publications

2026

1. Embodied AI

   Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models

   Jungin Park^*, Chaoran Zhu^*, Changjae Oh, and 1 more author

   In Conference on Neural Information Processing Systems (NeurIPS), 2026

   Bib

   @inproceedings{park2026spatial,
     title = {Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models},
     author = {Park, Jungin and Zhu, Chaoran and Oh, Changjae and Sohn, Kwanghoon},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
     year = {2026},
     publisher = {NeurIPS},
     selected = true
   }

2. Omnimodal

   V-LynX: Video interface alignment for video+x llms

   Jungin Park, Jiyoung Lee^†, and Kwanghoon Sohn^†

   In Internaional Conference on Machine Learning (ICML), 2026

   Bib PDF Code

   @inproceedings{park2026vlynx,
     title = {V-LynX: Video interface alignment for video+x llms},
     author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon},
     booktitle = {Internaional Conference on Machine Learning (ICML)},
     year = {2026},
     publisher = {ICML},
     selected = true
   }

3. Efficient ML

   Saliency-aware model merging

   Jungin Park, Jiyoung Lee^†, and Kwanghoon Sohn^†

   In Internaional Conference on Machine Learning (ICML), 2026

   Bib PDF

   @inproceedings{park2026saliency,
     title = {Saliency-aware model merging},
     author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon},
     booktitle = {Internaional Conference on Machine Learning (ICML)},
     year = {2026},
     publisher = {ICML},
     selected = true
   }

2025

1. Efficient ML

   Geospatial domain adaptation with truncated parameter-efficient fine-tuning

   Kwonyoung Kim, Jungin Park, and Kwanghoon Sohn^†

   IEEE Geoscience and Remote Sensing Letters (GRSL), 2025

   Bib PDF

   @article{kim2025geospatial,
     title = {Geospatial domain adaptation with truncated parameter-efficient fine-tuning},
     author = {Kim, Kwonyoung and Park, Jungin and Sohn, Kwanghoon},
     journal = {IEEE Geoscience and Remote Sensing Letters (GRSL)},
     year = {2025},
     publisher = {IEEE},
     selected = false
   }

2. Video-language

   Language-guided recursive spatiotemporal graph modeling for video summarization

   Jungin Park, Jiyoung Lee^†, and Kwanghoon Sohn^†

   International Journal of Computer Vision (IJCV), 2025

   Bib PDF

   @article{park2025videograph,
     title = {Language-guided recursive spatiotemporal graph modeling for video summarization},
     author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon},
     journal = {International Journal of Computer Vision (IJCV)},
     year = {2025},
     publisher = {Springer},
     selected = true
   }

3. Video understanding

   Bootstrap your own views: Masked ego-exo modeling for fine-grained view-invariant video representations

   Jungin Park, Jiyoung Lee^†, and Kwanghoon Sohn^†

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   Bib PDF Code

   @inproceedings{park2025bootstrap,
     title = {Bootstrap your own views: Masked ego-exo modeling for fine-grained view-invariant video representations},
     author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2025},
     publisher = {IEEE/CVF},
     selected = true
   }

4. Efficient ML

   Faster parameter-efficient tuning with token redundancy reduction

   Kwonyoung Kim, Jungin Park^†, Jin Kim, and 2 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   Bib PDF Code

   @inproceedings{kim2025faster,
     title = {Faster parameter-efficient tuning with token redundancy reduction},
     author = {Kim, Kwonyoung and Park, Jungin and Kim, Jin and Kwon, Hyeongjun and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2025},
     publisher = {IEEE/CVF},
   }

2024

1. Vision-language

   Bridging vision and language spaces with assignment prediction

   Jungin Park, Jiyoung Lee^†, and Kwanghoon Sohn^†

   In International Conference on Learning Representations (ICLR), 2024

   Bib PDF Code

   @inproceedings{park2024briding,
     title = {Bridging vision and language spaces with assignment prediction},
     author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2024},
     selected = true
   }

