Action recognition on large categories of unconstrained videos taken from the web is a very
challenging problem compared to datasets like KTH (6 actions), IXMAS (13 actions), and …

Our day-to-day life has always been influenced by what people think. Ideas and opinions of
others have always affected our own opinions. The explosion of Web 2.0 has led to …

Combining multiple low-level visual features is a proven and effective strategy for a range of
computer vision tasks. However, limited attention has been paid to combining such features …

This paper presents a method for movie genre categorization of movie trailers, based on
scene categorization. We view our approach as a step forward from using only low-level …

Recognizing actions in videos is rapidly becoming a topic of much research. To facilitate the
development of methods for action recognition, several video collections, along with …

An important part of education is student's learning. Good quality education is based mainly
on how well student attain the knowledge. One way to achieve that is to simplify the content …

Automatic event detection in a large collection of unconstrained videos is a challenging and
important task. The key issue is to describe long complex video with high level semantic …

(57) ABSTRACT A video is segmented to produce Volumetric video regions. Descriptors are
created for the video regions. A region graph is created for the video, where the region …

Human activity recognition is a challenging high-level vision task, for which multiple factors,
such as subject, object, and their diverse interactions, have to be considered and modeled …

Generating coherent synopsis for surveillance video stream remains a formidable challenge
due to the ambiguity and uncertainty inherent to visual observations. In contrast to existing …