Personal AI Agent for Camera Roll VQA

Arxiv CS.CV (computer vision)

Paper introduces a personal AI agent that accesses a user's camera roll to answer visual questions. The agent retrieves relevant photos for queries ranging from simple facts to complex questions.

computer-vision

Arxiv CS.CV (computer vision)·Thao NguyenKrishna Kumar SinghDonghyun KimYong Jae LeeYuheng Li

6 days ago