Cross-Domain Sketch Analysis Using Deep Learning Methods
Newcastle upon Tyne, United Kingdom
in conjunction with BMVC 2018
Cross-Domain Sketch Analysis Using Deep Learning Methods
Newcastle upon Tyne, United Kingdom
in conjunction with BMVC 2018

About

With the development of the touch-screen technology, sketching has become a much easier way for humans to interact with computer systems such as tablets and smart phones. Since sketch is intuitive and convenient for users, in the computer vision community it is widely used in cross-domain tasks such as sketch-based image retrieval and sketch-based 3D shape retrieval. Advances in deep learning via convolutional neural networks (CNNs) has resulted in great gains in various computer vision tasks. Due to the discriminatory nature of features of deep neural networks, researchers also employ deep learning techniques to reduce the domain discrepancy in cross-domain sketch analysis. The aim of this workshop is to gather researchers to present their work and highlight the latest developments on sketch analysis. It is expected that the community will engage in dedicated discussions on new sketch-based applications and domain adaptation with deep learning techniques.

About

With the development of the touch-screen technology, sketching has become a much easier way for humans to interact with computer systems such as tablets and smart phones. Since sketch is intuitive and convenient for users, in the computer vision community it is widely used in cross-domain tasks such as sketch-based image retrieval and sketch-based 3D shape retrieval. Advances in deep learning via convolutional neural networks (CNNs) has resulted in great gains in various computer vision tasks. Due to the discriminatory nature of features of deep neural networks, researchers also employ deep learning techniques to reduce the domain discrepancy in cross-domain sketch analysis. The aim of this workshop is to gather researchers to present their work and highlight the latest developments on sketch analysis. It is expected that the community will engage in dedicated discussions on new sketch-based applications and domain adaptation with deep learning techniques.

Topics

􀀀 Sketch Recognition/Classification
􀀀 Hashing for sketch retrieval
􀀀 Sketch representation learning
􀀀 Cross-domain/cross-modality sketch-based retrieval, e.g., sketch-based image/3D shape/text retrieval.
􀀀 Adversarial learning for sketch representation
􀀀 Facial sketch applications
􀀀 Deep learning for sketch generation
􀀀 Other sketch-related analysis
􀀀 Other cross-domain applications

Topics

􀀀 Sketch Recognition/Classification
􀀀 Hashing for sketch retrieval
􀀀 Sketch representation learning
􀀀 Cross-domain/cross-modality sketch-based retrieval, e.g., sketch-based image/3D shape/text retrieval.
􀀀 Adversarial learning for sketch representation
􀀀 Facial sketch applications
􀀀 Deep learning for sketch generation
􀀀 Other sketch-related analysis
􀀀 Other cross-domain applications

Important Dates

Paper Submission Deadline: 4, July, 2018
Notification of Acceptance: 15, August, 2018
Camera-Ready Due: 22, August, 2018
Workshop Event: 6, September, 2018

Important Dates

Paper Submission Deadline: 4, July, 2018
Notification of Acceptance: 15, August, 2018
Camera-Ready Due: 22, August, 2018
Workshop Event: 6, September, 2018

Speakers

Prof. Yi-Zhe Song

Prof. Yi-Zhe Song received the Ph.D. degree in computer vision and graphics from the University of Bath in 2008. He is currently a Senior Lecturer (Associate Professor), and the Founding Director of the SketchX Research Laboratory, School of Electronic Engineering and Computer Science, Queen Mary University of London. His research interests lay solely on understanding human sketches and enabling novel applications of sketches. He has authored over 50 papers in major international journals and conferences.

