Using High-Level Semantic Features in Video Retrieval

by: Wujie Zheng, Jianmin Li, Zhangzhang Si, Fuzong Lin, Bo Zhang

Image and Video Retrieval (2006), pp. 370-379.

View FullText article

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

arjen, dvallet, NETS-UAM (group), NETS (group), javimol

Find related articles with these CiteULike tags

annotation, image-retrieval, mir, multimedia, no-tag, rank_aggregation, semantic, video-retrieval

Abstract

Extraction and utilization of high-level semantic features are critical for more effective video retrieval. However, the performance of video retrieval hasn’t benefited much despite of the advances in high-level feature extraction. To make good use of high-level semantic features in video retrieval, we present a method called pointwise mutual information weighted scheme(PMIWS). The method makes a good judgment of the relevance of all the semantic features to the queries, taking the characteristics of semantic features into account. The method can also be extended for the fusion of multi-modalities. Experiment results based on TRECVID2005 corpus demonstrate the effectiveness of the method.

@incollection{citeulike:2334379, abstract = {Extraction and utilization of high-level semantic features are critical for more effective video retrieval. However, the performance of video retrieval hasn’t benefited much despite of the advances in high-level feature extraction. To make good use of high-level semantic features in video retrieval, we present a method called pointwise mutual information weighted scheme(PMIWS). The method makes a good judgment of the relevance of all the semantic features to the queries, taking the characteristics of semantic features into account. The method can also be extended for the fusion of multi-modalities. Experiment results based on TRECVID2005 corpus demonstrate the effectiveness of the method.}, author = {Zheng, Wujie and Li, Jianmin and Si, Zhangzhang and Lin, Fuzong and Zhang, Bo }, citeulike-article-id = {2334379}, doi = {http://dx.doi.org/10.1007/11788034\_38}, journal = {Image and Video Retrieval}, keywords = {annotation, image-retrieval, video-retrieval}, pages = {370--379}, posted-at = {2008-02-05 11:13:22}, priority = {0}, title = {Using High-Level Semantic Features in Video Retrieval}, url = {http://dx.doi.org/10.1007/11788034\_38}, year = {2006} }

RIS record

TY - CHAP ID - citeulike:2334379 L3 - citeulike-article-id:2334379 TI - Using High-Level Semantic Features in Video Retrieval JF - Image and Video Retrieval SP - 370 EP - 379 N2 - Extraction and utilization of high-level semantic features are critical for more effective video retrieval. However, the performance of video retrieval hasn’t benefited much despite of the advances in high-level feature extraction. To make good use of high-level semantic features in video retrieval, we present a method called pointwise mutual information weighted scheme(PMIWS). The method makes a good judgment of the relevance of all the semantic features to the queries, taking the characteristics of semantic features into account. The method can also be extended for the fusion of multi-modalities. Experiment results based on TRECVID2005 corpus demonstrate the effectiveness of the method. KW - annotation KW - image-retrieval KW - video-retrieval AU - Zheng, Wujie AU - Li, Jianmin AU - Si, Zhangzhang AU - Lin, Fuzong AU - Zhang, Bo PY - 2006/// UR - http://dx.doi.org/10.1007/11788034_38 ER -

RIS BibTeX