We present an unsupervised representation learning approach that compactly encodes the
motion dependencies in videos. Given a pair of images from a video clip, our framework …

Emerging many-core platforms are very difficult to program in a performance portable
manner whilst achieving high efficiency on a diverse range of architectures. We present …

In recent years, human action recognition systems have been increasingly developed to
support a wide range of application areas, such as surveillance, behaviour analysis …

Automatic interpretation of human actions gained strong interest among researchers in
patter recognition and computer vision because of its wide range of applications, such as in …

In this paper, we propose a new local spatio-temporal descriptor for videos and we propose
a new approach for action recognition in videos based on the introduced descriptor. The …

The Dense Trajectories concept is one of the most successful approaches in action
recognition, suitable for scenarios involving a significant amount of motion. However, due to …

Action recognition using dense trajectories is a popular concept. However, many spatio-
temporal characteristics of the trajectories are lost in the final video representation when …

In this paper, we propose to improve the traditional use of RNNs by employing a many to
many model for video classification. We analyze the importance of modeling spatial layout …

In this paper, we study how different skeleton extraction methods affect the performance of
action recognition. As shown in previous work skeleton information can be exploited for …

This paper presents a practical approach and tool (DART) for functional black-box
regression testing of complex legacy database applications. Such applications are important …