Prof. Wangmeng Zuo

Prof. Wangmeng Zuo received the Ph.D. degree in computer application technology from the Harbin Institute of Technology, Harbin, China, in 2007. He was a Research Assistant with the Department of Computing, Hong Kong Polytechnic University, Hong Kong, in 2004, from 2005 to 2006, and from 2007 to 2008. From 2009 to 2010, he was a Visiting Professor with Microsoft Research Asia, Beijing, China. He has authored over 40 papers in top-tier academic journals and conferences, His current research interests include discriminative learning, image modeling, low-level vision, and biometrics. Prof. Zuo is an Associate Editor of the IET Biometrics and Scientific World Journal, and a Guest Editor of Neurocomputing Special Issue on Smart Computing for Large Scale Visual Data Sensing and Processing.

Speakers

Prof. Yi-Zhe Song

Prof. Yi-Zhe Song received the Ph.D. degree in computer vision and graphics from the University of Bath in 2008. He is currently a Senior Lecturer (Associate Professor), and the Founding Director of the SketchX Research Laboratory, School of Electronic Engineering and Computer Science, Queen Mary University of London. His research interests lay solely on understanding human sketches and enabling novel applications of sketches. He has authored over 50 papers in major international journals and conferences.

Prof. Wangmeng Zuo

Prof. Wangmeng Zuo received the Ph.D. degree in computer application technology from the Harbin Institute of Technology, Harbin, China, in 2007. He was a Research Assistant with the Department of Computing, Hong Kong Polytechnic University, Hong Kong, in 2004, from 2005 to 2006, and from 2007 to 2008. From 2009 to 2010, he was a Visiting Professor with Microsoft Research Asia, Beijing, China. He has authored over 40 papers in top-tier academic journals and conferences, His current research interests include discriminative learning, image modeling, low-level vision, and biometrics. Prof. Zuo is an Associate Editor of the IET Biometrics and Scientific World Journal, and a Guest Editor of Neurocomputing Special Issue on Smart Computing for Large Scale Visual Data Sensing and Processing.

Committee Chairs

Prof. Jin Xie

Jin Xie received his Ph.D. degree from the Department of Computing, The Hong Kong Polytechnic University. He is a professor at Nanjing University of Science and Technology (NJUST), China. Prior to joining NJUST, he was a research scientist at New York University Abu Dhabi. His research interests include image forensics, computer vision and machine learning. Currently he is focusing on 3D computer vision with convex optimization and deep learning methods. He has published papers in many top conferences and journals, including CVPR, ECCV, AAAI, ACM MM, IEEE TPAMI and TIP. He has served as a PC member for CVPR, ICCV, ACM MM, ICPR and ACPR, a journal reviewer for IEEE TPAMI, TIP, TNNLS, TMM, TCYB, TCSVT, PR and PRL. He was a special issue chair for ACPR 2017 and a guest editor for Pattern Recognition.

Prof. Fumin Shen

Fumin Shen is a professor in School of Computer Science and Engineering, University of Electronic Science and Technology of China. He received his PhD degree from School of Computer Science, Nanjing University of Science and Technology, China in 2014. From 2010 to 2012, He visited NICTA, Australian National University and ACVT, University of Adelaide, Australia, as a joint PhD student supervised by Prof. Chunhua Shen. He received my bachelor degree in Applied Mathematics from Shandong University in 2007. His research focuses on computer vision and machine learning, especially learning based hashing algorithms and their applications in visual retrieval and recognition problems. He has published 80+ papers in CVPR, ICCV, MM, SIGIR, TPAMI, TIP, TMM, TCSVT, etc. He has served as a regular PC member for ICCV, ACM MM, AAAI, ICMR, ICPR, MMM, journal reviewer for IEEE TIP, TNNLS, TKDE, TMM, TCYB, TCSVT, guest editor for Neurocomputing, PRL, NPL, special issue chair for ACPR'17 and special session organizer for MMM'16, ICMICS'16. He is the recipient of the Best Paper Award Honorable Mention at ACM SIGIR 2016 & ACM SIGIR 2017 and the World's FIRST 10K Best Paper Award - Platinum Award at IEEE ICME 2017.

