer models.
- Free from randomly initialized correlationExcerpt of 61,673 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:fa71259337de01ec, topic:object-tracking, readme:object detection, readme:instance segmentation
matched fp:fa71259337de01ec, topic:transformer
matched fp:fa71259337de01ec, topic:awesome-list