153
click to vote
CLOR
2006
15 years 7 months ago
2006
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...
133
click to vote
CLOR
2006
15 years 7 months ago
2006
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the dis...
127
click to vote
CLOR
2006
15 years 7 months ago
2006
The chapter describes visual classification by a hierarchy of semantic fragments. In fragment-based classification, objects within a class are represented by common sub-structures ...
160
click to vote
CLOR
2006
15 years 7 months ago
2006
Abstract. A popular framework for the interpretation of image sequences is the layers or sprite model, see e.g. [1], [2]. Jojic and Frey [3] provide a generative probabilistic mode...
159
click to vote
CLOR
2006
15 years 7 months ago
2006
We describe an approach to object retrieval which searches for and localizes all the occurrences of an object in a video, given a query image of the object. The object is represent...