THE 6TH LSVOS CHALLENGE - RVOS Track
Organized by ntuLC - Current server time: March 26, 2025, 9 a.m. UTC
First phase
ValidationJuly 1, 2024, midnight UTC
End
Competition EndsAug. 11, 2024, noon UTC
The 6th Large-scale Video Object Segmentation Challenge - Track 2: Referring Video Object Segmentation
Introduction
The 6th LSVOS challenge will be held in conjunction with ECCV 2024 in MiCo Milano. In this edition of the workshop andchallenge, we replace the classic YouTube-VOS benchmark with MOSE and LVOS to study the VOS under more challenging complex environments. MOSE focuses on complex scenes, including the disappearance-reappearance of objects, inconspicuous small objects, heavy occlusions, crowded environments, etc. LVOS focuses on long-term videos, with complex object motion and long-term reappearance. Besides, we also replace the origin YouTube-RVOS benchmark with MeViS. MeViS focuses on referring the target object in a video through its motion descriptions instead of static attributes, which breaks the basic design principles behind existing RVOS methods and boosts the rethinking of motion modeling. In addition, we will hold a series of talks by the leading experts in video understating.
BibTeX
Please consider to cite MeViS if it helps your research.
@inproceedings{MeViS,
title={{MeViS}: A Large-scale Benchmark for Video Segmentation with Motion Expressions},
author={Ding, Henghui and Liu, Chang and He, Shuting and Jiang, Xudong and Loy, Chen Change},
booktitle={ICCV},
year={2023}
}@inproceedings{GRES,
title={{GRES}: Generalized Referring Expression Segmentation},
author={Liu, Chang and Ding, Henghui and Jiang, Xudong},
booktitle={CVPR},
year={2023}
}@article{VLT,
title={{VLT}: Vision-language transformer and query generation for referring segmentation},
author={Ding, Henghui and Liu, Chang and Wang, Suchen and Jiang, Xudong},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2023},
publisher={IEEE}
}A majority of videos in MeViS are from MOSE: Complex Video Object Segmentation Dataset.
@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}
}The data of MeViS is released for non-commercial research purpose only.
The data of MeViS is released for non-commercial research purpose only.
Validation
Start: July 1, 2024, midnight
Description: Submit results on the **val** set.
Test
Start: Aug. 1, 2024, midnight
Description: Testing
Competition Ends
Aug. 11, 2024, noon
You must be logged in to participate in competitions.
Sign In