One Identity, Many Roles: Multimodal Entity Coreference
for Enhanced Video Situation Recognition


Balaji Darur1 Amanmeet Garg2 Makarand Tapaswi1
1CVIT, IIIT Hyderabad, India    2Amazon Prime Video, Seattle
Paper arXiv Code (Coming Soon)

Abstract

Coming soon.

Paper


@article{darur2025oneidentity,
  title={{One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition}},
  author={Darur, Balaji and Garg, Amanmeet and Tapaswi, Makarand},
  year={2025}
}