We develop nonparametric Bayesian models for multiscale representations of images depicting natural scene categories. Individual features or wavelet coefficients are marginally de...
Jyri J. Kivinen, Erik B. Sudderth, Michael I. Jord...
We study in this paper the problem of bridging the semantic gap between low-level image features and high-level semantic concepts, which is the key hindrance in content-based imag...
— This paper presents a novel approach for visual scene modeling and classification, investigating the combined use of text modeling methods and local invariant features. Our wo...
Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Da...
The paper proposes a new method to perform foreground detection by means of background modeling using the tensor concept. Sometimes, statistical modelling directly on image values...