Computer Vision Machine Learning Lab

School of Computer Science and Engineering, Chung-Ang University


221 Hueksuk-Dong, Dongjak-gu, Seoul
156-756, Korea




News

- We have 1 paper accepted in TPAMI
- We have 1 paper accepted in BMVC 2020
- Prof. Kwon is serving as a Demo Chair for KCCV 2020
- We have 1 paper accepted in ICIP 2020
- We have 2 papers accepted in ICCV 2019
- We have 3 papers accepted in ICIP 2019
- Prof. Kwon is serving as a Demo Chair for ICCV 2019
- Our paper entitled "Sphere Generative Adversarial Network Based on Geometric Moment Matching" got accepted to CVPR 2019 as an oral presentation -- congrats sung woo!
- Prof. Kwon is serving as a Area Chair for ACCV 2018
- Prof. Kwon is serving as a Finance Chair for ACM Multimedia 2018
- Outstanding Reviewer Award, BMVC 2017
- Our paper entitled "visual tracking decomposition" published in CVPR 2010 has been cited more than 1000 times.
- The first paper of CVML is accepted at BMVC 2017 -- congrats guisik!


Major Interests

- Statistical machine learning: Optimal trasport, Wasserstein ambiguity, Monte Carlo Sampling
- Deep learning: Generative adversarial network. Graph Convolution
- High-level vision: Object detection, Object tracking, Segmentation, Re-identification, 3D Point clouds, Event summarization
- Low-level vision: Dehazing, Super-resolution, and Low-light enhancement



Members

- Advisor
Junseok Kwon (2016.03~, Assistant Professor), Personal page

- Graduate students
Guisik Kim (2017.09~, PhD Candidate)
Sung Woo Park (2020.03~, PhD Candidate)
Sungmin Cho (2020.09~, PhD Candidate)
Dong Wook Shu (2020.09~, PhD Candidate)
Jin Wook Paeng (2019.03~, Master)
Dokyeong Kwon (2019.03~, Master)
Jinhee Park (2019.09~, Master)
Suhyeon Ha (2019.09~, Master)
Jin Hong (2020.03~, Master)
Juhyeon Park (2020.03~, Master)
Heebin Yoo (2021.03~, Master)

- Undergraduate Students
Kevin Jin, , , Wonbeom Jang, Hyeseong Kim, Ji Soo Kim, Amy Yoon, ٺ, Hyomin Kim, , Jisoo Park, Hunhi Jung, Rosaline Shin,

- Collaborator
Janghoon Choi, Sungyong Baik (PhD candidate, SNU)

- Alumni
Chan-Ju Park (2017, KAIST), Rae Hyuk Jung (2018, KAIST), Minseok Song (2018, Kakao), Ji Young Park (2019, Alchera), Ga Young Kim (2019, LG Electronics), Bo Won Choi (2019, LG CNS), Taehong Kim (2020), Chanil Kim (2020), Hjunjun Joo (2020, Hyundai Autoever), Shinyeong Yun (2020, Bear Robotics, USA), Jeongmin Lee (2021, KAIST)


Recent & Selected Publications [Click here for a full list]

- Visual Tracking by TridentAlign and Context Embedding
Janghoon Choi, Junseok Kwon, Kyoung Mu Lee, Asian Conference on Computer Vision (ACCV), Kyoto, Japan, 2020
[pdf]





- DALE : Dark Region-Aware Low-light Image Enhancement
Dokyeong Kwon, Guisik Kim, and Junseok Kwon, The 31th British Machine Vision Conference (BMVC), Manchester, UK, 2020
[pdf] [code]





- Upright Adjustment with Graph Convolutional Networks
Raehyuk Jung, Sungmin Cho, and Junseok Kwon, The 27th IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2020
[pdf]





- 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions
Dong Wook Shu*, Sung Woo Park*, and Junseok Kwon, International Conference on Computer Vision (ICCV), Seoul, Korea, 2019
(*equal contribution)
[pdf] [video1] [video2] [code]




- Deep Meta Learning for Real-Time Target-Aware Visual Tracking
Janghoon Choi, Junseok Kwon, and Kyoung Mu Lee, International Conference on Computer Vision (ICCV), Seoul, Korea, 2019
[pdf]





- Bidirectional Deep Residual learning for Haze Removal
Guisik Kim, Jinhee Park, Suhyeon Ha and Junseok Kwon, Computer Vision and Pattern Recognition (CVPR) Workshop, Long beach, USA, 2019
[pdf]





- Multi-Domain Attentive Detection Network
Sungmin Cho, Bowon Choi, Do-Hwi Kim, and Junseok Kwon, The 26th IEEE International Conference on Image Processing (ICIP) Oral presentation , Taipei, Taiwan, 2019
[pdf]





- LOW-LIGHTGAN: Low-Light Enhancement via Advanced Generative Adversarial Network with Task-Driven Training
Guisik Kim, Dokyeong Kwon, and Junseok Kwon, The 26th IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 2019
[pdf]




- Learning to Remember Past to Predict Future for Visual Tracking
Sungyong Baik, Junseok Kwon, and Kyoung Mu Lee, The 26th IEEE International Conference on Image Processing (ICIP) Oral presentation , Taipei, Taiwan, 2019
[pdf]




- Sphere Generative Adversarial Network Based on Geometric Moment Matching
Sung Woo Park and Junseok Kwon, Computer Vision and Pattern Recognition (CVPR) Oral presentation , Long beach, USA, 2019
[pdf] [code]




- Real-time Visual Tracking by Deep Reinforced Decision Making
Janghoon Choi, Junseok Kwon, and Kyoung Mu Lee, Computer Vision and Image Understanding (CVIU), vol. 171, June, page 10-19, 2018
[pdf]




- Adaptive Patch based Convolutional Neural Network for Robust Dehazing
Guisik Kim, Suhyeon Ha, Junseok Kwon, The 25th IEEE International Conference on Image Processing (ICIP), Athenes, Greece, 2018
[pdf]




- Robust Pixel-wise Dehazing Algorithm based on Advanced Haze-Relevant Features
Guisik Kim, Junseok. Kwon, The 28th British Machine Vision Conference (BMCV), London, UK. 2017.
[pdf]





Project

- Visual Recognition Algorithms based on Deep Learning in the application of Intelligent Robots
Funded by NRF, Korea (August 2018 - February 2021)
- The technology development for event recognition/relational reasoning and learning knowledge based system for video understanding
Funded by IITP, Korea (July 2017 - December 2021)
- Computer vision system based deep learning by the handling of meteorological changes (March 2020 - February 2025)


Awards

2019.02 31th Image Processing and Image Understanding : Silver Prize
2018.02 30th Image Processing and Image Understanding : Silver Prize
2017.09 28th BMVC Outstanding Reviewers
2014.11 12th ACCV Best Reviewers
2012.11 11th ACCV Best Reviewers
2012.6 25th CVPR Doctoral Consortium
2012.2 18th Samsung Humantech Thesis Prize : Bronze Prize
2011.2 23th Image Processing and Image Understanding : Best Poster
2011.2 17th Samsung Humantech Thesis Prize : Gold Prize
2010.2 16th Samsung Humantech Thesis Prize : Honor Prize