{"id":13442506,"url":"https://github.com/MasterBin-IIAU/Unicorn","last_synced_at":"2025-03-20T14:31:23.386Z","repository":{"id":45692337,"uuid":"514085646","full_name":"MasterBin-IIAU/Unicorn","owner":"MasterBin-IIAU","description":"[ECCV'22 Oral] Towards Grand Unification of Object Tracking","archived":false,"fork":false,"pushed_at":"2022-10-17T06:49:09.000Z","size":22456,"stargazers_count":949,"open_issues_count":23,"forks_count":87,"subscribers_count":20,"default_branch":"master","last_synced_at":"2024-10-28T05:59:18.721Z","etag":null,"topics":["multi-object-tracking-segmentation","multiple-object-tracking","object-tracking","single-object-tracking","video-object-segmentation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MasterBin-IIAU.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-07-15T00:30:32.000Z","updated_at":"2024-10-11T03:03:12.000Z","dependencies_parsed_at":"2022-08-12T12:00:53.927Z","dependency_job_id":null,"html_url":"https://github.com/MasterBin-IIAU/Unicorn","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MasterBin-IIAU%2FUnicorn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MasterBin-IIAU%2FUnicorn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MasterBin-IIAU%2FUnicorn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MasterBin-IIAU%2FUnicorn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MasterBin-IIAU","download_url":"https://codeload.github.com/MasterBin-IIAU/Unicorn/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244630148,"owners_count":20484324,"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":["multi-object-tracking-segmentation","multiple-object-tracking","object-tracking","single-object-tracking","video-object-segmentation"],"created_at":"2024-07-31T03:01:46.574Z","updated_at":"2025-03-20T14:31:23.379Z","avatar_url":"https://github.com/MasterBin-IIAU.png","language":"Python","funding_links":[],"categories":["Python","算法论文"],"sub_categories":["**2022**"],"readme":"## Unicorn :unicorn: : Towards Grand Unification of Object Tracking\n\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/towards-grand-unification-of-object-tracking/multiple-object-tracking-on-bdd100k)](https://paperswithcode.com/sota/multiple-object-tracking-on-bdd100k?p=towards-grand-unification-of-object-tracking)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/towards-grand-unification-of-object-tracking/multi-object-tracking-and-segmentation-on-2)](https://paperswithcode.com/sota/multi-object-tracking-and-segmentation-on-2?p=towards-grand-unification-of-object-tracking)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/towards-grand-unification-of-object-tracking/multi-object-tracking-on-mots20)](https://paperswithcode.com/sota/multi-object-tracking-on-mots20?p=towards-grand-unification-of-object-tracking)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/towards-grand-unification-of-object-tracking/visual-object-tracking-on-lasot)](https://paperswithcode.com/sota/visual-object-tracking-on-lasot?p=towards-grand-unification-of-object-tracking)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/towards-grand-unification-of-object-tracking/visual-object-tracking-on-trackingnet)](https://paperswithcode.com/sota/visual-object-tracking-on-trackingnet?p=towards-grand-unification-of-object-tracking)\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/towards-grand-unification-of-object-tracking/multi-object-tracking-on-mot17)](https://paperswithcode.com/sota/multi-object-tracking-on-mot17?p=towards-grand-unification-of-object-tracking)\n[![Models on Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model%20Hub-blue)](https://huggingface.co/models?arxiv=arxiv:2111.12085)\n![Unicorn](assets/Unicorn.png)\n\nThis repository is the project page for the paper [Towards Grand Unification of Object Tracking](https://arxiv.org/abs/2207.07078)\n\n## Highlight\n- Unicorn is accepted to ECCV 2022 as an **oral presentation**!\n- Unicorn first demonstrates grand unification for **four object-tracking tasks**.\n- Unicorn achieves strong performance in **eight tracking benchmarks**. \n\n## Introduction\n- The object tracking field mainly consists of four sub-tasks: Single Object Tracking (SOT), Multiple Object Tracking (MOT), Video Object Segmentation (VOS), and Multi-Object Tracking and Segmentation (MOTS). Most previous approaches are developed for only one of or part of the sub-tasks. \n\n- For the first time, Unicorn accomplishes the great unification of the network architecture and the learning paradigm for **four tracking tasks**. Besides, Unicorn puts forwards new state-of-the-art performance on many challenging tracking benchmarks **using the same model parameters**.\n\nThis repository supports the following tasks:\n\nImage-level\n- Object Detection\n- Instance Segmentation\n\nVideo-level\n- Single Object Tracking (SOT)\n- Multiple Object Tracking (MOT)\n- Video Object Segmentation (VOS)\n- Multi-Object Tracking and Segmentation (MOTS)\n\n## Demo\nUnicorn conquers four tracking tasks (SOT, MOT, VOS, MOTS) using **the same network** with **the same parameters**.\n\nhttps://user-images.githubusercontent.com/6366788/180479685-c2f4bf3e-3faf-4abe-b401-80150877348d.mp4\n\n## Results\n### SOT\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"assets/SOT.png\" width=\"600pix\"/\u003e\n\u003c/div\u003e\n\n### MOT (MOT17)\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"assets/MOT.png\" width=\"600pix\"/\u003e\n\u003c/div\u003e\n\n### MOT (BDD100K) \n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"assets/MOT-BDD.png\" width=\"600pix\"/\u003e\n\u003c/div\u003e\n\n### VOS\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"assets/VOS.png\" width=\"600pix\"/\u003e\n\u003c/div\u003e\n\n### MOTS (MOTS Challenge)\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"assets/MOTS.png\" width=\"600pix\"/\u003e\n\u003c/div\u003e\n\n### MOTS (BDD100K MOTS)\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"assets/MOTS-BDD.png\" width=\"600pix\"/\u003e\n\u003c/div\u003e\n\n## Getting started\n1. Installation: Please refer to [install.md](assets/install.md) for more details.\n2. Data preparation: Please refer to [data.md](assets/data.md) for more details.\n3. Training: Please refer to [train.md](assets/train.md) for more details.\n4. Testing: Please refer to [test.md](assets/test.md) for more details. \n5. Model zoo: Please refer to [model_zoo.md](assets/model_zoo.md) for more details.\n\n\n## Citing Unicorn\nIf you find Unicorn useful in your research, please consider citing:\n```bibtex\n@inproceedings{unicorn,\n  title={Towards Grand Unification of Object Tracking},\n  author={Yan, Bin and Jiang, Yi and Sun, Peize and Wang, Dong and Yuan, Zehuan and Luo, Ping and Lu, Huchuan},\n  booktitle={ECCV},\n  year={2022}\n}\n```\n\n## Acknowledgments\n- Thanks [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) and [CondInst](https://github.com/aim-uofa/AdelaiDet) for providing strong baseline for object detection and instance segmentation.\n- Thanks [STARK](https://github.com/researchmm/Stark) and [PyTracking](https://github.com/visionml/pytracking) for providing useful inference and evaluation toolkits for SOT and VOS.\n- Thanks [ByteTrack](https://github.com/ifzhang/ByteTrack), [QDTrack](https://github.com/SysCV/qdtrack) and [PCAN](https://github.com/SysCV/pcan/) for providing useful data-processing scripts and evalution codes for MOT and MOTS.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMasterBin-IIAU%2FUnicorn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMasterBin-IIAU%2FUnicorn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMasterBin-IIAU%2FUnicorn/lists"}