Abstract. Even a relatively unstructured captioned image set depicting a variety of objects in cluttered scenes contains strong correlations between caption words and repeated visu...
Local coordinate coding has recently been introduced to learning visual feature dictionary and achieved top level performance for object recognition. However, the computational co...
: In our department we have a long history of developing interfaces for learning, which are framed by constructivist and constructionist theories of learning. Thus we try to create...
This paper addresses the problem of establishing correspondences
between two sets of visual features using
higher-order constraints instead of the unary or pairwise
ones used in...
Francis R. Bach, In-So Kweon, Jean Ponce, Olivier ...
We propose using the proximity distribution of vectorquantized local feature descriptors for object and category recognition. To this end, we introduce a novel "proximity dis...