Understanding Images

  • Full Conference Pass (FC) Full Conference Pass (FC)
  • Full Conference One-Day Pass (1D) Full Conference One-Day Pass (1D)

Understanding Images
Date/Time: Thursday, December 6th, 9:00am - 9:25am
Venue: G402 (4F, Glass Building)


Summary: We present Gourmet Photograph Dataset, the first large-scale dataset for food photo aesthetics. We verify its effectiveness via extensive experiments with state-of-the-art visual machine learning algorithms and unseen food photos.

Speaker(s):

Kekai Sheng, NLPR, Institute of Automation, Chinese Academy of Sciences; University of Chinese Academy of Sciences, China
Kekai Sheng is currently working toward the Ph.D degree in National Laboratory of Pattern Recognition (NLPR) at Institute of Automation, Chinese Academy of Sciences. He received his B.Sc. degree in telecommunication engineering from University of Science and Technology, Beijing, China in 2014. His main research interests include machine learning, computer vision and multi-media.

Weiming Dong, NLPR, Institute of Automation, Chinese Academy of Sciences, China
Weiming Dong is a professor in the Sino-European Lab in Computer Science, Automation and Applied Mathematics (LIAMA) and National Laboratory of Pattern Recognition (NLPR) at Institute of Automation, Chinese Academy of Sciences. He received his BSc and MSc degrees in Computer Science in 2001 and 2004, both from Tsinghua University, China. He received his PhD in Computer Science from the University of Lorraine, France, in 2007. His research interests include image synthesis and image recognition. Weiming Dong is a member of the ACM and IEEE.

Haibin Huang, Megvii/Face++ Research, United States of America
Haibin Huang is currently a research scientist at Megvii Research US. He obtained his Ph.D. degree in Computer Science from the University of Massachusetts Amherst this September. Before that, he received his BSc and MSc degrees in Mathematics in 2009 and 2011 respectively from Zhejiang University His research mainly focuses on three-dimensional shape analysis, modeling and synthesis, and in particular machine learning techniques for geometry processing.

Chongyang Ma, Snap Inc., United States of America
Chongyang Ma is currently a Senior Research Scientist at Snap Research. Previously he was a Senior Research Engineer at Activision Central Tech working on facial performance capture for game production. Prior to that, he was a postdoc researcher at UBC and USC working with Prof. Alla Sheffer and Prof. Hao Li respectively. He obtained his Ph.D. in Computer Science from Institute for Advanced Study of Tsinghua University in 2012, under the supervision of Dr. Baining Guo and Dr. Li-Yi Wei. He received his B.S. in Mathematics and Physics from Fundamental Science Class of Tsinghua University in 2007.

Bao-Gang Hu, NLPR, Institute of Automation, Chinese Academy of Sciences, China
Bao-Gang Hu received his M.Sc. degree from University of Science and Technology, Beijing, China, in 1983, and his Ph.D. degree from MsMaster University, Canada, in 1993, all in mechanical engineering. From 1994 to 1997, he was a research engineer and senior research at CCORE, Memorial University of Newfoundland, Canada. Currently, he is a professor with National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, China. From 2000 to 2005, he was the Chinese director of LIAMA. His research interests include pattern recognition and plant growth modeling. He is a senior member of the IEEE.

Understanding Images
Date/Time: Thursday, December 6th, 9:25am - 9:50am
Venue: G402 (4F, Glass Building)


Summary: We present a novel architecture of GAN. The new architecture with a novel loss function improves the convergence problem and basically solves the mode collapse problem of the GAN.

Speaker(s):

Zhaoyu Zhang, University of Science and Technology of China, China
Zhaoyu Zhang received the B.S. degree from University of Science and Technology of China, China, in 2017. He is currently a three year master student in department of automation at University of Science and Technology of China. His research interests include machine learning, computer vision and computer graphics.

Mengyan Li, University of Science and Technology of China, China
Mengyan Li received the B.S. degree from Hefei University of technology, China, in 2017. He is currently a three year master student in department of automation at University of Science and Technology of China. His research interests include computer vision, machine learning and pattern recognition.

Jun Yu, University of Science and Technology of China, China
Jun Yu is an associate professor of University of Science and Technology of China. He is a member of the technical committee - Biological Information and Artificial Life, Chinese Association for Artificial Intelligence, and a member of the IEEE Signal Processing Society. His research interests include human computer interaction and intelligent robot. He has published more than 100 papers, and won the Best Paper Finalist at ICME 2017. E-mail: harryjun@ustc.edu.cn.

Understanding Images
Date/Time: Thursday, December 6th, 9:50am - 10:15am
Venue: G402 (4F, Glass Building)


Summary: We propose a complete system for segmenting and removing chosen objects in videos, taking as only input hand-drawn approximate outlines of these objects in at least one frame.

Speaker(s):

Thuc Trinh Le, LTCI, Telecom ParisTech; Paris-Saclay University, France
Thuc Trinh Le is a Ph.D. candidate in Computer Science and Applied Mathematics at the LTCI Lab of Telecom ParisTech, Paris-Saclay University, France. His research is devoted to the development of machine learning techniques to address some advanced problems in video editing, video segmentation, and video reconstruction.

