Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/TAO-Dataset/tao
Code for downloading and using the TAO dataset: http://taodataset.org/
https://github.com/TAO-Dataset/tao
Last synced: about 1 month ago
JSON representation
Code for downloading and using the TAO dataset: http://taodataset.org/
- Host: GitHub
- URL: https://github.com/TAO-Dataset/tao
- Owner: TAO-Dataset
- License: other
- Created: 2020-05-18T13:59:01.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2022-02-08T05:33:00.000Z (almost 3 years ago)
- Last Synced: 2024-08-01T20:37:21.964Z (4 months ago)
- Language: Python
- Size: 202 KB
- Stars: 189
- Watchers: 12
- Forks: 32
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-autonomous - TAO: A Large-Scale Benchmark for Tracking Any Object
- awesome-multiple-object-tracking - TAO
README
# TAO: A Large-Scale Benchmark for Tracking Any Object
[[Paper](https://arxiv.org/abs/2005.10356)] [[Website](http://taodataset.org)]
[Achal Dave](http://www.achaldave.com/), [Tarasha Khurana](http://www.cs.cmu.edu/~tkhurana/), [Pavel Tokmakov](https://pvtokmakov.github.io/home/), [Cordelia Schmid](https://thoth.inrialpes.fr/~schmid/), [Deva Ramanan](http://www.cs.cmu.edu/~deva/)
## Latest updates
- \[2020.10.25\]: Added [docs](https://github.com/TAO-Dataset/tao/blob/master/docs/trackers.md#single-object-trackers) for running single-object trackers. See [here](https://github.com/TAO-Dataset/tao/issues/23#issuecomment-716068985) for how to add your own SOT tracker!
- \[2020.07.10\]: The ECCV challenge is now live at the
[MOTChallenge website](https://motchallenge.net/results/TAO_Challenge/)!
See [here](docs/challenge.md) for more details.
- \[2020.07.02\]: TAO was accepted to ECCV '20 as a spotlight presentation!
- \[2020.02.20\]: We will be hosting a workshop and challenge at ECCV'20. See [here](http://taodataset.org/workshop/) for details.
## Setup
1. Clone this repo
```
git clone https://github.com/TAO-Dataset/tao
```
1. Install TAO toolkit:
```
pip install git+https://github.com/TAO-Dataset/tao
```
## Download dataset
See [download instructions](./docs/download.md).
## Challenge
We will be hosting a challenge at our
[ECCV '20 workshop](taodataset.org/workshop/). See [here](docs/challenge.md) for details.
## Evaluation
See [evaluation information](./docs/evaluation.md). Contains information on submitting to the challenge server.
## Run baseline trackers
See [tracker instructions](./docs/trackers.md).
## Questions?
Please see the [faqs](./docs/faqs.md) to check if we've anticipated your
question. If not, for questions about TAO usage or the challenge, please use
this Google Group: https://groups.google.com/forum/#!forum/tao-dataset/
For bug reports regarding the toolkit, annotations, or image download, please
file an issue in this repository.