We present a novel model for human action categorization. A video sequence is represented as a collection of spatial and spatial-temporal features by extracting static and dynamic...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
This paper proposes a general framework called Markov stationary features (MSF) to extend histogram based features. The MSF characterizes the spatial co-occurrence of histogram pa...
We present a fast and accurate framework for registration of multi-modal volumetric images based on decoupled estimation of registration parameters utilizing spatial information i...
Parastoo Sadeghi, Ramtin Shams, Richard I. Hartley...
This paper describes a system that can build appearance models of animals automatically from a video sequence of the relevant animal with no explicit supervisory information. The ...