Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
We propose a novel method for removing irrelevant frames from a video given user-provided frame-level labeling for a very small number of frames. We first hypothesize a number of c...
Abstract. Recently, on-line adaptation of binary classifiers for tracking have been investigated. On-line learning allows for simple classifiers since only the current view of the ...
Shadows are one of the most significant difficulties of the photometric stereo method. When four or more images are available, local surface orientation is overdetermined and the s...
Abstract. We present a comparative study on how to use discriminative learning methods such as classification, regression, and ranking to address deformable shape segmentation. Tra...
Jingdan Zhang, Shaohua Kevin Zhou, Dorin Comaniciu...