Deep learning for visual understanding: A review

详细信息    查看全文

• 作者：Yanming Guo^a ; ^c ; ^{y.guo@liacs.leidenuniv.nl" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Yu Liu^a ; ^{y.liu@liacs.leidenuniv.nl" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Ard Oerlemans^b ; ^{a.oerlemans@vdgsecurity.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Songyang Lao^c ; ^{laosongyang@vip.sina.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Song Wu^a ; ^{s.wu@liacs.leidenuniv.nl" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Michael S. Lew^a ; ^{m.s.lew@liacs.leidenuniv.nl" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：Deep learning ; Computer vision ; Developments ; Applications ; Trends ; Challenges
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：26 April 2016
• 年：2016
• 卷：187
• 期：Complete
• 页码：27-48
• 全文大小：2565 K

文摘

Deep learning algorithms are a subset of the machine learning algorithms, which aim at discovering multiple levels of distributed representations. Recently, numerous deep learning algorithms have been proposed to solve traditional artificial intelligence problems. This work aims to review the state-of-the-art in deep learning algorithms in computer vision by highlighting the contributions and challenges from over 210 recent research papers. It first gives an overview of various deep learning approaches and their recent developments, and then briefly describes their applications in diverse vision tasks, such as image classification, object detection, image retrieval, semantic segmentation and human pose estimation. Finally, the paper summarizes the future trends and challenges in designing and training deep neural networks.