miranheo

Ph.D. student @ Yonsei Univ.

Yonsei UniversitySeoul, South Korea

Pinned Repositories

VISA
[ECCV24] VISA: Reasoning Video Object Segmentation via Large Language Model
Language:Python143 6 104
Elysium
[ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLM
Language:Python64 7 142
GenVIS
[CVPR'23] A Generalized Framework for Video Instance Segmentation
Language:Python125 7 105
VITA
VITA: Video Instance Segmentation via Object Token Association (NeurIPS 2022)
Language:Python100 7 1610

miranheo's Repositories

miranheo/GenVIS
[CVPR'23] A Generalized Framework for Video Instance Segmentation
Language:Python125 7 105