DocumentCode :
2576825
Title :
Automatic image captioning
Author :
Pan, Jia-Yu ; Yang, Hyung-Jeong ; Duygulu, Pinar ; Faloutsos, Christos
Author_Institution :
Dept. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
Volume :
3
fYear :
2004
fDate :
27-30 June 2004
Firstpage :
1987
Abstract :
We examine the problem of automatic image captioning. Given a training set of captioned images, we want to discover correlations between image features and keywords, so that we can automatically find good keywords for a new image. We experiment thoroughly with multiple design alternatives on large datasets of various content styles, and our proposed methods achieve up to a 45% relative improvement on captioning accuracy over the state of the art.
Keywords :
content-based retrieval; correlation methods; feature extraction; image classification; image retrieval; adaptive blob-tokens; automatic image annotation; automatic image captioning; captioning accuracy; content based image retrieval systems; image feature/keyword correlations; Clustering algorithms; Content based retrieval; Image databases; Image retrieval; Indexing; Information retrieval; Noise reduction; Shape; Statistics; Sun;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on
Print_ISBN :
0-7803-8603-5
Type :
conf
DOI :
10.1109/ICME.2004.1394652
Filename :
1394652
Link To Document :
بازگشت