Jinwoo Choi (최진우), Ph.D.
Assistant Professor
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 / LinkedIn
About Me
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
Jun. 2025 One paper is accepted to ICCV 2025.
May 2025 Multi-Purpose Visual Information Coding for Human and Machine Vision (인간과 기계 시각을 동시에 지원하는 다목적 시각정보 압축 연구) has been selected as a Global Basic Research Lab funded by the NRF, Korea (한국연구재단 글로벌기초연구실).
Apr. 2025 MASH-VLM is selected as a Highlight (3.7% acceptance rate) in CVPR 2025!
Feb. 2025 Two papers are accepted to CVPR 2025.
Dec. 2024 One paper is accepted to AAAI 2025.
Aug. 2024 One paper is accepted to ECCV 2024 as an Oral (2.3% acceptance rate).
Mar. 2024 I serve as an Industry Chair of KCCV 2024, Busan, Korea.
Feb. 2024 Two papers are accepted to CVPR 2024.
Sep. 2023 One paper is accepted to NeurIPS 2023.
Nov. 2022 Selected as an outstanding reviewer at ECCV 2022.
Jul. 2021 I launched KHU Vision and Learning Reading Group with Prof. Seong Tae Kim and Prof. Gyeong-Moon Park at KHU CS.
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.
Feb. 2021 Selected as Top 25% program committee of AAAI 2021.
Dec. 2020 I successfully defended my Ph.D. dissertation.
Selected Publications († equally contributed first authors, * indicates the corresponding author(s))
- ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning
To appear in IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
Jongseo Lee†, Kyungho Bae†, Kyle Min, Gyeong-Moon Park*, Jinwoo Choi*
- PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition
XAI4CV Workshop, IEEE/CVF Computer Vision and Pattern Recognition (CVPR), (Spotlight! presentation, 16.7% acceptance rate) 2025. [arXiv]
Jongseo Lee, Wooil Lee, Gyeong-Moon Park*, Seong Tae Kim* and Jinwoo Choi*
- MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. (Highlight! presentation, 3.7% acceptance rate) [pdf] [arXiv]
Kyungho Bae, Jinhyung Kim, Sihaeng Lee, Soonyoung Lee, Gunhee Lee*, Jinwoo Choi*
- Universal Domain Adaptation for Semantic Segmentation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [arXiv]
Seun-An Choe, Keon-Hee Park, Jinwoo Choi, Gyeong-Moon Park*
- HiCM^2: Hierarchical Compact Memory Modeling for Dense Video Captioning.
AAAI Conference on Artificial Intelligence (AAAI), 2025. [arXiv]
Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi*, Seong Tae Kim*
- DEVIAS: Learning Disentangled Video Representations of Action and Scene
European Conference on Computer Vision (ECCV) 2024. (Oral! presentation, 2.3% acceptance rate) [arXiv][project page][talk][code]
Kyungho Bae†, Geo Ahn†, Youngrae Kim†, Jinwoo Choi*
- Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [arXiv][code]
Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi*, Seong Tae Kim*
- Open Set Domain Adaptation for Semantic Segmentation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [arXiv][code]
Seun-An Choe†, Ah-Hyung Shin†, Keon-Hee Park, Jinwoo Choi*, Gyeong-Moon Park*
- 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*
- 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
- 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),