2nd Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
This work addresses video object segmentation guided by natural language with motion descriptions for computer vision researchers, but it is incremental as it builds on existing RVOS methods.
The paper tackled the Motion Expression guided Video Segmentation task by enhancing RVOS methods with mask information from a video instance segmentation model and using SAM for spatial refinement, achieving scores of 49.92 J &F in validation and 54.20 J &F in test, securing 2nd place in the challenge.
Motion Expression guided Video Segmentation is a challenging task that aims at segmenting objects in the video based on natural language expressions with motion descriptions. Unlike the previous referring video object segmentation (RVOS), this task focuses more on the motion in video content for language-guided video object segmentation, requiring an enhanced ability to model longer temporal, motion-oriented vision-language data. In this report, based on the RVOS methods, we successfully introduce mask information obtained from the video instance segmentation model as preliminary information for temporal enhancement and employ SAM for spatial refinement. Finally, our method achieved a score of 49.92 J &F in the validation phase and 54.20 J &F in the test phase, securing the final ranking of 2nd in the MeViS Track at the CVPR 2024 PVUW Challenge.