publications

2025

1. Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations

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

   In IEEE/CVF International Conference on Computer Vision Pattern Recognition (CVPR), 2025

   Bib Code Paper

   @inproceedings{park2025byov,
     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 = {IEEE/CVF International Conference on Computer Vision Pattern Recognition (CVPR)},
     year = {2025},
     paper = {https://arxiv.org/abs/2503.19706},
   }

2. Read, watch and scream! sound generation from text and video

   Yujin Jeong , Yunji Kim, Sanghyuk Chun, and Jiyoung Lee

   In AAAI Conference on Artificial Intelligence (AAAI), 2025

   Bib Code Project Paper

   @inproceedings{jeong2025read,
     title = {Read, watch and scream! sound generation from text and video},
     author = {Jeong, Yujin and Kim, Yunji and Chun, Sanghyuk and Lee, Jiyoung},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     year = {2025},
     paper = {https://arxiv.org/abs/2407.05551},
   }

2024

1. Prototype-Guided Attention Distillation for Discriminative Person Search

   Hanjae Kim, Jiyoung Lee, and Kwanghoon Sohn

   IEEE transactions on pattern analysis and machine intelligence (TPAMI), 2024

   Paper
2. