cv
You can find my CV on the top pdf download button.
Basics
| Name | Jungin Park |
| Label | Assistant Professor, PhD |
| jungin.park@dgist.ac.kr | |
| Url | https://park-jungin.github.io |
Interests
| Artificial Intelligence | ||||||
| Computer Vision | ||||||
| Video Understanding | ||||||
| Multi-modal Learning | ||||||
| Vision-and-Language | ||||||
| Efficient Machine Learning | ||||||
Education
-
2018.03 - 2024.02 Seoul, Korea
PhD
Yonsei University, Seoul, Korea Electrical and Electronic Engineering - Advisor: Kwanghoon Sohn
- Dissertation: Language-guided spatiotemporal representation learning for video understanding
-
2012.03 - 2018.02 Seoul, Korea
BS
Yonsei University, Seoul, Korea Electrical and Electronic Engineering
Work
-
2026.10 - present Assistant Professor
DGIST -
2025.04 - 2026.09 Research Professor
Yonsei University -
2024.09 - 2025.03 Postdoctoral Fellow
Yonsei University -
2024.03 - 2024.09 Visiting Researcher
NAVER Cloud AI Lab
Publications
-
2026 Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models
Conference on Neural Information Processing Systems (NeurIPS) Jungin Park, Chaoran Zhu, Changjae Oh, and Kwanghoon Sohn† -
2026 V-LynX: Video interface alignment for video+x llms
International Conference on Machine Learning (ICML) Jungin Park, Jiyoung Lee†, and Kwanghoon Sohn† -
2026 Saliency-aware model merging
International Conference on Machine Learning (ICML) Jungin Park, Jiyoung Lee†, and Kwanghoon Sohn† -
2025 Geospatial domain adaptation with truncated parameter-efficient fine-tuning
IEEE Geoscience and Remote Sensing Letters (GRSL) Kwonyoung Kim, Jungin Park, and Kwanghoon Sohn† -
2025.09 Language-guided recursive spatiotemporal graph modeling for video summarization
International Journal of Computer Vision (IJCV) Jungin Park, Jiyoung Lee†, and Kwanghoon Sohn† -
2025.02 Bootstrap your own views: Masked ego-exo modeling for fine-grained view-invariant video representations
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jungin Park, Jiyoung Lee†, and Kwanghoon Sohn† -
2025.02 Faster parameter-efficient tuning with token redundancy reduction
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Kwonyoung Kim, Jungin Park†, Jin Kim, Hyeongjun Kwon, and Kwanghoon Sohn† -
2024.05 Bridging vision and language spaces with assignment prediction
International Conference on Learning Representations (ICLR) Jungin Park, Jiyoung Lee†, and Kwanghoon Sohn† -
2023.1 Knowing where to focus: Event-aware transformer for video grounding
IEEE/CVF International Conference on Computer Vision (ICCV) Jinhyun Jang, Jungin Park, Jin Kim, Hyeongjun Kwon, and Kwanghoon Sohn -
2023.06 Dual-path adaptation from image to video transformers
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jungin Park*, Jiyoung Lee*, and Kwanghoon Sohn -
2023.06 Partmix: Regularization strategy to learn part discovery for visible-infrared person re-identification
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Minsu Kim, Seungryong Kim, Jungin Park, Seongheon Park, and Kwanghoon Sohn -
2023.01 Language-free training for zero-shot video grounding
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Dahye Kim, Jungin Park, Jiyoung Lee, Seongheon Park, and Kwanghoon Sohn -
2022.1 Pointfix: Learning to fix domain bias for robust online stereo adaptation
European Conference on Computer Vision (ECCV) Kwonyoung Kim, Jungin Park, Jiyoung Lee, Dongbo Min, and Kwanghoon Sohn -
2022.06 Probabilistic representations for video contrastive learning
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jungin Park, Jiyoung Lee, Ig-Jae Kim, and Kwanghoon Sohn -
2022.06 Pin the memory: Learning to generalize semantic segmentation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jin Kim, Jiyoung Lee, Jungin Park, Dongbo Min, and Kwanghoon Sohn -
2021.09 Self-balanced learning for domain generalization
IEEE International Conference on Image Processing (ICIP) Jin Kim, Jiyoung Lee, Jungin Park, Dongbo Min, and Kwanghoon Sohn -
2021.06 Bridge to answer: Structure-aware graph interaction network for video question answering
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jungin Park, Jiyoung Lee, and Kwanghoon Sohn -
2020.12 Cross-domain grouping and alignment for domain adaptive semantic segmentation
AAAI Conference on Artificial Intelligence (AAAI) Minsu Kim, Sunghun Joung, Seungryong Kim, Jungin Park, Ig-Jae Kim, and Kwanghoon Sohn -
2020.1 Sumgraph: Video summarization via recursive graph modeling
European Conference on Computer Vision (ECCV) Jungin Park*, Jiyoung Lee*, Ig-Jae Kim, and Kwanghoon Sohn -
2019.1 Context-aware emotion recognition networks
IEEE/CVF International Conference on Computer Vision (ICCV) Jiyoung Lee, Seungryong Kim, Sunok Kim, Jungin Park, and Kwanghoon Sohn -
2019.1 Video summarization by learning relationships between action and scene
IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, and Kwanghoon Sohn -
2019.09 Graph regularization network with semantic affinity for weakly-supervised temporal action localization
IEEE International Conference on Image Processing (ICIP) Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, and Kwanghoon Sohn -
2018.1 Learning to detect, associate, and recognize human actions and surrounding scenes in untrimmed videos
ACM Multimedia Workshop (MMW) Jungin Park, Sangryul Jeon, Seungryong Kim, Jiyoung Lee, Sunok Kim, and Kwanghoon Sohn
Awards
-
2023 Academic Research Fellowship
Yonsei University -
2019 Outstanding 100 National Research Projects
Ministry of Science and ICT, Korea Research assistant -
2019 3rd Place at the CoVieW 2019 ICCV Challenge
ICCV 2019 Workshop -
2019 2nd Place at the Workshop on Frontiers of Electrical Engineering
Yonsei University
Projects
-
2025.03 - 2026.09 Omni-modal Benchmarking and Learning
Omni-modal Data Construction and Integration towards Artificial General Intelligence- Ministry of Science and ICT - Mid-level Research
-
2025.03 - 2026.09 Omni-modal Learning
Development of Omni-modal-based General-purpose Artificial Intelligence- Yonsei University - Yonsei Signature Research Cluster
-
2022.03 - 2024.02 Multi-modal Learning
Development of Multimodal-based General-purpose Artificial Social Intelligence- Yonsei University - Yonsei Signature Research Cluster
-
2021.03 - 2024.02 Multi-modal Learning
Development of Multi-modal Data Fusion and Artificial Social Intelligence for Comprehensive Scene Understanding and Prediction- Ministry of Science - Mid-level Research
-
2020.04 - 2022.03 Domain Generalization and Adaptation
To Create AI Systems that Act Appropriately and Effectively in Novel Situations that Occur in Open Worlds- Institute of Information&Communication Technology
-
2018.03 - 2020.02 Video Understanding
Fundamental Research of Vision Algorithms for Comprehensive and Thorough Video Understanding- Ministry of Science, ICT, and Future Planning
Languages
| Korean | ||
| Native speaker | ||
| English | ||
| Fluent | ||