A novel automatic image annotation system is proposed, which integrates two sets of SVMs (Support Vector Machines), namely the MIL-based (Multiple Instance Learning) and global-fe...
We discuss the problem of clustering elements according to the sources that have generated them. For elements that are characterized by independent binary attributes, a closedform...
A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
Building robust low and mid-level image representations, beyond edge primitives, is a long-standing goal in vision. Many existing feature detectors spatially pool edge information...
Matthew Zeiler, Dilip Krishnan, Graham Taylor, Rob...
Unlike simple questions, complex questions cannot be answered by simply extracting named entities. These questions require inferencing and synthesizing information from multiple d...