Preprint
Aug 2026
R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video
R4DSG introduces a relative 4D scene graph memory for long egocentric video, built on recent RGB-only advances in promptable video segmentation, temporal propagation, and relative 3D lifting, and produces a retrieval-ready memory directly usable for long-horizon question answering.
Ke Ma, Ya-Min Mao, Weiming Li et al.
· 0 citations