I'm a Ph.D. student at KAIST, South Korea. My research is mainly focused on solving computer vision problems using machine learning. Specifically, my research has been focusing on computer vision problems where a prior in data needs to be modeled properly, e.g., unsupervised learning. Here's a brief list of my topics of interest:
- Optical flow estimation: it is a fundamental feature for video recognition. I have been mainly focusing on the lack of datasets with ground-truth optical flow, e.g., unsupervised / semi-supervised learning.
- Un/semi-supervised learning: learning with unlabeled examples is not avoidable in some applcations: unsupervised optical flow estimation, single-sample per person (SSPP) face recognition, etc.
- Video recognition: recognizing video contents by machine learning.
- Face recognition: recognizing identity, age, and other attributes with machine-learning.
Not only on the topics mentioned above, I'm knowledgeable about 3D vision and NLP. I have been implemented my code using Python, C++ with OpenCV, Tensorflow (1 and 2), and Pytorch, while participating in many vision-related projects: face recognition, 3D teleportation, and multi-view line matching.
- Unsupervised Learning of Optical Flow with Deep Feature Similarity European Conference on Computer Vision (ECCV)
- Combined Center Dispersion Loss Function for Deep Facial Expression Recognition Pattern Recognition Letters
- Two-stream Spatiotemporal Feature for Video QA Task https://arxiv.org/abs/1907.05006
- Acoustic Material Estimation with Convolutional Neural Network Korea Robotics Society Annual Conference (KRoC)
- An Application of Convolutional-LSTM Network and Video QA Korea Computer Congress (KCC)
- Scale-Varying Triplet Ranking with Classification Loss for Facial Age Estimation Asian Conference on Computer Vision (ACCV)
- CBVMR: Content-Based Video-Music Retrieval Using Soft Intra-Modal Structure Constraint Proceedings of the ACM international conference on Multimedia Retrieval (ICMR)
- D3: Recognizing dynamic scenes with deep dual descriptor based on key frames and key segments Neurocomputing
SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person
International Conference on Image Processing (ICIP'17), IEEE
- Convolutional Texture Networks based on Histogram Pooling
- Image-text multi-modal representation learning by adversarial backpropagation arXiv preprint arXiv:1612.08354
- Deep CNN-based Person Identification using Facial and Clothing Features Jun 2016, Summer General Conference '16, IEEK
- Using Triplet-based Loss for Training Ordinal Classification Deep Models [detail]
- Partial Face Based Person Identification Across Poses [detail]
- Rendering for teleportaion in AR devices
- Mar 2018 - Dec 2020, funded by National Research Foundation (NRF)
- Lab website renovation, Dec 2019 (sgvr.kaist.ac.kr)
- Age, gender, and expression recognition using face images
- Dec 2016 - Feb 2018, funded by Korea Advanced Institute of Science and Technology
- Multi-view Face Recognition based on Deep Learning
- May 2016 - May 2017, funded by Electronics and Telecommunications Research Institute (ETRI)
- Teaching Assistants
- GSAG-KAIST Research and Education Program, 1/2019-2/2019
- CS206: Data Structure (Spring 2019), 3/2019-6/2019
- CS688: Web-Scale Image Retrieval (Fall 2018), 9/2018-12/2018
- CS101: Introduction to Programming, 9/2016-12/2017, 9/2018-12/2018
- Undergraduate Research Assistant
- DB Lab, Yonsei University, 1/2014-2/2014