1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
This work addresses the emerging challenge of motion expression in video segmentation for the computer vision community, but it is incremental as it builds on existing RVOS methods.
The paper tackled the Motion Expression guided Video Segmentation (MeViS) task by investigating static-dominant data and frame sampling, achieving a J&F score of 0.5447 and ranking 1st in the CVPR 2024 PVUW Workshop competition.
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.