Video Object Segmentation in Cultural Context
Published in CVPR 2027 (under review), 2026
Tracking and segmenting culturally significant objects through video, where the object’s identity depends on cultural knowledge rather than appearance alone.
Status
This work is under review. There is no preprint yet; a link will appear here when one is available.
If it overlaps something you are working on, get in touch; I would rather compare notes early than collide at submission.
Related
It extends the grounding requirement in Seeing Culture (EMNLP 2025) and reasoning segmentation of cultural artifacts from single images into video, and shares the video setting of the Cultural Moment benchmark.