{"id":13521010,"url":"https://github.com/GXNU-ZhongLab/AQATrack","last_synced_at":"2025-03-31T20:30:30.815Z","repository":{"id":228913389,"uuid":"768134810","full_name":"GXNU-ZhongLab/AQATrack","owner":"GXNU-ZhongLab","description":"CVPR24","archived":false,"fork":false,"pushed_at":"2024-08-04T06:04:09.000Z","size":890,"stargazers_count":31,"open_issues_count":2,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-11-02T05:32:29.978Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/GXNU-ZhongLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-03-06T14:32:39.000Z","updated_at":"2024-10-23T08:33:17.000Z","dependencies_parsed_at":"2024-04-04T14:54:29.426Z","dependency_job_id":"21f1b37c-8b0a-4009-8725-c9d6dbe67778","html_url":"https://github.com/GXNU-ZhongLab/AQATrack","commit_stats":null,"previous_names":["gxnu-zhonglab/aqatrack"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GXNU-ZhongLab%2FAQATrack","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GXNU-ZhongLab%2FAQATrack/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GXNU-ZhongLab%2FAQATrack/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GXNU-ZhongLab%2FAQATrack/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GXNU-ZhongLab","download_url":"https://codeload.github.com/GXNU-ZhongLab/AQATrack/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246535714,"owners_count":20793311,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-01T06:00:26.116Z","updated_at":"2025-03-31T20:30:29.937Z","avatar_url":"https://github.com/GXNU-ZhongLab.png","language":"Python","readme":"# AQATrack  \nThe official implementation for the **CVPR'2024** paper [_Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers_](https://arxiv.org/abs/2403.10574) \n\nModels:[[Models]](https://drive.google.com/drive/folders/1h0aaZ5rzaYc_0Crd4lZs-ouvFCgWdbyT)\nRaw Results:[[Raw Results]](https://drive.google.com/drive/folders/1lx-ge-N3vRZAPLwkyWK5creiQyHktWEz)\nTraining logs:[[Training logs]](https://drive.google.com/drive/folders/1SB4cry17xNGikJdNmFmoPHP119Yv-1rp)\n\n## :sunny: Structure of AQATrack \n![structure](https://github.com/JinxiaXie/AQATrack/blob/main/assets/arch.png)\n\n\n## :sunny: Highlights\n\n### :star2: New Autoregressive Query-based Tracking Framework\nAQATrack is a simple, high-performance **autoregressive query-based spatio-temporal tracker** for adaptive learning the instantaneous target appearance changes in a sliding window\nfashion. Without any additional upadate strategy, AQATrack achieves SOTA performance on multiple benchmarks.\n\n| Tracker     | LaSOT (AUC)|LaSOT\u003csub\u003eext (AUC)|UAV123 (AUC)|TrackingNet (AUC)|TNL2K(AUC)|GOT-10K (AO)\n|:-----------:|:----------:|:-----------------:|:----------:|:---------------:|:--------:|:----------:\n| AQATrack-256| 71.4       | 51.2              | 70.7       | 83.8            | 57.8     | 73.8         \n| AQATrack-384| 72.7       | 52.7              | 71.2       | 84.8            | 59.3     | 76.0         \n\n\n## Install the environment\nUse the Anaconda\n```\nconda create -n aqatrack python=3.8\nconda activate aqatrack\nbash install.sh\n```\n\n## Set project paths\nRun the following command to set paths for this project\n```\npython tracking/create_default_local_file.py --workspace_dir . --data_dir ./data --save_dir ./output\n```\nAfter running this command, you can also modify paths by editing these two files\n```\nlib/train/admin/local.py  # paths about training\nlib/test/evaluation/local.py  # paths about testing\n```\n\n## Data Preparation\nPut the tracking datasets in ./data. It should look like:\n   ```\n   ${PROJECT_ROOT}\n    -- data\n        -- lasot\n            |-- airplane\n            |-- basketball\n            |-- bear\n            ...\n        -- got10k\n            |-- test\n            |-- train\n            |-- val\n        -- coco\n            |-- annotations\n            |-- images\n        -- trackingnet\n            |-- TRAIN_0\n            |-- TRAIN_1\n            ...\n            |-- TRAIN_11\n            |-- TEST\n   ```\n\n\n## Training\nDownload pre-trained [HiViT-Base weights](https://drive.google.com/file/d/1VZQz4buhlepZ5akTcEvrA3a_nxsQZ8eQ/view?usp=share_link) and put it under `$PROJECT_ROOT$/pretrained_models` (see [HiViT](https://github.com/zhangxiaosong18/hivit) for more details).\n\n```\nbash train.sh\n```\n\n\n## Test\n```\npython test_epoch.py\n```\n\n## Evaluation \n```\npython tracking/analysis_results.py\n```\n\n\n## Test FLOPs, and Speed\n*Note:* The speeds reported in our paper were tested on a single RTX2080Ti GPU.\n\n```\n# Profiling AQATrack-ep150-full-256\npython tracking/profile_model.py --script aqatrack --config AQATrack-ep150-full-256\n# Profiling AQATrack-ep150-full-384\npython tracking/profile_model.py --script aqatrack --config AQATrack-ep150-full-384\n```\n\n\n## Acknowledgments\n* Thanks for the [EVPTrack](https://github.com/GXNU-ZhongLab/EVPTrack) and [PyTracking](https://github.com/visionml/pytracking) library, which helps us to quickly implement our ideas.\n\n\n## Citation\nIf our work is useful for your research, please consider cite:\n\n```\n@inproceedings{xie2024autoregressive,\n  title={Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers},\n  author={Xie, Jinxia and Zhong, Bineng and Mo, Zhiyi and Zhang, Shengping and Shi, Liangtao and Song, Shuxiang and Ji, Rongrong},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  pages={19300--19309},\n  year={2024}\n}\n```\n","funding_links":[],"categories":["Papers"],"sub_categories":["CVPR 2024"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FGXNU-ZhongLab%2FAQATrack","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FGXNU-ZhongLab%2FAQATrack","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FGXNU-ZhongLab%2FAQATrack/lists"}