Jinwoo Choi's Homepage

Jinwoo Choi (최진우), Ph.D.

Assistant Professor

Department of Computer Science and Engineering

Kyung Hee University

Contact

E-mail: jinwoochoi [at] khu [dot] ac [dot] kr (official)

Tel: +82-31-201-3758

Office: 324 Electronic Information College Building, 1732, Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do, Rep. of Korea, 17104

CV / Google Scholar / GitHub / LinkedIn


About Me

I am an Assistant Professor in the Department of Computer Science Engineering, Kyung Hee University, leading the Vision and Learning Lab. I obtained a Ph.D. from the Bradley Department of Electrical and Computer Engineering, Virginia Tech, in 2020 advised by Jia-Bin Huang. I am lucky to have the opportunity to work with Gaurav Sharma, Samuel Schulter, and Manmohan Chandraker from NEC Labs America. From March 2010 to July 2015, I completed my military duty at the Electronics and Telecommunications Research Institute (ETRI), the Republic of Korea as a computer vision researcher. Before that, I completed my master's degree at Seoul National University (SNU) advised by Sang-Uk Lee. During my master's course, I closely collaborated with Chang-Su Kim.


Research Interests

Computer Vision and Machine Learning

I am especially interested in human activity understanding, video representation learning, domain adaptation and mitigating biases in visual recognition.

I am also interested in object detection, semantic segmentation, scene understanding and other visual recognition problems.


Education

2020 : Ph.D. in Computer Engineering, Virginia Tech.

2010 : M.S. in Electrical Engineering and Computer Science, Seoul National University (SNU), Seoul, Korea.

2008 : B.S. in Electrical Engineering, Seoul National University (SNU), Seoul, Korea.

News


Jul. 2021 I launched KHU Vision and Learning Reading Group with Prof. Seong Tae Kim and Prof. Gyeong-Moon Park at KHU CS.

Jul. 2021 Hyogun Lee is joining our lab as an undergraduate intern!

Jun. 2021 Dongho Lee and Jongmin (Paul) Shin joined our lab as master students, and Gyeongho Bae joined our lab as an undergraduate intern!

May. 2021 Selected as an outstanding reviewer at CVPR 2021.

Mar. 2021 I joined the Department of Computer Science Engineering, Kyung Hee University, as an Assistant Professor. Drop me an email with your CV if you are interested in working with me on computer vision, machine learning, and video understanding problems!

Feb. 2021 Selected as Top 25% program committee of AAAI 2021.

Feb. 2021 I will be serving as a reviewer of ICCV 2021.

Dec. 2020 I have successfully defended my Ph.D. dissertation.

Dec. 2020 I will be serving as a reviewer of CVPR 2021 and ICML 2021.

Nov. 2020 Submitted one paper to CVPR 2021.

Oct. 2020 I receive the Bindi Prasad Fellowship from the Bradley Department of Electrical and Computer Engineering, Virginia Tech.

Aug. 2020 I will be serving as a PC (reviewer) of AAAI 2021.

Jul. 2020 I will be serving as a reviewer of ICLR 2021.

Jul. 2020 One paper is accepted to ECCV 2020. Virtually see you at ECCV this August!

Jun. 2020 Submitted one paper to NeurIPS 2020.

Mar. 2020 I will be serving as a reviewer of NeurIPS 2020.

Jan. 2020 I gave an invited talk "Action Recognition with Knowledge Transfer" at Samsung Advanced Institute of Technology, Korea.

Oct. 2019 I have been selected for a NeurIPS 2019 travel award.

Sep. 2019 One paper is accepted to NeurIPS 2019. See you at Vancouver, Canada this December!

May. 2019 I returned to NEC Labs Amercia, Media Analytics Department, located in San Jose, CA, as a reserch intern. Gaurav Sharma, Samuel Schulter and Manmohan Chandraker are my mentors here.

Jun. 2018 I started my internship at NEC Labs Amercia, Media Analytics Department, located in Cuptertino, CA, as a reserch intern. Gaurav Sharma and Manmohan Chandraker are my mentors here.

Sep. 2016 Created Awesome Action Recognition GitHub page.

