This technical report describes our 2nd-place solution for the ECCV 2022 YouTube-VIS Long Video Challenge. We adopt the previously proposed online video instance segmentation method IDOL for this challenge. In addition, we use pseudo labels to further help contrastive learning, so as to obtain more temporally consistent instance embedding to improve tracking performance between frames. The proposed method obtains 40.2 AP on the YouTube-VIS 2022 long video dataset and was ranked second place in this challenge. We hope our simple and effective method could benefit further research.
@article{arxiv.2211.09973,
title = {The Runner-up Solution for YouTube-VIS Long Video Challenge 2022},
author = {Junfeng Wu and Yi Jiang and Qihao Liu and Xiang Bai and Song Bai},
journal= {arXiv preprint arXiv:2211.09973},
year = {2022}
}
Comments
The Runner-up Solution for YouTube-VIS Long Video Challenge 2022, ECCV 2022 Workshop. arXiv admin note: text overlap with arXiv:2207.10661