Taehwan Kim


Postdoctoral Scholar

Department of Computing and Mathematical Sciences

California Institute of Technology
Email: taehwan[at]caltech[.]edu

I am a postdoctoral scholar in the Computing and Mathematical Sciences department at the California Institute of Technology working with Prof. Yisong Yue. I completed my PhD in 2016 at Toyota Technological Institute at Chicago, a philanthropically endowed academic computer science institute located on the University of Chicago campus, and my advisor was Prof. Karen Livescu. I did my master in Computer Science at USC and bachelor in Computer Science & Engineering and Mathematics at POSTECH.

My main research interests span various problems related to the fields of Machine Learning and applications to Computer Vision. Specifically, I am interested in Spatio-Temporal Data Analysis, Optimization, and Deep Learning.



·  CS159 Advanced Topics in Machine Learning: Structured Prediction, Spring 2017, Caltech





·  Taehwan Kim, Jonathan Keane, Weiran Wang, Hao Tang, Jason Riggle, Gregory Shakhnarovich, Diane Brentari and Karen Livescu, Lexicon-Free Fingerspelling Recognition from Video: Data, Models, and Signer Adaptation, (In submission) [pdf]



·  Sarah Taylor, Taehwan Kim, Yisong Yue, James Krahe, Anastasio Garcia Rodriguez, Jessica Hodgins, Moshe Mahler, Iain Matthews, A Deep Learning Approach for Generalized Speech Animation, ACM Conference on Computer Graphics (SIGGRAPH), 2017


·  Taehwan Kim, Weiran Wang, Hao Tang and Karen Livescu, Signer-independent Fingerspelling Recognition with Deep Neural Network Adaptation, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016 (Best Student Paper of Speech and Language Processing) [pdf]


·  Taehwan Kim, Yisong Yue, Sarah Taylor and Iain Matthews, A Decision Tree Framework for Spatiotemporal Sequence Prediction, ACM Conference on Knowledge Discovery and Data Mining (KDD), 2015 [pdf]


·  Taehwan Kim, Greg Shakhnarovich and Karen Livescu, Fingerspelling Recognition with semi-Markov Conditional Random Fields, IEEE International Conference on Computer Vision (ICCV), 2013 [pdf]


·  Taehwan Kim, Karen Livescu and Greg Shakhnarovich, American Sign Language Fingerspelling Recognition With Phonological Feature-based Tandem Models, IEEE Workshop on Spoken Language Technology (SLT), 2012 [pdf]


·  Taehwan Kim, Greg Shakhnarovich and Raquel Urtasun, Sparse Coding for Learning Interpretable Spatio-temporal Primitives, Neural Information Processing Systems (NIPS), 2010 [pdf]


·  Jihie Kim, Erin Shaw, Saul Wyner, Taehwan Kim and Jia Li, Discerning Affect in Student Discussions, Annual Meeting of the Cognitive Science Society (CogSci), 2010


·  Jihie Kim, Jia Li and Taehwan Kim: Identifying student online discussions with unanswered questions, K-CAP, 2009


·  Jihie Kim, Taehwan Kim and Jia Li, Identifying unresolved issues in online students discussions: A multi-phase dialogue classification approach, Proc. of the AI in Education Conference (AIED), 2009