ABSTRACT
A novel region-based approach is proposed to model semantic concepts using web images. Web images are mined to obtain multiple visual patterns automatically that then are used to model a semantic concept. First, the salient region groups corresponding to the representative visual patterns of a concept are mined and selected as positive samples. Next, a representative visual pattern is built in each salient region group by using a BDA classifier. Finally all the visual patterns are aggregated to describe the concept by using a BDA ensemble approach. Because the proposed method models a semantic concept utilizing multiple visual patterns, it enhances the visual variability of a visual model when learning from diverse web images and improves the robustness of the visual model in handling segmentation-related uncertainties. Experiment results demonstrate our method performs well on generic images including not only "object" concepts, but also complex "scene" concepts.
- http://yahoo.comGoogle Scholar
- http://www.itl.nist.gov/iaui/894.02/projects/trecvidGoogle Scholar
- Jia Li, James Wang, "Automatic Linguistic Indexing of Pictures By a Statistical Modeling Approach", IEEE Trans. PAMI, Vol.25, No.10, pp.1--14, Oct. 2003 Google ScholarDigital Library
- Deng Cai, Xiaofei He, Zhiwei Li, Wei-Ying Ma, Ji-Rong Wen, "Hierarchical Clustering of WWW Image Search Results Using Visual, Textual and Link Analysis," ACM Multimedia(MM), pp.952--959, 2004 Google ScholarDigital Library
- Yongqing Sun,et al. "Visual pattern discovery using web images", Proc. of ACM Multimedia Workshop on Multimedia Information Retrieval, pp.127--136, 2006 Google ScholarDigital Library
- Keiji Yanai, Kobus Barnard, "Probabilistic Web Image Gathering", Proc. of ACM Multimedia Workshop on Multimedia Information Retrieval, pp.57--64, Nov.05 Google ScholarDigital Library
- R. Fergus, L. Fei-Fei, P. Perona and A. Zisserman, "Learning Object Categories from Google's Image Search", IEEE Inter. Conf. Computer Vision, pp. 1816 --1823, Vol.2, 05 Google ScholarDigital Library
- Xiaodan Song, Ching-Yung Lin, Ming-Ting Sun, "Autonomous learning of visual concept models", ISCAS (5) 2005: pp.4598--4601Google Scholar
- Xie X. L., Beni G., "A validity measure for fuzzy clustering", IEEE Trans. PAMI, vol.13, no.8, pp.841--847, Aug. 1991 Google ScholarDigital Library
- Zhou X. S., Huang T. S., "Comparing Discriminate Transformations and SVM for Learning during Multimedia Retrieval", ACM Multimedia, Canada, 2001 Google ScholarDigital Library
Index Terms
- A novel region-based approach to visual concept modeling using web images
Recommendations
A novel method for semantic video concept learning using web images
MM '11: Proceedings of the 19th ACM international conference on MultimediaIn recent years, exploring the rich web image resources has been offering promising solutions to the problem of how to perform low-manual-cost concept learning. However, concept classifiers trained using web images perform poorly when they are directly ...
Image region entropy: a measure of "visualness" of web images associated with one concept
MULTIMEDIA '05: Proceedings of the 13th annual ACM international conference on MultimediaWe propose a new method to measure "visualness" of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by ...
Finding visual concepts by web image mining
WWW '06: Proceedings of the 15th international conference on World Wide WebWe propose measuring "visualness" of concepts with images on the Web, that is, what extent concepts have visual characteristics. This is a new application of "Web image mining". To know which concept has visually discriminative power is important for ...
Comments