About me
I am a postdoctoral fellow in the School of Engineering and Applied Sciences at Harvard University, working with Prof. Hanspeter Pfister. I received my B.S., M.S., and Ph.D. from KAIST, advised by Prof. In So Kweon. My research lies in computer vision and machine learning. I am particularly interested in data-efficient learning, focusing on audio-visual learning, multimodal learning, multi-task learning, and other related areas.
Journals Publications
ENInst: Enhancing weakly-supervised low-shot instance segmentation
JMoon Ye-Bin, Dongmin Choi, Yongjin Kwon, Junsik Kim, Tae-Hyun Oh
Pattern Recognition, 2024
[Paper]Weakly Supervised Contrastive Learning for Unsupervised Vehicle Reidentification
Jongmin Yu, Hyeontaek Oh, Minkyung Kim, Junsik Kim†
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023 (Early Access)
[Paper]An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
Minkyung Kim, Jongmin Yu, Junsik Kim†, Tae-Hyun Oh, Jun Kyun Choi
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023 (Early Access)
[Paper]Active Anomaly Detection Based on Deep One-Class Classification
Minkyung Kim, Junsik Kim, Jongmin Yu, Jun Kyun Choi
Pattern Recognition Letters, 2022
[Paper]Learning to Localize Sound Source in Visual Scenes: Analysis and Applications
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang ,In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
[Paper] [Project]Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time
Kyungdon Joo, Tae-Hyun Oh, Junsik Kim, In So Kweon
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019
[Paper] [Project]
Conferences Proceedings
Sound Source Localization is All about Cross-Modal Alignment
Arda Senocak*, Hyeonggon Ryu*, Junsik Kim*, Tae-Hyun Oh, Hanspeter Pfister, Joon Son Chung
IEEE International Conference on Computer Vision (ICCV), Oct. 2023
[Paper]
Event-Specific Audio-Visual Fusion Layers: A Simple and New Perspective on Video Understanding
Arda Senocak*, Junsik Kim*, Tae-Hyun Oh, Dingzeyu Li, In So Kweon
IEEE Winter Conference on Applications of Computer Vision (WACV), Jan. 2023
[Paper]
Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics
Minkyung Kim, Junsik Kim, Jongmin Yu, Jun Kyun Choi
ICDM 2022 Workshop Deep Learning and Clustering (ICDMW), Nov 2022
[Paper]
ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound
Domain Adaptation in Semantic Segmentation
Fei Pan, Sungsu Hur, Seokju Lee, Junsik Kim, In So Kweon
European Conference on Computer Vision (ECCV), Oct 2022
[Paper]
Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification
Jongmin Yu, Junsik Kim, Minkyung Kim, Hyeontaek Oh
IEEE International Conference on Robotics and Automation (ICRA), May 2022
[Paper] [Project]
Learning Sound Localization Better from Semantically Similar Samples
Arda Senocak*, Hyeonggon Ryu*, Junsik Kim*, In So Kweon (* equal contribution)
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022
[Paper]
Less Can Be More: Sound Source Localization With a Classification Model
Arda Senocak*, Hyeonggon Ryu*, Junsik Kim*, In So Kweon (* equal contribution)
IEEE Winter Conference on Applications of Computer Vision (WACV), Jan. 2022
[Paper]
Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination
Jongmin Yu, Hyeontaek Oh, Minkyung Kim, Junsik Kim
NeurIPS 2021 Workshop DGMs Applications, Dec. 2021
[Paper] [Project]
Restoration of Video Frames From a Single Blurred Image With Motion Understanding
Dawit Mureja Argaw, Junsik Kim, Francois Rameau, Chaoning Zhang, In So Kweon
IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshop), Jun. 2021
[Paper]
Motion-blurred Video Interpolation and Extrapolation
Dawit Mureja Argaw, Junsik Kim, Francois Rameau, In So Kweon
AAAI Conference on Artificial Intelligence (AAAI), Feb. 2021
[Paper]
Optical Flow Estimation from a Single Motion-Blurred Image
Dawit Mureja Argaw, Junsik Kim, Francois Rameau, JaeWon Cho, In So Kweon
AAAI Conference on Artificial Intelligence (AAAI), Feb. 2021
[Paper]
ResNet or DenseNet? Introducing Dense Short-cuts to ResNet
Chaoning Zhang*, Philipp Benz*, Dawit Mureja Argaw, Seokju Lee, Junsik Kim, Francois Rameau,
Jean-Charles Bazin, In So Kweon
IEEE Winter Conference on Applications of Computer Vision (WACV), Jan. 2021.
