Title :
Learning the semantics of words and pictures
Author :
Barnard, Kobus ; Forsyth, David
Author_Institution :
Comput. Div., California Univ., Berkeley, CA, USA
Abstract :
We present a statistical model for organizing image collections which integrates semantic information provided by associate text and visual information provided by image features. The model is very promising for information retrieval tasks such as database browsing and searching for images based on text and/or image features. Furthermore, since the model learns relationships between text and image features, it can be used for novel applications such as associating words with pictures, and unsupervised learning for object recognition
Keywords :
image retrieval; information retrieval; unsupervised learning; visual databases; associate text; database browsing; image collections; image features; information retrieval tasks; object recognition; semantic information; unsupervised learning; visual information; Image databases; Image retrieval; Image segmentation; Information retrieval; Object recognition; Organizing; Predictive models; Spatial databases; Statistics; Unsupervised learning;
Conference_Titel :
Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7695-1143-0
DOI :
10.1109/ICCV.2001.937654