Dr. Fan Zhu

Fan Zhu received his MSc degree in Electrical Engineering with distinction, Ph.D degree in computer vision from the University of Sheffield, UK, in 2011 and 2015 respectively. Currently, he is a Lead Scientist with Inception Institute of Artificial Intelligence, UAE. Previously, he was a Post-doctoral Research Fellow with the Electrical and Computer Engineering department of New York University Abu Dhabi from 2014 to 2017, and a Data Scientist with Pegasus LLC from 2017 to 2018. He was a recipient of the National Scholarship for Outstanding Self-funded Oversea Students of China in 2014. He has authored/co-authored 30+ papers in top conferences and journals, including CVPR, ECCV, IJCV, PAMI, AAAI and ACMMM. He is a regular reviewer of CVPR, ICCV, TIP, TNN, T-Cybernetics and other conferences and journals. He was on the program committee board of International Workshop of Deep Learning for Pattern Recognition, 2016. His current research interests include deep feature learning for 2D images and 3D shapes, scene understanding, video analytics and adversarial learning.

Dr. Li Liu

Li Liu received the PhD degree from Department of Electronic and Electrical Engineering, University of Sheffield, Sheffield, U.K in 2014. Currently, he is a Lead Scientist with Inception Institute of Artificial Intelligence, UAE. He has over 9-year experience in Computer Vision, Machine Learning and Pattern Recognition, and authored/co-authored over 60 top-ranked journals and conferences in these areas, which received over 1,000 citations (Google Scholar), such as IEEE TPAMI, TIP, TNNLS, IJCV, ICCV, CVPR, ECCV, IJCAI, AAAI, ACM SIGIR and ACM MM, and holds several patents. In addition, he has 3- year industrial project experience on deep learning-based visual detection/recognition/retrieval for public security surveillance and big data prediction. Currently, his research interests mainly focus on large-scale data retrieval/recognition and deep-learning based visual analysis. He has served as a PC member for ICCV, CVPR, ACM MM, ICPR, BMVC, journal reviewer for IEEE TPAMI, TIP, TNNLS, TKDE, TMM, TCYB, TCSVT, and lead guest editor for PRL and Advances in Multimedia. He is the recipient of the Best Paper Award Honorable Mention at ACM SIGIR 2017 and the Best Poster Award Honorable Mention at BMVC 2017.

Organizors

Prof. Jin Xie

Jin Xie received his Ph.D. degree from the Department of Computing, The Hong Kong Polytechnic University. He is a professor at Nanjing University of Science and Technology (NJUST), China. Prior to joining NJUST, he was a research scientist at New York University Abu Dhabi. His research interests include image forensics, computer vision and machine learning. Currently he is focusing on 3D computer vision with convex optimization and deep learning methods. He has published papers in many top conferences and journals, including CVPR, ECCV, AAAI, ACM MM, IEEE TPAMI and TIP. He has served as a PC member for CVPR, ICCV, ACM MM, ICPR and ACPR, a journal reviewer for IEEE TPAMI, TIP, TNNLS, TMM, TCYB, TCSVT, PR and PRL. He was a special issue chair for ACPR 2017 and a guest editor for Pattern Recognition.

Prof. Fumin Shen

Fumin Shen is a professor in School of Computer Science and Engineering, University of Electronic Science and Technology of China. He received his PhD degree from School of Computer Science, Nanjing University of Science and Technology, China in 2014. From 2010 to 2012, He visited NICTA, Australian National University and ACVT, University of Adelaide, Australia, as a joint PhD student supervised by Prof. Chunhua Shen. He received my bachelor degree in Applied Mathematics from Shandong University in 2007. His research focuses on computer vision and machine learning, especially learning based hashing algorithms and their applications in visual retrieval and recognition problems. He has published 80+ papers in CVPR, ICCV, MM, SIGIR, TPAMI, TIP, TMM, TCSVT, etc. He has served as a regular PC member for ICCV, ACM MM, AAAI, ICMR, ICPR, MMM, journal reviewer for IEEE TIP, TNNLS, TKDE, TMM, TCYB, TCSVT, guest editor for Neurocomputing, PRL, NPL, special issue chair for ACPR'17 and special session organizer for MMM'16, ICMICS'16. He is the recipient of the Best Paper Award Honorable Mention at ACM SIGIR 2016 & ACM SIGIR 2017 and the World's FIRST 10K Best Paper Award - Platinum Award at IEEE ICME 2017.

