Paper Info
Title
Hidden Markov Model for Event Photo Stream Segmentation
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
Year
DOI
Venue
2012
10.1109/ICMEW.2012.12
ICME Workshops
Keywords
Field
DocType
unsegmented event photo stream,personal photo set,exif metadata,multiple event,existing photo stream segmentation,single event,event photo stream segmentation,chronological sequence,event photo stream,hidden markov model,photo stream,photo stream segmentation method,statistical significance,feature extraction,vectors,statistical analysis,hidden markov models,stochastic processes,image segmentation,visualization
Training set,Metadata,Computer vision,Pattern recognition,Segmentation,Visualization,Computer science,Image segmentation,Feature extraction,Artificial intelligence,Hidden Markov model,Statistical analysis
Conference
ISSN
Citations 
PageRank 
2330-7927
8
0.47
References 
Authors
12
3
Name
Order
Citations
PageRank
Jesse Prabawa Gozali1121.92
Min-yen Kan22786162.35
Hari Sundaram31984151.57