Haojie Li
ABSTRACT
Besides the traditional textual semantic description to convey the meanings of a certain concept or word, visual illustration is a complementary, yet important and more intuitive way to interpret the word. Thus the technique that converts word to image is desirable though it is very difficult. Since a word usually has different semantic aspects, we need several correct and semantic-rich images to represent the word. In this paper, we explore how to leverage the web image collections to fulfill such task and develop a novel multimedia application system, Word2Image. Various techniques, including the correlation analysis, semantic and visual clustering are adapted into our system to produce sets of high quality, precise, diverse and representative images to visually translate a given word. The objective and subjective evaluations show the feasibility and effectiveness of our approach.
- Google image search engine, http://images.google.com/Google Scholar
- AltaVista image search, http://www.altavista.com/image/Google Scholar
- Flickr, http://www.flickr.com/Google Scholar
- D. Cai, X. He, Z. Li, W.Y. Ma, and J. R. Wen, "Hierarchical clustering of www image search results using visual, textual and link information", ACM MM 2004 Google ScholarDigital Library
- Bin Gao, Tie-Yan Liu, Xin Zheng, Qian-Sheng Cheng, Wei-Ying Ma, "Web image clustering by consistent utilization of visual features and surrounding texts", ACM MM, 2005 Google ScholarDigital Library
- Feng Jing, Changhu Wang, et al, "IGroup: web image search results clustering", ACM MM, 2006 Google ScholarDigital Library
- X. Zhu, A. B. Goldberg, et al, "A Text-to-Picture Synthesis System for Augmenting Communication", AAAI 2007 Google ScholarDigital Library
- Lyndon S. Kennedy, Mor Naaman: "Generating diverse and representative image search results for landmarks", WWW 2008 Google ScholarDigital Library
- Berry, Michael W, "Survey of Text Mining I: Clustering, Classification, and Retrieval", Springer-Verlag, New York, 2003 Google ScholarDigital Library
- A. Jain and R. Dube, "Algorithms for Clustering Data", Prentice-Hall, Englewood Cliffs, NJ, 1988 Google ScholarDigital Library
- M. F. Porter, "An algorithm for suffix stripping", Program, 14(3), pp 130--137, 1980Google ScholarCross Ref
- Christiane Fellbaum, "WordNet: An Electronic Lexical Database", MIT Press, 1999Google Scholar
- X.-L. Liu, T. Mei, X.-S. Hua, et al, "Video Collage", ACM MM 2007 Google ScholarDigital Library
Index Terms
- Word2Image: towards visual interpreting of words
Recommendations
Multimedia sign language dictionary for the deaf and hard of hearing
i-CREATe '11: Proceedings of the 5th International Conference on Rehabilitation Engineering & Assistive TechnologyMultimedia sign language dictionary for the deaf and hard of hearing is a computer based application which is designed to assist people, especially children with hearing impaired problem to master their sign language and speech reading. The main module ...
Multilingual phrase sampling for text entry evaluations
Presents a novel phrase sampling method for multilingual text entry.The method uses knowledge graphs derived from BabelNet.The method has clear benefits over other sampling techniques in several scenarios. Text entry evaluations are typically conducted ...
Representatively memorable: sampling the right phrase set to get the text entry experiment right
CHI '14: Proceedings of the SIGCHI Conference on Human Factors in Computing SystemsIn text entry experiments, memorability is a desired property of the phrases used as stimuli. Unfortunately, to date there is no automated method to achieve this effect. As a result, researchers have to use either manually curated English-only phrase ...
Comments