Virtual multimedia libraries built from the web
作者： Neil C. Rowe
关键词: Expert system 、 Interface (Java) 、 Multimedia 、 Computer science 、 Navy 、 Index (publishing) 、 Crawling 、 Artificial neural network 、 World Wide Web
摘要: We have developed a tool MARIE-4 for building virtual libraries of multimedia (images, video, and audio) by automatically exploring (crawling) specified subdomain the World Wide Web to create an index based on caption keywords. Our approach uses carefully-researched criteria identify rate text, employs both expert system neural network. used it keyword-based interface nearly all nontrivial captioned publicly-accessible U.S. Navy images (667,573), video (8,290), audio (2,499), called Virtual Multimedia Library (NAVMULIB).
core.ac.uk
acm.org
sci-hub.se 参考文章(4)
N.C. Rowe, Marie-4: a high-recall, self-improving Web crawler that finds images using captions IEEE Intelligent Systems. ,vol. 17, pp. 8- 14 ,(2002) , 10.1109/MIS.2002.1024745
Rohini K. Srihari, Use of captions and other collateral text in understanding photographs Artificial Intelligence Review. ,vol. 8, pp. 409- 430 ,(1995) , 10.1007/BF00849728
Stan Sclaroff, Marco La Cascia, Saratendu Sethi, Leonid Taycher, Unifying textual and visual cues for content-based image retrieval on the World Wide Web Computer Vision and Image Understanding. ,vol. 75, pp. 86- 98 ,(1999) , 10.1006/CVIU.1999.0765
SOUGATA MUKHERJEA, JUNGHOO CHO, Automatically Determining Semantics for World Wide Web Multimedia Information Retrieval Journal of Visual Languages and Computing. ,vol. 10, pp. 585- 606 ,(1999) , 10.1006/JVLC.1999.0147