TY - GEN
T1 - Dual cross-media relevance model for image annotation
AU - Liu, Jing
AU - Wang, Bin
AU - Li, Mingjing
AU - Li, Zhiwei
AU - Ma, Weiying
AU - Lu, Hanqing
AU - Ma, Songde
N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].
PY - 2007
Y1 - 2007
N2 - Image annotation has been an active research topic in recent years due to its potential impact on both image understanding and web image retrieval. Existing relevance-model-based methods perform image annotation by maximizing the joint probability of images and words, which is calculated by the expectation over training images. However, the semantic gap and the dependence on training data restrict their performance and scalability. In this paper, a dual cross-media relevance model (DCMRM) is proposed for automatic image annotation, which estimates the joint probability by the expectation over words in a pre-defined lexicon. DCMRM involves two kinds of critical relations in image annotation. One is the word-to-image relation and the other is the word-to-word relation. Both relations can be estimated by using search techniques on the web data as well as available training data. Experiments conducted on the Corel dataset and a web image dataset demonstrate the effectiveness of the proposed model. Copyright 2007 ACM.
AB - Image annotation has been an active research topic in recent years due to its potential impact on both image understanding and web image retrieval. Existing relevance-model-based methods perform image annotation by maximizing the joint probability of images and words, which is calculated by the expectation over training images. However, the semantic gap and the dependence on training data restrict their performance and scalability. In this paper, a dual cross-media relevance model (DCMRM) is proposed for automatic image annotation, which estimates the joint probability by the expectation over words in a pre-defined lexicon. DCMRM involves two kinds of critical relations in image annotation. One is the word-to-image relation and the other is the word-to-word relation. Both relations can be estimated by using search techniques on the web data as well as available training data. Experiments conducted on the Corel dataset and a web image dataset demonstrate the effectiveness of the proposed model. Copyright 2007 ACM.
KW - Image annotation
KW - Image retrieval
KW - Relevance model
KW - Word correlation
UR - https://www.scopus.com/pages/publications/37849050214
UR - https://www.scopus.com/pages/publications/37849050214#tab=impact
U2 - 10.1145/1291233.1291380
DO - 10.1145/1291233.1291380
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9781595937025
T3 - Proceedings of the ACM International Multimedia Conference and Exhibition
SP - 605
EP - 614
BT - Proceedings of the Fifteenth ACM International Conference on Multimedia, MM'07
T2 - 15th ACM International Conference on Multimedia, MM'07
Y2 - 24 September 2007 through 29 September 2007
ER -