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.
[ECCV 2022] Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
| Date | Stars |
|---|---|
| 2026-07-24 | 666 |
| 2026-07-25 | 667 |
| 2026-07-28 | 667 |
| 2026-07-30 | 667 |
| 2026-08-06 | 667 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# OSTrack The official implementation for the **ECCV 2022** paper [_Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework_](https://arxiv.org/abs/2203.11991). [[Models](https://drive.google.com/drive/folders/1ttafo0O5S9DXK2PX0YqPvPrQ-HWJjhSy?usp=sharing)][[Raw Results](https://drive.google.com/drive/folders/1TYU5flzZA1ap2SLdzlGRQDbObwMxCiaR?usp=sharing)][[Training logs](https://drive.google.com/drive/folders/1LUsGf9JRV0k-R3TA7UFBRlcic22M4uBp?usp=sharing)] <!-- [](https://paperswithcode.com/sota/visual-object-tracking-on-lasot?p=joint-feature-learning-and-relation-modeling) [](https://paperswithcode.com/sota/visual-object-tracking-on-got-10k?p=joint-feature-learning-and-relation-modeling) [//]: # ([](https://paperswithcode.com/sota/visual-object-tracking-on-trackingnet?p=joint-feature-learning-and-relation-modeling)) [](https://paperswithcode.com/sota/visual-object-tracking-on-uav123?p=joint-feature-learning-and-relation-modeling) --> <p align="center"> <img width="85%" src="https://github.com/botaoye/OSTrack/blob/main/assets/arch.png" alt="Framework"/> </p> ## News **[Dec. 12, 2022]** - OSTrack is now available in [Modelscope](https://modelscope.cn/models/damo/cv_vitb_video-single-object-tracking_ostrack/summary), where you can run demo videos online and conveniently integrate OSTrack into your code. **[Oct. 28, 2022]** - :trophy: We are the winners of VOT-2022 STb(box GT) & RTb challenges. ## Highlights ### :star2: New One-stream Tracking Framework OSTrack is a simple, neat, high-performance **one-stream tracking framework** for joint feature learning and relational modeling based on self-attention operators. Without any additional temporal information, OSTrack achieves SOTA performance on multiple benchmarks. OSTrack can serve as a strong baseline for further research. | Tracker | GOT-10K (AO) | LaSOT (AUC) | TrackingNet (AUC) | UAV123(AUC) | |:-----------:|:------------:|:-----------:|:-----------------:|:-----------:| | OSTrack-384 | 73.7 | 71.1 | 83.9 | 70.7 | | OSTrack-256 | 71.0 | 69.1 | 83.1 | 68.3 | ### :star2: Fast Training OSTrack-256 can be trained in ~24 hours with 4*V100 (16GB of memory per GPU), which is much faster than recent SOTA transformer-based trackers. The fast training speed comes from: 1. While previous Siamese-style trackers required separate feeding of the template and search region into the backbone at each iteration of training, OSTrack directly combines the template and search region. The tight and highly parallelized structure results in improved training and inference speed. 2. The proposed early candidate elimination (ECE) module significantly reduces memory and time consumption. 3. Pretrained Transformer weights enable faster convergence. ### :star2: Good performance-speed trade-off [//]: # () <p align="center"> <img width="70%" src="https://github.com/botaoye/OSTrack/blob/main/assets/speed_vs_performance.png" alt="speed_vs_performance"/> </p> ## Install the environment **Option1**: Use the Anaconda (CUDA 10.2) ``` conda create -n ostrack python=3.8 conda activate ostrack bash install.sh ``` **Option2**: Use the Anacon
Excerpt of 8,443 characters
Read on GitHub
24
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8b0542e6b075ee59, topic:transformer