Jinwoo Choi's Academic Homepage



Jinwoo Choi (최진우)

  Ph.D. Candidate



  Contact
  E-mail: jinchoi [at] vt [dot] edu (official) 
  Tel: +1-540-998-1587
  Lab: 415 Whittemore, 1185 Perry Street, Blacksburg VA 24061, USA





About Me

I am a Ph.D. candidate in the Virginia Tech Vision and Learning Lab and my advisor is Professor Jia-Bin Huang. From March 2010 to July 2015, I completed my military duty at the Electronics and Telecommunications Research Institute (ETRI), Republic of Korea as a computer vision researcher. Prior to that, I completed my master's degree at Seoul National University (SNU) under the supervision of Professor Sang-Uk Lee. During my master's course, I closely collaborated with Professor Chang-Su Kim.


I am lucky to have the opportunity to work with Gaurav Sharma, Samuel Schulter and Manmohan Chandraker from NEC Labs America.



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, segmentation, and scene understanding.



Education


Now : Ph.D. candidate in Bradley Department of Electrical and 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


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.
Jun. 2020    I will be serving as a reviewer of ICPR 2020.
Mar. 2020    I will be serving as a reviewer of NeurIPS
 2020.
Mar. 2020    Submitted one paper to ECCV 2020 in collaboration with NEC Labs Amercia.
Jan. 2020    I gave an invited talk "Action Recognition with Knowledge Transfer" at Samsung Advanced Institute of Technology, Korea.
Dec. 2019    One paper is accepted to WACV 2020.
Dec. 2019    I have passed my Ph.D. preliminary exam.
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!
Aug. 2019    Successfully finished my second internship
 at NEC Labs Amercia.
Aug. 2019    I am serving as a reviewer of WACV 2020.
Jul.  2019    Submitted one paper to WACV 2020 in collaboration with 
NEC Labs Amercia.
May. 2019    
I returned to NEC Labs AmerciaMedia Analytics Department, located in San Jose, CA, as a reserch intern. Gaurav Sharma, Samuel Schulter and Manmohan Chandraker are my mentors here. 
May. 2019   Submitted one paper to NeurIPS 2019. 
Apr. 2019   
I'll return to NEC Labs Amercia, as a research intern during Summer 2019.
Aug. 2018    Successfully finished my internship at NEC Labs Amercia.
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. 
Feb. 2018    I'll work at NEC Labs Amercia, as a research intern during Summer 2018.
Sep. 2016    Created Awesome Action Recognition GitHub page.


Selected Publications


          Anonymous Title

           Submitted to NeurIPS 2020.

            Jinwoo Choi, Gaurav Sharma, and Jia-Bin Huang


          - Shuffle and Attend: Video Domain Adaptation

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

            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 (ECCVWorkshop, 2014. [pdfslide]

  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 



Relevant Courses Taken


@ Virginia Tech
- Computer Vision
- Machine Learning
- Advanced Computer Vision
- Probabilistic Graphical Models and Structured Prediction
- Introduction to Artificial Intelligence
- Bayesian Statistics
- Convex Optimization

@ SNU
- Multiple View Geometry
- Stochastic Signals and Random Processes
- Adaptive Signal Processing
- Multirate Signal Processing
- Image Signal Processing



Skills

Programming Languages

     • Python

     • MATLAB

     • C/C++

     • Java

     • Shell Script


Deep Learning Libraries

     • PyTorch

     • TensorFlow

     • Keras

     • Caffe

     • MatConvNet



 
Last update: Aug. 27, 2020