M$^3$-VOS

💡 Description

A new benchmark, Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (M$^3$-VOS), to verify the ability of models to understand object phases, which consists of 479 high-resolution videos spanning over 10 distinct everyday scenarios. We collected 205,181 masks, with an average track duration of 14.27s. M$^3$-VOS covers 120+ categories of objects across 6 phases within 14 scenarios, encompassing 23 specific phase transitions.

• Venue: CVPR2025
• Repository: Tool 🛠️, Page🏠
• Paper: arxiv.org/html/2412.13803v2
• Point of Contact: Jiaxin Li , Zixuan Chen