1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
2024-06-11Code Available1· sign in to hype
Mingqi Gao, Jingnan Luo, Jinyu Yang, Jungong Han, Feng Zheng
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/tapall-ai/mevis_track_solution_2024OfficialIn paperpytorch★ 32
Abstract
Motion Expression guided Video Segmentation (MeViS), as an emerging task, poses many new challenges to the field of referring video object segmentation (RVOS). In this technical report, we investigated and validated the effectiveness of static-dominant data and frame sampling on this challenging setting. Our solution achieves a J&F score of 0.5447 in the competition phase and ranks 1st in the MeViS track of the PVUW Challenge. The code is available at: https://github.com/Tapall-AI/MeViS_Track_Solution_2024.