STRUCTURE AWARE HUMAN POSE ESTIMATION USING ADVERSARIAL LEARNING
Abstract
Pose estimation using Deep Neural Networks (DNNs) has shown outstanding performance in recent years, due to the availability of powerful GPUs and larger training datasets. However, there are still many challenges due to the large variability of human body appearances, lighting conditions, complex background, occlusions and postures. Among all these peculiarities, partial occlusions, and overlapping body poses often result in deviated pose predictions. These circumstances can result in wrong and sometimes unrealistic results. The human mind can predict such poses because of the underlying structural awareness of the geometry, of a human body. In this thesis, we discuss an efficient training technique that helps us to correct structurally implausible poses caused due to partial occlusions. We introduce a pose discriminator which helps us to incorporate priors about the human body's structure, into our model. As shown in the experiments, using this pose discriminator results in improved accuracy.
Related items
Showing items related by title, author, creator and subject.
-
Classification of Factual and Non-Factual Statements Using Adversarially Trained LSTM Networks
Obembe, Daniel; 0000-0001-9890-4208 (2020-06-08)Being able to determine which statements are factual and therefore likely candidates for further verification is a key value-add in any automated fact-checking system. For this task, it has been shown that LSTMs outperform ... -
GAN-Based Domain Translation for Hand Pose Estimation and Face Reconstruction
Farahanipad, Farnaz (2022-08-05)Deep learning solutions for hand pose estimation are now very reliant on comprehensive datasets covering diverse camera perspectives, lighting conditions, shapes, and pose variations. Since, acquiring such datasets is a ... -
ROBUST NOISE-BASED ATTACKS AGAINST AUDIO EVENT DETECTION SYSTEMS
Silva Dos Santos, Rodrigo Augusto; 0000-0003-0277-6315 (2022-04-14)The massive advances on the field of deep neural networks in the 2000 and 2010 decades led to an overwhelming adoption of these algorithms on all sorts of domains and applications. Under this widespread adoption scenario, ...