High-dimensional data usually incur learning deficiencies and computational difficulties. We present a novel semi-supervised dimensionality reduction technique that embeds high-dim...
Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...
Sudheendra Vijayanarasimhan (University of Texas a...
This paper addresses the problem of automatic temporal
annotation of realistic human actions in video using mini-
mal manual supervision. To this end we consider two asso-
ciate...
Olivier Duchenne, Ivan Laptev, Josef Sivic, Franci...
Object detection in unconstrained images is an important image understanding problem with many potential applications. There has been little success in creating a single algorithm...
We present a novel method for analyzing reflections on arbitrary surfaces. We model reflections using a broader than usual class of imaging models, which include both perspective ...