Transfer tagging from image to video

Yang, Yang, Yang, Yi, Huang, Zi and Shen, Heng Tao (2011). Transfer tagging from image to video. In: MM '11 Proceedings of the 19th ACM international conference on Multimedia. 19th ACM International Conference on Multimedia ACM Multimedia 2011 (MM’11), Scottsdale, AZ, United States, (1137-1140). 28 November-01 December 2011. doi:10.1145/2072298.2071958

Author Yang, Yang
Yang, Yi
Huang, Zi
Shen, Heng Tao
Title of paper Transfer tagging from image to video
Language of Title eng
Conference name 19th ACM International Conference on Multimedia ACM Multimedia 2011 (MM’11)
Conference location Scottsdale, AZ, United States
Conference dates 28 November-01 December 2011
Convener Association for Computing Machinery
Proceedings title MM '11 Proceedings of the 19th ACM international conference on Multimedia
Language of Proceedings Title eng
Journal name MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops
Language of Journal Name eng
Place of Publication New York, United States
Publisher ACM Press
Publication Year 2011
Sub-type Fully published paper
DOI 10.1145/2072298.2071958
Open Access Status
ISBN 9781450306164
Start page 1137
End page 1140
Total pages 4
Collection year 2012
Language eng
Formatted Abstract/Summary
Nowadays massive amount of web video datum has been emerging on the Internet. To achieve an effective and efficient video retrieval, it is critical to automatically assign semantic keywords to the videos via content analysis. However, most of the existing video tagging methods suffer from the problem of lacking sufficient tagged training videos due to high labor cost of manual tagging. Inspired by the observation that there are much more well-labeled data in other yet relevant types of media (e.g. images), in this paper we study how to build a "cross-media tunnel" to transfer external tag knowledge from image to video. Meanwhile, the intrinsic data structures of both image and video spaces are well explored for inferring tags. We propose a Cross-Media Tag Transfer (CMTT) paradigm which is able to: 1) transfer tag knowledge between image and video by minimizing their distribution difference; 2) infer tags by revealing the underlying manifold structures embedded within both image and video spaces. We also learn an explicit mapping function to handle unseen videos. Experimental results have been reported and analyzed to illustrate the superiority of our proposal.
Keyword Video tagging
Tag transfer
Tag inference
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ

Version Filter Type
Citation counts: Scopus Citation Count Cited 8 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 06 Mar 2012, 09:59:49 EST by Dr Helen Huang on behalf of School of Information Technol and Elec Engineering