[Paper]
DeepPTZ: Deep Self-Calibration for PTZ Cameras
Chaoning Zhang, Francois Rameau, Junsik Kim, Dawit Mureja Argaw, Jean-Charles Bazin, In So Kweon
IEEE Winter Conference on Applications of Computer Vision (WACV), Mar. 2020.
[Paper]
Revisiting Residual Networks with Nonlinear Shortcuts
Chaoning Zhang, Francois Rameau, Seokju Lee, Junsik Kim, Philipp Benz, Dawit Mureja Argaw,
Jean-Charles Bazin, In So Kweon
British Machine Vision Conference (BMVC), Sep. 2019 (spotlight)
[Paper]
Visuomotor Understanding for Representation Learning of Driving Scenes
Seokju Lee, Junsik Kim, Tae-Hun Oh, Yongseop Jeong, Donggeun Yoo, Stephen Lin, In So Kweon
British Machine Vision Conference (BMVC), Sep. 2019
[Paper] [Project]
Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
Junsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2019
[Paper] [Project]
Part-based Player Identification using Deep Convolutional Representation and Multi-scale Pooling
Arda Senocak, Tae-Hyun Oh, Junsik Kim, In So Kweon
In CVSports workshop in conjunction with CVPR, Jun. 2018
[Paper]
Learning to Localize Sound Source in Visual Scenes
Arda Senocak, Tae-Hyun Oh, Junsik Kim, Ming-Hsuan Yang, In So Kweon
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2018
[Paper] [Project]
Co-domain Embedding using Deep Quadruplet Networks for Unseen Traffic Sign Recognition
Junsik Kim, Seokju Lee, Tae-Hyun Oh, In So Kweon
AAAI Conference on Artificial Intelligence (AAAI), Feb. 2018
[Paper]
VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition
Seokju Lee, Junsik Kim, Jae Shin Yoon, Seunghak Shin, Oleksandr Bailo, Namil Kim, Tae-Hee Lee,
Hyun Seok Hong, Seung-Hoon Han, In So Kweon
IEEE International Conference on Computer Vision (ICCV), Oct. 2017
[Paper] [Project]
Pixel-Level Matching for Video Object Segmentation Using Convolutional Neural Networks
Jae Shin Yoon, Francois Rameau, Junsik Kim, Seokju Lee, Seunghak Shin, In So Kweon
IEEE International Conference on Computer Vision (ICCV), Oct. 2017
[Paper] [Project]
Awards & Honors
Best Poster Award, Workshop on What is Motion for? in conjuction with ECCV 2022
Outstanding Reviewer Award, International Conference on Learning Representations (ICLR) 2021
Qualcomm Innovation Awards Sep. 2018
Best Poster Presentation Award, IPIU Feb. 2018
Magna Cum Laude, KAIST, Feb. 2012
Honor Student Program, KAIST Sep. 2010 - Feb. 2012
National Science and Engineering Scholarship, KOSAF Feb. 2008 - Feb. 2012
Academic Activities
Reviewer
International Journals
Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
International Journal of Computer Vision (IJCV)
Sensors
The Visual Computer
Electronics
International Conferences
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 -
IEEE International Conference on Computer Vision (ICCV) 2019 -
European Conference on Computer Vision (ECCV) 2018 -
Conference on Neural Information Processing Systems (NeurIPS) 2020 -
International Conference on Machine Learning (ICML) 2020 -
International Conference on Learning Representations (ICLR) 2021 -
AAAI Conference on Artificial Intelligence (AAAI) 2020 -
British Machine Vision Conference (BMVC) 2019 -
Winter Conference on Applications of Computer Vision (WACV) 2020 -
Asia Conference on Computer Vision (ACCV) 2018 -