no code implementations • 6 Jan 2024 • Haritha Thilakarathne, Aiden Nibali, Zhen He, Stuart Morgan
Group activity recognition in video is a complex task due to the need for a model to recognise the actions of all individuals in the video and their complex interactions.
no code implementations • 9 Aug 2021 • Haritha Thilakarathne, Aiden Nibali, Zhen He, Stuart Morgan
We introduce a novel deep learning based group activity recognition approach called the Pose Only Group Activity Recognition System (POGARS), designed to use only tracked poses of people to predict the performed group activity.
Ranked #6 on Group Activity Recognition on Volleyball
1 code implementation • 5 Jun 2018 • Aiden Nibali, Zhen He, Stuart Morgan, Luke Prendergast
Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem.
Ranked #46 on 3D Human Pose Estimation on MPI-INF-3DHP
2 code implementations • 23 Jan 2018 • Aiden Nibali, Zhen He, Stuart Morgan, Luke Prendergast
We study deep learning approaches to inferring numerical coordinates for points of interest in an input image.
Ranked #29 on Pose Estimation on MPII Human Pose
no code implementations • 28 May 2017 • Brandon Victor, Zhen He, Stuart Morgan, Dino Miniutti
Most research has been focused on action recognition and using it to classify many clips in continuous video for action localisation.
no code implementations • 25 May 2017 • Aiden Nibali, Zhen He, Stuart Morgan, Daniel Greenwood
Due to recent advances in technology, the recording and analysis of video data has become an increasingly common component of athlete training programmes.
no code implementations • CVPR 2013 • Patrick Lucey, Alina Bialkowski, Peter Carr, Stuart Morgan, Iain Matthews, Yaser Sheikh
In this paper, we describe a method to represent and discover adversarial group behavior in a continuous domain.