2023

1. Video-language

   Knowing where to focus: Event-aware transformer for video grounding

   Jinhyun Jang, Jungin Park, Jin Kim, and 2 more authors

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023

   Bib PDF Code

   @inproceedings{jang2023knowing,
     title = {Knowing where to focus: Event-aware transformer for video grounding},
     author = {Jang, Jinhyun and Park, Jungin and Kim, Jin and Kwon, Hyeongjun and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
     pages = {13846--13856},
     year = {2023},
     publisher = {IEEE/CVF},
   }

2. Efficient ML

   Dual-path adaptation from image to video transformers

   Jungin Park^*, Jiyoung Lee^*, and Kwanghoon Sohn

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

   Bib PDF Code

   @inproceedings{park2023dual,
     title = {Dual-path adaptation from image to video transformers},
     author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {2203--2213},
     year = {2023},
     publisher = {IEEE/CVF},
     selected = true
   }

3. Vision

   Partmix: Regularization strategy to learn part discovery for visible-infrared person re-identification

   Minsu Kim, Seungryong Kim, Jungin Park, and 2 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

   Bib PDF

   @inproceedings{kim2023partmix,
     title = {Partmix: Regularization strategy to learn part discovery for visible-infrared person re-identification},
     author = {Kim, Minsu and Kim, Seungryong and Park, Jungin and Park, Seongheon and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {18621--18632},
     year = {2023},
     publisher = {IEEE/CVF},
   }

4. Video-language

   Language-free training for zero-shot video grounding

   Dahye Kim, Jungin Park, Jiyoung Lee, and 2 more authors

   In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023

   Bib PDF

   @inproceedings{kim2023language,
     title = {Language-free training for zero-shot video grounding},
     author = {Kim, Dahye and Park, Jungin and Lee, Jiyoung and Park, Seongheon and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
     pages = {2539--2548},
     year = {2023},
     publisher = {IEEE/CVF},
   }

2022

1. Vision

   Pointfix: Learning to fix domain bias for robust online stereo adaptation

   Kwonyoung Kim, Jungin Park, Jiyoung Lee, and 2 more authors

   In European Conference on Computer Vision (ECCV), 2022

   Bib PDF

   @inproceedings{kim2022pointfix,
     title = {Pointfix: Learning to fix domain bias for robust online stereo adaptation},
     author = {Kim, Kwonyoung and Park, Jungin and Lee, Jiyoung and Min, Dongbo and Sohn, Kwanghoon},
     booktitle = {European Conference on Computer Vision (ECCV)},
     pages = {568--585},
     year = {2022},
     publisher = {Springer},
   }

2. Video understanding

   Probabilistic representations for video contrastive learning

   Jungin Park, Jiyoung Lee, Ig-Jae Kim, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

   Bib PDF

   @inproceedings{park2022probabilistic,
     title = {Probabilistic representations for video contrastive learning},
     author = {Park, Jungin and Lee, Jiyoung and Kim, Ig-Jae and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {14711--14721},
     year = {2022},
     publisher = {IEEE/CVF},
     selected = true
   }

3. Vision

   Pin the memory: Learning to generalize semantic segmentation

   Jin Kim, Jiyoung Lee, Jungin Park, and 2 more authors

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

   Bib PDF Code

   @inproceedings{kim2022pin,
     title = {Pin the memory: Learning to generalize semantic segmentation},
     author = {Kim, Jin and Lee, Jiyoung and Park, Jungin and Min, Dongbo and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {4350--4360},
     year = {2022},
     publisher = {IEEE/CVF},
   }

2021

1. Vision

   Self-balanced learning for domain generalization

   Jin Kim, Jiyoung Lee, Jungin Park, and 2 more authors

   In 2021 IEEE International Conference on Image Processing (ICIP), 2021

   Bib PDF

   @inproceedings{kim2021self,
     title = {Self-balanced learning for domain generalization},
     author = {Kim, Jin and Lee, Jiyoung and Park, Jungin and Min, Dongbo and Sohn, Kwanghoon},
     booktitle = {2021 IEEE International Conference on Image Processing (ICIP)},
     pages = {779--783},
     year = {2021},
     publisher = {IEEE},
   }

2. Video-language

   Bridge to answer: Structure-aware graph interaction network for video question answering

