Human activity recognition (HAR) is one of the most important and challenging problems in
the computer vision. It has critical application in wide variety of tasks including gaming …

Human activity recognition systems are developed as part of a framework to enable
continuous monitoring of human behaviours in the area of ambient assisted living, sports …

Temporally locating and classifying action segments in long untrimmed videos is of
particular interest to many applications like surveillance and robotics. While traditional …

We focus on multi-modal fusion for egocentric action recognition, and propose a novel
architecture for multi-modal temporal-binding, ie the combination of modalities within a …

The ability to identify and temporally segment fine-grained human actions throughout a
video is crucial for robotics, surveillance, education, and beyond. Typical approaches …

With the success of deep learning in classifying short trimmed videos, more attention has
been focused on temporally segmenting and classifying activities in long untrimmed videos …

The dominant paradigm for video-based action segmentation is composed of two steps: first,
compute low-level features for each frame using Dense Trajectories or a Convolutional …

In this work we study the use of 3D hand poses to recognize first-person dynamic hand
actions interacting with 3D objects. Towards this goal, we collected RGB-D video sequences …

We address the task of jointly determining what a person is doing and where they are
looking based on the analysis of video captured by a headworn camera. We propose a …

We present a comprehensive framework for egocentric interaction recognition using
markerless 3D annotations of two hands manipulating objects. To this end, we propose a …