Deep learning has achieved great successes in conventional computer vision tasks. In this
paper, we exploit deep learning techniques to address the hyperspectral image …

Unlike the visual object tracking, thermal infrared object tracking can track a target object in
total darkness. Therefore, it has broad applications, such as in rescue and video …

Human action recognition based on 3D data is attracting increasing attention because it
could provide more abundant spatial and temporal information compared with RGB videos …

Robustness and efficiency are the two main goals of existing trackers. Most robust trackers
are implemented with combined features or models accompanied with a high computational …

Common tracking algorithms only use a single feature to describe the target appearance,
which makes the appearance model easily disturbed by noise. Furthermore, the tracking …

Remote photoplethysmography (rPPG) can achieve contactless human vital signs
monitoring, but its signal quality is limited by the remote operation nature. In practical …

Most of the correlation filter based tracking algorithms can achieve good performance and
maintain fast computational speed. However, in some complicated tracking scenes, there is …

Depth sequences are useful for action recognition since they are insensitive to illumination
variation and provide geometric information. Many current action recognition methods are …

In order to improve the interpretation of principal components, many sparse principal
component analysis (PCA) methods have been proposed by in the form of self-contained …

Bug triaging is an important activity in any software development project. It involves
developers working through the set of unassigned bugs, determining for each of the bugs …