Modeling images as mixtures of image models
作者： Florent C. Perronnin , Yan Liu
DOI:
关键词:
摘要: A system and method for generating an image representation are provided. The is modeled as a set of mixture weights, one each reference models, such Gaussian models (GMMs). weights derived by optimizing objective function in which model associated with its respective weight.
lens.org 参考文章(22)
J Farquhar, H Meng, J Shawe-Taylor, S Szedmak, Improving "bag-of-keypoints" image categorisation: Generative Models and PDF-Kernels ,(2005)
Florent Perronnin, Generic visual categorization method and system ,(2005)
Florent Perronnin, Bags of visual context-dependent words for generic visual categorization ,(2006)
Alexander C. Loui, Sanjiv Kumar, Method for image region classification using unsupervised and supervised learning ,(2002)
Anna Bosch, Andrew Zisserman, Xavier Muñoz, Scene Classification Via pLSA Computer Vision – ECCV 2006. pp. 517- 530 ,(2006) , 10.1007/11744085_40
Florent Perronnin, Christopher Dance, Gabriela Csurka, Marco Bressan, Adapted Vocabularies for Generic Visual Categorization Computer Vision – ECCV 2006. pp. 464- 475 ,(2006) , 10.1007/11744085_36
Milind Naphade, Apostol Natsev, John R. Smith, Method and apparatus for content representation and retrieval in concept model space ,(2003)
G. Csurka, Visual categorization with bags of keypoints european conference on computer vision. ,vol. 1, pp. 22- ,(2004)
Won-jun Hwang, Jong-ha Lee, Tae-Kyun Kim, Seok-cheol Kee, Hyun-woo Kim, Method and apparatus of recognizing face using component-based 2nd-order principal component analysis (PCA)/independent component analysis (ICA) ,(2003)
Hayit Greenspan, Guy Dvir, Yossi Rubner, Context-dependent segmentation and matching in image databases Computer Vision and Image Understanding. ,vol. 93, pp. 86- 109 ,(2004) , 10.1016/J.CVIU.2003.08.004