Visual Recognition Going Beyond Datasets
Visual Recognition Going Beyond Datasets(영어 강의)
Bio: Jonghyun Choi is an assistant professor at GIST. He received a PhD degree from University of Maryland, College Park in 2015 and a BS and MS degrees in electrical engineering and computer science from Seoul National University, Seoul Korea in 2003 and 2008 respectively. He has worked as an intern in various research labs including US Army Research Lab, Adobe Research, Disney Research Pittsburgh and Microsoft Research Redmond. He was a senior researcher at Comcast Applied AI Research and a research scientist at Allen Institute for Artificial Intelligence (AI2). His research interest includes visual category recognition using weakly labeled data, regularized classifier learning and improving the performance by external semantic information.
Abstract: The supervision in curating datasets is sometimes not enough even for the target task and the supervision is expensive and bias prone. I will discuss a few ideas to build recognition models with information going beyond the given datasets.