Dr. Fan Zhu

Fan Zhu received his MSc degree in Electrical Engineering with distinction, Ph.D degree in computer vision from the University of Sheffield, UK, in 2011 and 2015 respectively. Currently, he is a Lead Scientist with Inception Institute of Artificial Intelligence, UAE. Previously, he was a Post-doctoral Research Fellow with the Electrical and Computer Engineering department of New York University Abu Dhabi from 2014 to 2017, and a Data Scientist with Pegasus LLC from 2017 to 2018. He was a recipient of the National Scholarship for Outstanding Self-funded Oversea Students of China in 2014. He has authored/co-authored 30+ papers in top conferences and journals, including CVPR, ECCV, IJCV, PAMI, AAAI and ACMMM. He is a regular reviewer of CVPR, ICCV, TIP, TNN, T-Cybernetics and other conferences and journals. He was on the program committee board of International Workshop of Deep Learning for Pattern Recognition, 2016. His current research interests include deep feature learning for 2D images and 3D shapes, scene understanding, video analytics and adversarial learning.

Dr. Li Liu

Li Liu received the PhD degree from Department of Electronic and Electrical Engineering, University of Sheffield, Sheffield, U.K in 2014. Currently, he is a Lead Scientist with Inception Institute of Artificial Intelligence, UAE. He has over 9-year experience in Computer Vision, Machine Learning and Pattern Recognition, and authored/co-authored over 60 top-ranked journals and conferences in these areas, which received over 1,000 citations (Google Scholar), such as IEEE TPAMI, TIP, TNNLS, IJCV, ICCV, CVPR, ECCV, IJCAI, AAAI, ACM SIGIR and ACM MM, and holds several patents. In addition, he has 3- year industrial project experience on deep learning-based visual detection/recognition/retrieval for public security surveillance and big data prediction. Currently, his research interests mainly focus on large-scale data retrieval/recognition and deep-learning based visual analysis. He has served as a PC member for ICCV, CVPR, ACM MM, ICPR, BMVC, journal reviewer for IEEE TPAMI, TIP, TNNLS, TKDE, TMM, TCYB, TCSVT, and lead guest editor for PRL and Advances in Multimedia. He is the recipient of the Best Paper Award Honorable Mention at ACM SIGIR 2017 and the Best Poster Award Honorable Mention at BMVC 2017.

Submission
All submissions will be handled electronically via the workshop’s CMT Website.
Click the following link to go to the submission site: https://cmt3.research.microsoft.com/CDSA2018
Example submission paper with detailed instructions: bmvc_cdsa_review.pdf
Papers should describe original and unpublished work about the related topics. Each paper will receive double blind reviews, moderated by the workshop chairs. Authors should take into account the following:
- All papers must be written and presented in English.
- All papers must be submitted in PDF format. The workshop paper format guidelines are the same as the Main Conference papers.
- The maximum paper length is 14 pages (excluding references). Note that shorter submissions are also welcome.
Submission
All submissions will be handled electronically via the workshop’s CMT Website.
Click the following link to go to the submission site: https://cmt3.research.microsoft.com/CDSA2018
Example submission paper with detailed instructions: bmvc_cdsa_review.pdf
Papers should describe original and unpublished work about the related topics. Each paper will receive double blind reviews, moderated by the workshop chairs. Authors should take into account the following:
- All papers must be written and presented in English.
- All papers must be submitted in PDF format. The workshop paper format guidelines are the same as the Main Conference papers.
- The maximum paper length is 14 pages (excluding references). Note that shorter submissions are also welcome.