AI RESEARCH
VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation
arXiv CS.CV
•
ArXi:2603.27060v1 Announce Type: new Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a vision language model with a separate propagation module often fail to capture rapidly changing spatiotemporal dynamics and to handle queries requiring multi-step reasoning, leading to sharp performance drops on motion-intensive and reasoning-oriented videos beyond static RVOS benchmarks.