Recognizing human activities from video sequences or still images is a challenging task due
to problems, such as background clutter, partial occlusion, changes in scale, viewpoint …

Abstract Human Motion Analysis (HMA) is currently one of the most popularly active
research domains as such significant research interests are motivated by a number of real …

Multimodal fusion has become one of the hottest topics in affective computing and other
research areas. Yet, this topic is less studied in surveillance systems. In general, it focused …

Capturing the'mutual gaze'of people is essential for understanding and interpreting the
social interactions between them. To this end, this paper addresses the problem of detecting …

Gait recognition systems typically rely solely on silhouettes for extracting gait signatures.
Nevertheless, these approaches struggle with changes in body shape and dynamic …

We address the problem of detecting and recognizing online the occurrence of human
interactions as seen by a network of multiple cameras. We represent interactions by forming …

The goal of this paper is to evaluate how the fusion of multimodal features (ie, audio, RGB
and depth) can help in the challenging task of people identification based on their gait (ie …

In this work, we look into the problem of recognizing two-person interactions in videos. Our
method integrates multiple visual features in a weakly supervised manner by utilizing an …

Multimodal fusion has become a hot topic in computer vision. For surveillance applications
detecting unwanted behavior such as aggression is a complex task. The definition of …

In this paper, a human behavior recognition method using multimodal features is presented.
We focus on modeling individual and social behaviors of a subject (eg, friendly/aggressive …