In this paper we present two contributions to improve accuracy and speed of an image search system based on bag-of-features: a contextual dissimilarity measure (CDM) and an effici...
Current approaches to motion category recognition typically focus on either full spatiotemporal volume analysis (holistic approach) or analysis of the content of spatiotemporal in...
The goal of this paper is to find sparse and representative spatial priors that can be applied to part-based object localization. Assuming a GMRF prior over part configurations, w...
Linear and affine subspaces are commonly used to describe appearance of objects under different lighting, viewpoint, articulation, and identity. A natural problem arising from the...
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...