Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/MasterBin-IIAU/Unicorn

[ECCV'22 Oral] Towards Grand Unification of Object Tracking
https://github.com/MasterBin-IIAU/Unicorn

multi-object-tracking-segmentation multiple-object-tracking object-tracking single-object-tracking video-object-segmentation

Last synced: about 1 month ago
JSON representation

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

Host: GitHub
URL: https://github.com/MasterBin-IIAU/Unicorn
Owner: MasterBin-IIAU
License: mit
Created: 2022-07-15T00:30:32.000Z (almost 2 years ago)
Default Branch: master
Last Pushed: 2022-10-17T06:49:09.000Z (over 1 year ago)
Last Synced: 2024-03-17T19:47:58.856Z (3 months ago)
Topics: multi-object-tracking-segmentation, multiple-object-tracking, object-tracking, single-object-tracking, video-object-segmentation
Language: Python
Homepage:
Size: 21.4 MB
Stars: 941
Watchers: 20
Forks: 87
Open Issues: 23
Metadata Files:
- Readme: README.md
- License: LICENSE

Lists

awesome-stars - Unicorn - [ECCV'22 Oral] Towards Grand Unification of Object Tracking (Python)
awesome-stars - MasterBin-IIAU/Unicorn - [ECCV'22 Oral] Towards Grand Unification of Object Tracking (Python)
awesome-stars - MasterBin-IIAU/Unicorn - [ECCV'22 Oral] Towards Grand Unification of Object Tracking (Python)
awesome-multiple-object-tracking - [code

README

        ## Unicorn :unicorn: : Towards Grand Unification of Object Tracking

[![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)

[![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)

[![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)

[![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)

[![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)

[![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)

[![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)

![Unicorn](assets/Unicorn.png)

This repository is the project page for the paper [Towards Grand Unification of Object Tracking](https://arxiv.org/abs/2207.07078)

## Highlight

- Unicorn is accepted to ECCV 2022 as an **oral presentation**!

- Unicorn first demonstrates grand unification for **four object-tracking tasks**.

- Unicorn achieves strong performance in **eight tracking benchmarks**. 

## Introduction

- 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. 

- 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**.

This repository supports the following tasks:

Image-level

- Object Detection

- Instance Segmentation

Video-level

- Single Object Tracking (SOT)

- Multiple Object Tracking (MOT)

- Video Object Segmentation (VOS)

- Multi-Object Tracking and Segmentation (MOTS)

## Demo

Unicorn conquers four tracking tasks (SOT, MOT, VOS, MOTS) using **the same network** with **the same parameters**.

https://user-images.githubusercontent.com/6366788/180479685-c2f4bf3e-3faf-4abe-b401-80150877348d.mp4

## Results

### SOT







### MOT (MOT17)







### MOT (BDD100K) 







### VOS







### MOTS (MOTS Challenge)







### MOTS (BDD100K MOTS)







## Getting started

1. Installation: Please refer to [install.md](assets/install.md) for more details.

2. Data preparation: Please refer to [data.md](assets/data.md) for more details.

3. Training: Please refer to [train.md](assets/train.md) for more details.

4. Testing: Please refer to [test.md](assets/test.md) for more details. 

5. Model zoo: Please refer to [model_zoo.md](assets/model_zoo.md) for more details.

## Citing Unicorn

If you find Unicorn useful in your research, please consider citing:

```bibtex

@inproceedings{unicorn,

  title={Towards Grand Unification of Object Tracking},

  author={Yan, Bin and Jiang, Yi and Sun, Peize and Wang, Dong and Yuan, Zehuan and Luo, Ping and Lu, Huchuan},

  booktitle={ECCV},

  year={2022}

}

```

## Acknowledgments

- 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.

- 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.

- 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.