MemoVision: A Digital Catalog for Everyday Interactions
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41646-41648
DOI: 10.1609/aaai.v40i48.42368 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Lai Xing Ng und 2 weiteren Autor:innen.
Abstract (Originalsprache)
We present MemoVision, a digital catalog system that captures semantic, spatial, temporal and interaction information as users move around physical environments using client devices such as smart glasses. The system utilizes open-vocabulary semantic segmentation and 3D scans to store objects-of-interest with comprehensive semantic, spatial, temporal and interaction labels. Our demonstration shows multimodal information query and retrieval capabilities, supporting specific queries about object locations, temporal events and user interactions including eye gaze and hand poses, enabling more contextualized responses compared to current multimodal large language models.
Zitieren
APA
Ng, L. X., Tang, K. T. W., & Tan, J. J. W. (2026). MemoVision: A Digital Catalog for Everyday Interactions. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41646-41648. https://doi.org/10.1609/aaai.v40i48.42368
Vancouver
Ng LX, Tang KTW, Tan JJW. MemoVision: A Digital Catalog for Everyday Interactions. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41646-41648. doi:10.1609/aaai.v40i48.42368
BibTeX
@article{Ng2026,
author = {Ng, Lai Xing and Tang, Keith Tien Wei and Tan, Jacky Jie Wei},
title = {MemoVision: A Digital Catalog for Everyday Interactions},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41646--41648},
doi = {10.1609/aaai.v40i48.42368}
}
EUVIMED