Law Result and Weights: https://drive.google.com/drive/folders/1PqiciVkwmtD9VCRkHVhZLsLA6cuz5oF1?usp=share_link

• Create a new conda environment and activate it.

conda create -n TATrack python=3.9 -y
conda activate TATrack

• Install pytorch and torchvision.

conda install pytorch torchvision cudatoolkit -c pytorch

• Install other required packages.

pip install -r requirements.txt

• Prepare the datasets: OTB2015, VOT2018, UAV123, GOT-10k, TrackingNet, LaSOT, COCO*, and something else you want to test. Set the paths as the following:

├── TATrack
|   ├── ...
|   ├── ...
|   ├── datasets
|   |   ├── COCO -> /opt/data/COCO
|   |   ├── GOT-10k -> /opt/data/GOT-10k
|   |   ├── LaSOT -> /opt/data/LaSOT/LaSOTBenchmark
|   |   ├── OTB
|   |   |   └── OTB2015 -> /opt/data/OTB2015
|   |   ├── TrackingNet -> /opt/data/TrackingNet
|   |   ├── UAV123 -> /opt/data/UAV123/UAV123
|   |   ├── VOT
|   |   |   ├── vot2018
|   |   |   |   ├── VOT2018 -> /opt/data/VOT2018
|   |   |   |   └── VOT2018.json

• Notes

i. Star notation(*): just for training. You can ignore these datasets if you just want to test the tracker.

ii. In this case, we create soft links for every dataset. The real storage location of all datasets is /opt/data/. You can change them according to your situation.

• Note that all paths we used here are relative, not absolute. See any configuration file in the experiments directory for examples and details.

python main/test.py --config testing_dataset_config_file_path

Take GOT-10k as an example:

python main/test.py --config experiments/tatrack/test/base/got.yaml

• Prepare the datasets as described in the last subsection.
• Run the shell command.

python main/train.py --config experiments/tatrack/train/base-got.yaml

python main/train.py --config experiments/tatrack/train/base.yaml

@article{he2023target, title={Target-Aware Tracking with Long-term Context Attention}, author={He, Kaijie and Zhang, Canlong and Xie, Sheng and Li, Zhixin and Wang, Zhiwen}, journal={arXiv preprint arXiv:2302.13840}, year={2023} }