Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
11-2012
Abstract
Associating celebrity faces appearing in videos with their names is of increasingly importance with the popularity of both celebrity videos and related queries. However, the problem is not yet seriously studied in Web video domain. This paper proposes a Community connected Celebrity Name-Face Association approach (CCNFA), where the community is regarded as an intermediate connector to facilitate the association. Specifically, with the names and faces extracted from Web videos, C-CNFA decomposes the association task into a three-step framework: community discovering, community matching and celebrity face tagging. To achieve the goal of efficient name-face association under this umbrella, algorithms such as the constrained density-based clustering and exemplar based voting are developed by leveraging different pieces of visual and contextual cues. The evaluation on 0.4 million faces and 144 celebrities shows the effectiveness of the proposed C-CNFA approach. Moreover, using the obtained associations, encouraging results are reported in celebrity video ranking.
Keywords
celebrity videos, community analysis, name-face association
Discipline
Data Storage Systems | Graphics and Human Computer Interfaces
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of the 20th ACM international conference on Multimedia, MM 2012, Nara, Japan, October 29 - November 2
First Page
809
Last Page
812
ISBN
9781450310895
Identifier
10.1145/2393347.2396318
Publisher
ACM
City or Country
Nara, Japan
Citation
CHEN, Zhineng; NGO, Chong-wah; CAO, Juan; and ZHANG, Wei.
Community as a connector: Associating faces with celebrity names in web videos. (2012). Proceedings of the 20th ACM international conference on Multimedia, MM 2012, Nara, Japan, October 29 - November 2. 809-812.
Available at: https://ink.library.smu.edu.sg/sis_research/6515
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.