Time and space for segmenting personal photo sets

Posted onAuthorNuno Datia

Nuno Datia, João Moura Pires, Nuno Correia: Time and space for segmenting personal photo sets. In: Multimedia Tools and Applications, pp. 1–33, 2016, ISSN: 1573-7721.

Datia, Nuno; Pires, João Moura; Correia, Nuno
Time and space for segmenting personal photo sets (Journal Article)
Multimedia Tools and Applications, pp. 1–33, 2016, ISSN: 1573-7721.

Abstract

A personal collection of photos shows large variability in the depicted items, making difficult a fully automated solution to cope with sensory and semantic gaps. Emotions and non-visual contextual information can be very important to address those problems. Manual annotations are key, but their time-consuming nature alienate users from doing them. One solution is to lower the annotation effort, building solutions on top of algorithms that prepare a context separation, making possible the reuse of annotations. In this paper we present a segmentation algorithm that uses spatio-temporal information to segment personal photo collections. The algorithm is assessed in a user study, using the participants own photos. The results show users make none or few changes to the proposed segmentations, indicating an acceptance of the algorithm outcome.

Links

BibTeX (Download)

@article{Datia2016,
title = {Time and space for segmenting personal photo sets},
author = { Nuno Datia and João Moura Pires and Nuno Correia},
url = {https://rdcu.be/6oz7
http://staresearch.net/wp-content/uploads/2016/03/MTA2015.pdf
http://dx.doi.org/10.1007/s11042-016-3341-2},
doi = {10.1007/s11042-016-3341-2},
issn = {1573-7721},
year  = {2016},
date = {2016-01-01},
journal = {Multimedia Tools and Applications},
pages = {1--33},
abstract = {A personal collection of photos shows large variability in the depicted items, making difficult a fully automated solution to cope with sensory and semantic gaps. Emotions and non-visual contextual information can be very important to address those problems. Manual annotations are key, but their time-consuming nature alienate users from doing them. One solution is to lower the annotation effort, building solutions on top of algorithms that prepare a context separation, making possible the reuse of annotations. In this paper we present a segmentation algorithm that uses spatio-temporal information to segment personal photo collections. The algorithm is assessed in a user study, using the participants own photos. The results show users make none or few changes to the proposed segmentations, indicating an acceptance of the algorithm outcome.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}