Deep learning is one of the most important breakthroughs in the field of artificial intelligence over the last decade. It has achieved great success in speech recognition, natural language processing, computer vision, and multimedia. Many face analysis tasks, including face detection, alignment, reconstruction, and recognition, benefit from the powerful representation learning capability of deep learning techniques. Not only there has been a constantly growing flow of related research papers, but also substantial progress has been achieved in real-world applications such as security, video surveillance, and human-computer interaction.
While substantial progress has been achieved in face analysis with deep learning, many issues still remain and new problems emerge. For instance, the scalability of deep networks to large-scale unconstrained recognition needs be improved. In-the-wild facial attributes recognition with imbalance class distribution is still challenging. The accuracy and efficiency of detecting faces with a wide range of scales in a crowded scene still see a large room for improvement.
This special issue presents a great platform to make a definitive statement about the state of the art by providing a significant collective contribution to this emerging field of study.
International Journal of Computer Vision
Volume 127, Issues 6-7 Pages 533-971 (June 2019)
Deep Learning for Face Analysis
Edited by Chen Change Loy, Xiaoming Liu, Tae-Kyun Kim, Fernando De la Torre, Rama Chellappa
The issue is available electronically on Springer at the following link: https://link.springer.com/journal/11263/127/6
Rama Chellappa, University of Maryland, USA
Xiaoming Liu, Michigan State University, USA
Tae-Kyun Kim, Imperial College London, UK
Fernando De la Torre, Facebook, USA
Chen Change Loy, Nanyang Technological University, Singapore