Selected Publications


- Learning Representational Invariances for Data-Efficient Action Recognition

arXiv preprint. [arXiv] [project page] [code]

Jinwoo Choi*, Yuliang Zou*, Qitong Wang, and Jia-Bin Huang

(* indicates equal contribution)

- Shuffle and Attend: Video Domain Adaptation

European Conference on Computer Vision (ECCV) 2020. (26.4% acceptance rate) [pdf] [project page] [short talk] [long talk] [supplementary]

Jinwoo Choi, Gaurav Sharma, Samuel Schulter, and Jia-Bin Huang

- Unsupervised and Semi-Supervised Domain Adaptation for Action Recognition from Drones

Winter Conference on Applications of Computer Vision (WACV) 2020. (Oral presentation) [pdf] [project page] [talk video]


Jinwoo Choi, Gaurav Sharma, Manmohan Chandraker, and Jia-Bin Huang

- Why Can’t I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition


Proceedings of Neural Information Processing Systems (NeurIPS), 2019. (21.2% acceptance rate) [pdf] [arXiv] [project page] [code] [poster]

Jinwoo Choi, Chen Gao, Joseph Messou, and Jia-Bin Huang


- Robust Multi-Person Tracking for Real-Time Intelligent Video Surveillance

ETRI Journal (SCI), 2015.

Jinwoo Choi, Daesung Moon, and Jang-Hee Yoo


- Obscene Video Detection Using Multiple-Classifier Fusion

Japan-Korea Joint Workshop on Frontiers of Computer Vision (FCV), 2015. (Oral presentation)

Jinwoo Choi and Seungwan Han


- The Visual Object Tracking VOT2014 Challenge Results

European Conference on Computer Vision (ECCV) Workshop, 2014. [pdf, slide]

Matej Kristan et al. (including Jinwoo Choi),


- Real-Time Multi-Person Tracking in Fixed Surveillance Camera Environment

IEEE International Conference on Consumer Electronics (ICCE), 2013. [pdf]

Jinwoo Choi and Jang-Hee Yoo


- Multiple Channel Division for Efficient Distributed Video Coding

IEEE International Conference on Image Processing (ICIP), 2009. [pdf]

Sang-Uk Park, Young-Yoon Lee, Jinwoo Choi, Chang-Su Kim, and Sang-Uk Lee


- Flexible Complexity Control between Encoder and Decoder for Video Coding

IEEE International Workshop on Multimedia Signal Processing (MMSP), 2009. [pdf]

Jinwoo Choi, Sang-Uk Park, Chang-Su Kim, and Sang-Uk Lee


- Efficient Distributed Video Coding Using Symmetric Motion Estimation and Channel Division

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, 2009. [pdf]

Sang-Uk Park, Jinwoo Choi, Chang-Su Kim, Sang-Uk Lee, Jung Won Kang, and Kyung Jun Lee

Projects


- Visual Question Answering with Various Feature Combinations: Extensions of Visual Question Answering (Fall 2015)

• Class Project of ECE5554 Computer Vision and CS5824 Machine Learning, Virginia Tech

Webpage / Final Report


- Development of the Filtering Technology for Objectionable Streaming Contents on Smart Experience Platform (Apr 2014 ~ Jul 2015)

• Funded by Ministry of Science, ICT and Future Planning, Korea

• Aimed at detecting and blocking of obscene video streams using computer vision and machine learning techniques on the mobile platform


- Development of Basic Technology of Human Identification and Retrieval at a Distance for Active Video Surveillance Service with Real-time Awareness of Safety Threats (Jun 2011 ~ Feb 2014)

• Funded by Ministry of Knowledge Economy, Korea

• Aimed at real-time detecting and tracking of pedestrian using fixed and pan-tilt-zoom cameras


- Research and Development of Open-IPTV Technologies for Wired and Wireless Networks (Mar 2010 ~ Feb 2011)

• Funded by Ministry of Knowledge Economy, Korea

• Aimed at real-time encoding and decoding of multiple-resolution videos simultaneously using H.264/AVC scalable extension


- Research and Development of Technologies for Next Generation IPTV Video Encoder (Jun 2010 ~ May 2011)

• Funded by SK Telecom, Korea

• Aimed at real-time encoding of multiple-resolution videos using H.264/AVC scalable extension


- Research and Development of Technologies for Improving the Quality of the Side Information in the Distributed Video Coding (Aug 2009 ~ Jan 2010)

• Funded by ETRI, Korea

• Aimed at improving the quality of the motion-compensated temporal interpolation of inter frames on the distributed video coding


- Research and Development of Technologies for Improving the Quality of the Side Information in the Distributed Video Coding (Aug 2008 ~ Jan 2009)

• Funded by ETRI, Korea

• Aimed at improving the quality of the motion-compensated temporal interpolation of inter frames on the distributed video coding

Skills

- Programming Languages

• Python

• MATLAB

• C/C++

• Java

• Shell Script


- Deep Learning Libraries

• PyTorch

• TensorFlow

• Keras

• Caffe

• MatConvNet