Awesome
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
š [Homepage] ā š[Arxiv]
This repository contains information and tools for the MOSE dataset.
Download
[š„02.09.2023: Dataset has been released!]
ā¬ļø Get the dataset from:
- āļø OneDrive (Recommended)
- āļø Google Drive
- āļø Baidu Pan (Access Code: MOSE)
š¦ Or use gdown:
# train.tar.gz
gdown 'https://drive.google.com/uc?id=ID_removed_to_avoid_overaccesses_get_it_by_yourself'
# valid.tar.gz
gdown 'https://drive.google.com/uc?id=ID_removed_to_avoid_overaccesses_get_it_by_yourself'
# test set will be released when competition starts.
Please also check the SHA256 sum of the files to ensure the data intergrity:
3f805e66ecb576fdd37a1ab2b06b08a428edd71994920443f70d09537918270b train.tar.gz
884baecf7d7e85cd35486e45d6c474dc34352a227ac75c49f6d5e4afb61b331c valid.tar.gz
Evaluation
[š„02.16.2023: Our CodaLab competition is on live now!]
Please submit your results on
- šÆ CodaLab.
File Structure
The dataset follows a similar structure as DAVIS and Youtube-VOS. The dataset consists of two parts: JPEGImages
which holds the frame images, and Annotations
which contains the corresponding segmentation masks. The frame images are numbered using five-digit numbers. Annotations are saved in color-pattlate mode PNGs like DAVIS.
Please note that while annotations for all frames in the training set are provided, annotations for the validation set will only include the first frame.
<train/valid.tar>
ā
āāā Annotations
ā ā
ā āāā <video_name_1>
ā ā āāā 00000.png
ā ā āāā 00001.png
ā ā āāā ...
ā ā
ā āāā <video_name_2>
ā ā āāā 00000.png
ā ā āāā 00001.png
ā ā āāā ...
ā ā
ā āāā <video_name_...>
ā
āāā JPEGImages
ā
āāā <video_name_1>
ā āāā 00000.jpg
ā āāā 00001.jpg
ā āāā ...
ā
āāā <video_name_2>
ā āāā 00000.jpg
ā āāā 00001.jpg
ā āāā ...
ā
āāā <video_name_...>
BibTeX
Please consider to cite MOSE if it helps your research.
@inproceedings{MOSE,
title={{MOSE}: A New Dataset for Video Object Segmentation in Complex Scenes},
author={Ding, Henghui and Liu, Chang and He, Shuting and Jiang, Xudong and Torr, Philip HS and Bai, Song},
booktitle={ICCV},
year={2023}
}
License
MOSE is licensed under a CC BY-NC-SA 4.0 License. The data of MOSE is released for non-commercial research purpose only.