Andrés Almansa, MAP5, CNRS & Université Paris Descartes, France
Andrés Almansa is a CNRS Research Director at Université Paris Descartes (France) since 2016. He received his MSc and Ph.D. degrees from ENS Cachan (1999, 2002), his MSc and Engineering degrees from Universidad de la República (1995, 1998). He has been previously working with Telecom ParisTech, ENS Cachan (France), Universitat Pompeu Fabra (Spain) and Universidad de la República (Uruguay). His current research interests include image restoration and analysis, subpixel stereovision and applications to earth observation, high quality digital photography and film editing and restoration.

Yann Gousseau, LTCI, Telecom ParisTech; Paris-Saclay University, France
Yann Gousseau received the engineering degree from the École Centrale de Paris, France, in 1995, and the Ph.D. degree in applied mathematics from the University of Paris-Dauphine in 2000. He is currently a professor at Telecom ParisTech. His research interests include the mathematical modeling of natural images and textures, stochastic geometry, computational photography, computer vision, image, and video processing.

Simon Masnou, Claude Bernard Lyon 1 University; Institut Camille Jordan, CNRS UMR 5208, France
Simon Masnou is a Professor in Mathematics at Claude-Bernard Lyon 1 University (France) and Head of Camille Jordan Institute. His research interests include image processing, shape optimization, calculus of variations, and geometric measure theory.

Understanding Images
Date/Time: Thursday, December 6th, 10:15am - 10:40am
Venue: G402 (4F, Glass Building)


Summary: We propose a systematic restoration process for high-resolution deteriorated mural textures, and show the potential for learning different image domain transfer with GAN.

Speaker(s):

Han-Lei Wang, National Taiwan University, Taiwan
I am graduated from National Taiwan University, and my subject is Computer Science and Information Engineering. I'm interested in Machine Learning and Software Engineering. Currently I focus on researches of object detection and tracking through Machine Learning. I also experience in HCI and VR/AR. Most important, I enjoy facing different challenges in fields which can make the world better.

Ping-Hsuan Han, National Taiwan University, Taiwan
Ping-Hsuan Han is a PhD candidate at the Graduate Institute of Networking and Multimedia at National Taiwan University. He is currently a lecturer in the Department of Interaction Design at the National Taipei University of Technology. He received his M.S. from Master Program in Toy and Game Design, and B.S. from Department of Digital Technology Design all at National Taipei University of Education. His current research interests include Human Computer Interaction (HCI), Virtual Reality (VR), Mixed Reality (MR), and Haptic Technology, and he also focuses on Creativity in Engineering Education.

Yu-Mu Chen, National Taiwan University, Taiwan
Currently studying as a senior in Computer Science and Information Engineering department in National Taiwan University, I have developed a keen interest in virtual / augmented reality. However, I also enjoy studying subjects in various fields such as machine learning and IT security. I find a liking in facing different challenges and learning new things from them, and I always do my best to be prepared for anything that is to come.

Kuan-Wen Chen, National Chiao Tung University, Taiwan
Kuan-Wen Chen received the B.S. degree in computer and information science from National Chiao Tung University, Hsinchu, Taiwan, in 2004, and the Ph.D. degree from the Department of Computer Science and Information Engineering at National Taiwan University, Taipei, Taiwan, in 2011. He is an assistant professor in Department of Computer Science, National Chiao Tung University and director of CoVis Lab from Feb 2016. His current research interests include computer vision, pattern recognition, visual surveillance, multimedia, and computer-human interaction.

XINYI LIN, National Taiwan University, Taiwan
I am a graduate student of Networking and Multimedia Department at National Taiwan University, as a member of imLab. I am interested in Deep Learning and Computer Vision. More specifically, my researches focus on video understanding and object detection. I also have experience in data analysis through Machine Learning. Recently I’ve been working on web development as a hobby. In a sense, I am a believer in Python.

Ming-Sui Lee, National Taiwan University, Taiwan
Ming-Sui Lee received her B.Sc. in Mathematical Sciences from the National Cheng Chi University. She received an M.Sc. in Electrical Engineering from University of California-Los Angeles, and a Ph.D. in Electrical Engineering from University of Southern California. She is currently the Assistant Professor at National Taiwan University. Her current research interests include multimedia signal processing with emphasis on digital image/video processing, techniques and applications.

Yi-Ping Hung, National Taiwan University, Tainan National University of the Arts, Taiwan
Yi-Ping Hung received his B.Sc. in Electrical Engineering from the National Taiwan University. He received an M.Sc. from the Division of Engineering and Division of Applied Mathematics, and a Ph.D. from the Division of Engineering, all at Brown University. He is currently the Dean of Research and Development and professor at the Graduate Institute of Animation and Film Art at Tainan National University of the Arts, and professor at the Graduate Institute of Networking and Multimedia at National Taiwan University. His current research interests include computer vision, pattern recognition, image processing, virtual reality and human-computer interface.

 

Back

/en/attendees/production-gallery /en/attendees/birds-of-a-feather