In this paper, we present a method for recognizing human activities using information
sensed by an RGB-D camera, namely the Microsoft Kinect. Our approach is based on the …

Abstract Analysis of human behaviour through visual information has been a highly active
research topic in the computer vision community. This was previously achieved via images …

In this work, we propose an approach to the spatiotemporal localisation (detection) and
classification of multiple concurrent actions within temporally untrimmed videos. Our …

Due to advances in information technology (eg, digital video cameras, ubiquitous sensors),
the automatic detection of human behaviors from video is a very recent research topic. In this …

Humans drive in a holistic fashion which entails, in particular, understanding dynamic road
events and their evolution. Injecting these capabilities in autonomous vehicles can thus take …

Understanding human behaviors is a challenging problem in computer vision that has
recently seen important advances. Human behavior understanding combines image and …

In this chapter, we propose a comparison between two techniques for one-shot person re-
identification from soft biometric cues. One is based upon a descriptor composed of features …

In this work, we describe a novel method for creating 3D models of persons freely moving in
front of a consumer depth sensor and we show how they can be used for long-term person …

Recognizing complex human activities usually requires the detection and modeling of
individual visual features and the interactions between them. Current methods only rely on …

This work addresses the problem of human body segmentation from multi-modal visual cues
as a first stage of automatic human behavior analysis. We propose a novel RGB–depth …