Profile

Jae Myung Kim is a first-year Ph.D. researcher as a member of the European Laboratory for Learning and Intelligent Systems (ELLIS) program co-supervised by Prof. Zeynep Akata at University of Tübingen and Prof. Cordelia Schmid at INRIA. He received his Master’s degree from Seoul National University in 2020, supervised by Prof. Jungwoo Lee, and Bachelor’s degree from Seoul National University in 2018. During winter 2020, he worked as a research intern at NAVER AI Lab, South Korea, advised by Dr. Sungjoon Oh and Dr. Junsuk Choi. His research interests include explainable AI and uncertainty estimation, with the goal of building trustworthiness for artificial intelligence system.

Publications

• "Large Loss Matters in Weakly Supervised Multi-Label Classification", Youngwook Kim*, Jae Myung Kim*, Zeynep Akata, Jungwoo Lee, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2022
• "Keep CALM and Improve Visual Feature Attribution", Jae Myung Kim, Junsuk Choe, Zeynep Akata, Seong Joon Oh, IEEE International Conference of Computer Vision, ICCV 2021