@Article{MarcBola{\~n}os2018,
author="Marc Bola{\~n}os
and Alvaro Peris
and Francisco Casacuberta
and Sergi Solera
and Petia Radeva",
title="Egocentric video description based on temporally-linked sequences",
journal="Journal of Visual Communication and Image Representation",
year="2018",
volume="50",
pages="205--216",
optkeywords="egocentric vision",
optkeywords="video description",
optkeywords="deep learning",
optkeywords="multi-modal learning",
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 1,339 events with 3,991 descriptions, from 55 days acquired by 11 people. Finally, we prove that our proposal outperforms classical attentional encoder-decoder methods for video description.",
optnote="MILAB; no proj",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3109), last updated on Mon, 24 Jan 2022 15:12:34 +0100",
opturl="https://doi.org/10.1016/j.jvcir.2017.11.022",
file=":http://refbase.cvc.uab.es/files/BPC2018.pdf:PDF"
}