Toward Intuitive Imagery: Machine Learning and Computer Vision for User Friendly Imagery Manipulation and Exploration
Bio:Kwang In Kim is an associate professor at the School of Electrical and Computer Engineering, UNIST. After he received a PhD from Kyungpook National University in 2000, he was a postdoctoral researcher at KAIST, Korea, and at the Max Planck Institute for Biological Cybernetics, Saarland University, and the Max Planck Institute for Informatics, all in Germany from 2000 to 2013. More recently, he was a senior lecturer at the department of Computer Science, University of Bath and a lecturer at the School of Computing and Communications, Lancaster University. Kwang In is interested in advancing the understanding of how people can explore, make sense of, and interact with visual data. He contributes to this endeavor by exploiting and developing new techniques in machine learning, computer vision, computer graphics, and human-computer interaction.
Abstract :Toward Intuitive Imagery: Machine Learning and Computer Vision for User Friendly Imagery Manipulation and Exploration With the ubiquity of cameras, it is easy to form collections of photographs and video. However, unlike professionally captured photographs and video, the imageries that are casually captured by regular users are often low quality. Important questions in this regard are how to help novice users 1) acquire high-quality images and videos and 2) explore large collections of imagery once they are formed. In this talk, we will discuss our recent effort to address these questions, including two specific examples of image and video editing, and video database exploration.