Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task a...
Over the past decade, multiple-instance learning (MIL)
has been successfully utilized to model the localized
content-based image retrieval (CBIR) problem, in which a
bag corresp...
Wu-Jun Li (Hong Kong University of Science and Tec...
This paper describes a machine learning approach for visual
object detection which is capable of processing images
extremely rapidly and achieving high detection rates. This
wor...
Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the fie...
Automatic analysis of head gestures and facial expressions is a challenging research area and it has significant applications in humancomputer interfaces. In this study, facial la...