Jinwoo Choi's Homepage

News

Mar. 2024    I serve as an Industry Chair of KCCV 2024, Busan, Korea.

Feb. 2024    Two papers are accepted to CVPR 2024.

Oct. 2023    One paper is accepted to WACV 2024.

Sep. 2023    One paper is accepted to NeurIPS 2023.

Nov. 2022    Selected as an outstanding reviewer at ECCV 2022.

Nov. 2022    I will be serving as a reviewer of CVPR 2023.

Aug. 2022    I will be serving as a reviewer of ICLR 2022 and a PC (reviewer) of AAAI 2023.

Jul.  2022    I will be serving as a reviewer of NeurIPS 2022.

Mar. 2022    One paper is accepted to ICPR 2022.

Mar. 2022    I will be serving as a reviewer of ECCV 2022.

Feb. 2022    Jongseo Lee (KHU BME) joined our lab as an undergraduate intern! 

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 (KHU EE) joined our lab as an undergraduate intern! 

Jun. 2021    Dongho Lee and Jongmin (Paul) Shin joined our lab as master students, and Gyeongho Bae (KHU CSE) 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 successfully defended my Ph.D. dissertation.

Selected Publications

           - Open Set Domain Adaptation for Semantic Segmentation

           To appear in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

           Seun-An Choe†, Ah-Hyung Shin†, Keon-Hee Park, Jinwoo Choi* and Gyeong-Moon Park*

         († equally contributed first authors, * indicates the corresponding author)

           - Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval

           To appear in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

           Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi* and Seong Tae Kim*

         († equally contributed first authors, * indicates the corresponding author)

           - CAST: Cross-Attention in Space and Time for Video Action Recognition

           Proceedings of Neural Information Processing Systems (NeurIPS), 2023. [arXiv] [project page] [code]

           Dongho Lee†, Jongseo Lee†, Jinwoo Choi*

         († equally contributed first authors, * indicates the corresponding author)

           - Learning Representational Invariances for Data-Efficient Action Recognition

           Computer Vision and Image Understanding (CVIU) 2023. [pdf] [arXiv] [project page] [code]

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

         (* indicates the corresponding author)

          - 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

 - The Visual Object Tracking VOT2014 Challenge Results

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

  Matej Kristan et al. (including Jinwoo Choi), 

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