The availability of graph data with node attributes that can be either discrete or real-valued is
constantly increasing. While existing Kernel methods are effective techniques for dealing …

Human activity recognition is a fundamental problem in computer vision with many
applications such as video retrieval, automatic visual surveillance and human computer …

We present an approach for human activity recognition based on trajectory grou**. Our
representation allows to perform partial matching between videos obtaining a robust …

This paper addresses the problem of action recognition with improved dense trajectories
(IDT). Recently, IDT achieved a significant performance in action recognition with realistic …

[eng] Action recognition is a very challenging and important problem in computer vision.
Researchers working on this field aspire to provide computers with the ability to visually …

Recognising human actions from video sequences is one of the most important topics in
computer vision and has been extensively researched during the last decades; however, it is …

In this thesis the problem of automatic human action recognition and localization in videos is
studied. In this problem, our goal is to recognize the category of the human action that is …

Die automatische Interpretation menschlicher Bewegungsabläufe auf Basis von Videos ist
ein wichtiger Bestandteil vieler Anwendungen im Bereich des Maschinellen Sehens, wie …

Detecting actions in videos is still a demanding task due to large intra-class variation caused
by varying pose, motion and scales. Conventional approaches use a Bag-of-Words model in …