Improving Pose Estimation through Contextual Activity Fusion

11/03/2021
by   David Poulton, et al.
0

This research presents the idea of activity fusion into existing Pose Estimation architectures to enhance their predictive ability. This is motivated by the rise in higher level concepts found in modern machine learning architectures, and the belief that activity context is a useful piece of information for the problem of pose estimation. To analyse this concept we take an existing deep learning architecture and augment it with an additional 1x1 convolution to fuse activity information into the model. We perform evaluation and comparison on a common pose estimation dataset, and show a performance improvement over our baseline model, especially in uncommon poses and on typically difficult joints. Additionally, we perform an ablative analysis to indicate that the performance improvement does in fact draw from the activity information.

READ FULL TEXT

page 2

page 5

page 6

research
02/29/2016

Evaluation of Deep Learning based Pose Estimation for Sign Language Recognition

Human body pose estimation and hand detection are two important tasks fo...
research
02/02/2018

Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming

In this paper we consider the problem of human pose estimation in real-w...
research
11/17/2016

Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation

Most recent approaches to monocular 3D human pose estimation rely on Dee...
research
09/24/2019

Pretraining boosts out-of-domain robustness for pose estimation

Deep neural networks are highly effective tools for human and animal pos...
research
05/26/2023

Generalizable Pose Estimation Using Implicit Scene Representations

6-DoF pose estimation is an essential component of robotic manipulation ...
research
06/22/2016

Model-based Deep Hand Pose Estimation

Previous learning based hand pose estimation methods does not fully expl...
research
04/20/2021

Table Tennis Stroke Recognition Using Two-Dimensional Human Pose Estimation

We introduce a novel method for collecting table tennis video data and p...

Please sign up or login with your details

Forgot password? Click here to reset