Title :
Geo-informative discriminative image representation by semi-supervised hierarchical topic modeling
Author :
Zijian Li ; Siliang Tang ; Jian Shao ; Weiming Lu ; Yueting Zhuang
Author_Institution :
Coll. of Comput. Sci. & Technol., Zhejiang Univ., Hangzhou, China
Abstract :
Nowadays, the prevalence of sharing tourist photos to online communities has created an increasing demand for mining discriminative architecture aspects from historic landmarks. Some previous researches have demonstrated that topic models could discover discriminative features represented by meaningful visual-topics. However, they seldom exploited the indicative function of geo-tags and the hierarchy in architecture characteristics. In order to utilize this information, we proposed a semi-supervised hierarchical topic modeling approach (namely, shTM). In our approach, every image could be represented by a probability distribution over selected geo-related visual-topics from a partly randomized topic tree. We evaluated our approach on a real-world dataset with over 26 thousand geo-informative photos from Flickr. Experiments show that shTM topics could reveal more discriminative aspects of a specific architecture than other well-known image features, such as HOG and SIFT, on the tasks of automatic photo categorization and geographical information retrieval.
Keywords :
image representation; probability; HOG; SIFT; automatic photo categorization; geo-informative discriminative image representation; geo-informative photos; geo-tags function; geographical information retrieval; mining discriminative architecture; online communities; probability distribution; semisupervised hierarchical topic modeling; Computational modeling; Data models; Integrated circuit modeling; Resource management; Semantics; Training; Vectors; hierarchy; image; models; shTM; topic;
Conference_Titel :
Multimedia and Expo (ICME), 2014 IEEE International Conference on
Conference_Location :
Chengdu
DOI :
10.1109/ICME.2014.6890266