{
  "id": 18407,
  "url": "https://arxiv.org/abs/2608.11017v1",
  "title": "R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video",
  "summary": "Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and transcript-based memories rarely preserve persistent object identity or structured spatial change. Existing long-video QA methods mainly emphasize temporal grounding and clip retrieval, while prior 3D scene-graph methods typically assume stronger geometry than free-moti",
  "authors": "Ke Ma, Yamin Mao, Weiming Li, Shuai Tan, Yijie Zhong, Hao Chen et al.",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-11T15:00:15.000Z",
  "fetched_at": "2026-08-12T05:10:43.828Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18407",
  "original_url": "https://arxiv.org/abs/2608.11017v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}