   Jungin Park, Jiyoung Lee, and Kwanghoon Sohn

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

   Bib PDF

   @inproceedings{park2021bridge,
     title = {Bridge to answer: Structure-aware graph interaction network for video question answering},
     author = {Park, Jungin and Lee, Jiyoung and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {15526--15535},
     year = {2021},
     publisher = {IEEE/CVF},
     selected = true
   }

2020

1. Vision

   Cross-domain grouping and alignment for domain adaptive semantic segmentation

   Minsu Kim, Sunghun Joung, Seungryong Kim, and 3 more authors

   In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020

   Bib PDF

   @inproceedings{kim2021cross,
     title = {Cross-domain grouping and alignment for domain adaptive semantic segmentation},
     author = {Kim, Minsu and Joung, Sunghun and Kim, Seungryong and Park, JungIn and Kim, Ig-Jae and Sohn, Kwanghoon},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
     volume = {35},
     number = {3},
     pages = {1799--1807},
     year = {2020},
     publisher = {AAAI Press},
   }

2. Video understanding

   Sumgraph: Video summarization via recursive graph modeling

   Jungin Park^*, Jiyoung Lee^*, Ig-Jae Kim, and 1 more author

   In European Conference on Computer Vision (ECCV), 2020

   Bib PDF

   @inproceedings{park2020sumgraph,
     title = {Sumgraph: Video summarization via recursive graph modeling},
     author = {Park, Jungin and Lee, Jiyoung and Kim, Ig-Jae and Sohn, Kwanghoon},
     booktitle = {European Conference on Computer Vision (ECCV)},
     pages = {647--663},
     year = {2020},
     publisher = {Springer},
     selected = true
   }

2019

1. Video understanding

   Video summarization by learning relationships between action and scene

   Jungin Park, Jiyoung Lee, Sangryul Jeon, and 1 more author

   In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2019

   3rd place Bib PDF

   3rd place in the ICCV Challenge on Comprehensive Video Understanding in the Wild (CoVieW 2019)

   @inproceedings{park2019video,
     title = {Video summarization by learning relationships between action and scene},
     author = {Park, Jungin and Lee, Jiyoung and Jeon, Sangryul and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
     year = {2019},
     publisher = {IEEE/CVF},
   }

2. Vision

   Context-aware emotion recognition networks

   Jiyoung Lee, Seungryong Kim, Sunok Kim, and 2 more authors

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019

   Bib PDF Dataset

   @inproceedings{lee2019context,
     title = {Context-aware emotion recognition networks},
     author = {Lee, Jiyoung and Kim, Seungryong and Kim, Sunok and Park, Jungin and Sohn, Kwanghoon},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
     pages = {10143--10152},
     year = {2019},
     publisher = {IEEE/CVF},
   }

3. Video understanding

   Graph regularization network with semantic affinity for weakly-supervised temporal action localization

   Jungin Park, Jiyoung Lee, Sangryul Jeon, and 2 more authors

   In 2019 IEEE International Conference on Image Processing (ICIP), 2019

   Bib PDF

   @inproceedings{park2019graph,
     title = {Graph regularization network with semantic affinity for weakly-supervised temporal action localization},
     author = {Park, Jungin and Lee, Jiyoung and Jeon, Sangryul and Kim, Seungryong and Sohn, Kwanghoon},
     booktitle = {2019 IEEE International Conference on Image Processing (ICIP)},
     pages = {3701--3705},
     year = {2019},
     publisher = {IEEE},
   }

2018

1. Video understanding

   Learning to detect, associate, and recognize human actions and surrounding scenes in untrimmed videos

   Jungin Park, Sangryul Jeon, Seungryong Kim, and 3 more authors

   In Proceedings of the ACM Multimedia Workshop (MMW), 2018

   Bib PDF

   @inproceedings{park2018learning,
     title = {Learning to detect, associate, and recognize human actions and surrounding scenes in untrimmed videos},
     author = {Park, Jungin and Jeon, Sangryul and Kim, Seungryong and Lee, Jiyoung and Kim, Sunok and Sohn, Kwanghoon},
     booktitle = {Proceedings of the ACM Multimedia Workshop (MMW)},
     pages = {21--26},
     year = {2018},
     publisher = {ACM},
   }