Files
Document type
ArticleVersion
Accepted versionPublication date
Publication license
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/143165
Egocentric video description based on temporally-linked sequences
Journal Title
Director/Tutor
Journal ISSN
Volume Title
Related resource
Abstract
Egocentric vision consists in acquiring images along the day from a first person point-of-view using wearable cameras. The automatic analysis of this information allows to discover daily patterns for improving the quality of life of the user. A natural topic that arises in egocentric vision is storytelling, that is, how to understand and tell the story relying behind the pictures. In this paper, we tackle storytelling as an egocentric sequences description problem. We propose a novel methodology that exploits information from temporally neighboring events, matching precisely the nature of egocentric sequences. Furthermore, we present a new method for multimodal data fusion consisting on a multi-input attention recurrent network. We also release the EDUB-SegDesc dataset. This is the first dataset for egocentric image sequences description, consisting of 1339 events with 3991 descriptions, from 55 days acquired by 11 people. Finally, we prove that our proposal outperforms classical attentional encoder-decoder methods for video description.
Subject (English)
Citation
Citation
BOLAÑOS SOLÀ, Marc, et al. Egocentric video description based on temporally-linked sequences. Journal of Visual Communication and Image Representation. 2018. Vol. 50, num. 205-216. ISSN 1047-3203. [consulted: 9 of August of 2026]. Available at: https://hdl.handle.net/2445/143165