Metraipolis › archive › dc_24459205a6c6

Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants — arXiv:2610.05526

Source
arXiv
Original
https://arxiv.org/abs/2610.05526
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:13.874Z
SHA-256 of the archived text
525032adbe9585f30e391e27dfd8795614cf5a1c3d718fba587d044ca2991ed4
Stable URL of this page
https://metraipolis.com/documento/dc_24459205a6c6

How to cite

Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants — arXiv:2610.05526 — arXiv, https://arxiv.org/abs/2610.05526 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24459205a6c6 (Metraipolis archive dc_24459205a6c6, sha256 525032adbe9585f30e391e27dfd8795614cf5a1c3d718fba587d044ca2991ed4)
BibTeX
@misc{dc24459205a6c6,
  title = {Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants — arXiv:2610.05526},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05526},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24459205a6c6; sha256 525032adbe9585f30e391e27dfd8795614cf5a1c3d718fba587d044ca2991ed4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05526. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Egocentric assistants must connect what users say with what they see across long interaction histories. We formalize this challenge as Spatially grounded Conversational Reasoning (SpaCR): cross-scene, recall-oriented, and counterfactual spatial queries that combine user-stated facts with geometric evidence. Direct vision-language models incur high inference costs and context limits as histories grow, while keyframe selection and retrieval can omit objects or evidence needed for complete recall. We propose Spatially grounded Conversational Memory (SpaC-MEM), an object-centric working memory that uses 3D reconstruction and segmentation to ground conversational information in persistent physical objects. It compresses multimodal histories while preserving spatial evidence and allowing object-specific facts to be updated through dialogue. We also introduce Ego-SpaCR, a benchmark comprising 620 ScanNet video sessions augmented with 95 task-oriented conversations and 3,100 evaluation queries. SpaC-MEM achieves the highest overall answer accuracy among the evaluated methods and improves object recall while requiring substantially fewer reference input tokens than native-video baselines. Removing 3D spatial information substantially degrades performance, highlighting the importance of preserving spatial and conversational evidence together.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.05526 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.603Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).