Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICMEW.2012.12
Title: Hidden Markov model for event photo stream segmentation
Authors: Gozali, J.P.
Kan, M.-Y. 
Sundaram, H.
Keywords: digital photo library
Event photo stream segmentation
hidden Markov model
Issue Date: 2012
Source: Gozali, J.P., Kan, M.-Y., Sundaram, H. (2012). Hidden Markov model for event photo stream segmentation. Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012 : 25-30. ScholarBank@NUS Repository. https://doi.org/10.1109/ICMEW.2012.12
Abstract: A photo stream is a chronological sequence of photos. Most existing photo stream segmentation methods assume that a photo stream comprises of photos from multiple events and their goal is to produce groups of photos, each corresponding to an event, i.e. they perform automatic albuming. Even if these photos are grouped by event, sifting through the abundance of photos in each event is cumbersome. To help make photos of each event more manageable, we propose a photo stream segmentation method for an event photo stream - the chronological sequence of photos of a single event - to produce groups of photos, each corresponding to a photo-worthy moment in the event. Our method is based on a hidden Markov model with parameters learned from time, EXIF metadata, and visual information from 1) training data of unlabelled, unsegmented event photo streams and 2) the event photo stream we want to segment. In an experiment with over 5000 photos from 28 personal photo sets, our method outperformed all six baselines with statistical significance (p < 0.10 with the best baseline and p < 0.005 with the others).© 2012 IEEE.
Source Title: Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012
URI: http://scholarbank.nus.edu.sg/handle/10635/41331
ISBN: 9780769547299
DOI: 10.1109/ICMEW.2012.12
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

8
checked on Dec 6, 2017

WEB OF SCIENCETM
Citations

5
checked on Nov 20, 2017

Page view(s)

57
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.