MeViS

The MeViS dataset/benchmark contains video sequences used to evaluate Referential Video Object Segmentation (RVOS) performance based on natural language descriptions.

Papers using MeViS (3)

Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation2025 · 1 citesEnhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Track2025Referring Video Object Segmentation via Language-aligned Track Selection2024 · 1 cites