Automated social event detection in large photo collections

Automated social event detection in large photo collections

Abstract

The detection of a specific social event requires for high semantic understanding in the interpretation of particular event characteristics such as its type and location. In many cases, photos capturing different events at the same (or highly similar) locations can hardly be distinguished by each other. Available metadata can provide assistance where there is no expert knowledge at hand. However, metadata often lack completeness and reliability. In this paper, we explore the feasibility of a fully automated approach for the detection of specific social events. In comparison to related approaches, we do not incorporate query-specific processing and we perform no manual adaptation of the input query. The resulting approach is applicable to arbitrary event types.

Grafik Top
Authors
  • Zaharieva, Maia
  • Zeppelzauer, Matthias
  • Breiteneder, Christian
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings
Event Title
ACM International Conference on Multimedia Retrieval (ICMR)
Divisions
Multimedia Information Systems
Subjects
Multimedia
Event Location
Dallas, Texas, USA
Event Type
Conference
Event Dates
April 16-19, 2013
Publisher
ACM
Page Range
pp. 167-174
Date
2013
Export
Grafik Top