Visual summary of egocentric photostreams by representative keyframes

M. Bolanos; Ricard Mestre; E. Talavera; Xavier Giró-i-Nieto; Petia Radeva

doi:10.1109/ICMEW.2015.7169863

Visual summary of egocentric photostreams by representative keyframes

M. Bolanos, Ricard Mestre, E. Talavera, Xavier Giró-i-Nieto, Petia Radeva

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

29 Citations (Scopus)

Abstract

Building a visual summary from an egocentric photostream captured by a lifelogging wearable camera is of high interest for different applications (e.g. memory reinforcement). In this paper, we propose a new summarization method based on keyframes selection that uses visual features extracted by means of a convolutional neural network. Our method applies an unsupervised clustering for dividing the photostreams into events, and finally extracts the most relevant keyframe for each event. We assess the results by applying a blind-taste test on a group of 20 people who assessed the quality of the summaries.

Original language	English
Title of host publication	2015 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2015
Subtitle of host publication	Turin, Italy, June 29-July 3, 2015
Publisher	IEEE
Number of pages	6
ISBN (Print)	978-1-4799-7079-7
DOIs	https://doi.org/10.1109/ICMEW.2015.7169863
Publication status	Published - 2015
Externally published	Yes

Access to Document

10.1109/ICMEW.2015.7169863

Cite this

@inproceedings{5f268696de0d45cbaf899ade7491c2e5,

title = "Visual summary of egocentric photostreams by representative keyframes",

abstract = "Building a visual summary from an egocentric photostream captured by a lifelogging wearable camera is of high interest for different applications (e.g. memory reinforcement). In this paper, we propose a new summarization method based on keyframes selection that uses visual features extracted by means of a convolutional neural network. Our method applies an unsupervised clustering for dividing the photostreams into events, and finally extracts the most relevant keyframe for each event. We assess the results by applying a blind-taste test on a group of 20 people who assessed the quality of the summaries.",

author = "M. Bolanos and Ricard Mestre and E. Talavera and Xavier Gir{\'o}-i-Nieto and Petia Radeva",

year = "2015",

doi = "10.1109/ICMEW.2015.7169863",

language = "English",

isbn = "978-1-4799-7079-7",

booktitle = "2015 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2015",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Visual summary of egocentric photostreams by representative keyframes

AU - Bolanos, M.

AU - Mestre, Ricard

AU - Talavera, E.

AU - Giró-i-Nieto, Xavier

AU - Radeva, Petia

PY - 2015

Y1 - 2015

N2 - Building a visual summary from an egocentric photostream captured by a lifelogging wearable camera is of high interest for different applications (e.g. memory reinforcement). In this paper, we propose a new summarization method based on keyframes selection that uses visual features extracted by means of a convolutional neural network. Our method applies an unsupervised clustering for dividing the photostreams into events, and finally extracts the most relevant keyframe for each event. We assess the results by applying a blind-taste test on a group of 20 people who assessed the quality of the summaries.

AB - Building a visual summary from an egocentric photostream captured by a lifelogging wearable camera is of high interest for different applications (e.g. memory reinforcement). In this paper, we propose a new summarization method based on keyframes selection that uses visual features extracted by means of a convolutional neural network. Our method applies an unsupervised clustering for dividing the photostreams into events, and finally extracts the most relevant keyframe for each event. We assess the results by applying a blind-taste test on a group of 20 people who assessed the quality of the summaries.

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-84945559602&partnerID=MN8TOARS

U2 - 10.1109/ICMEW.2015.7169863

DO - 10.1109/ICMEW.2015.7169863

M3 - Conference contribution

SN - 978-1-4799-7079-7

BT - 2015 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2015

PB - IEEE

ER -

Visual summary of egocentric photostreams by representative keyframes

Abstract

Access to Document

Other files and links

Fingerprint

Cite this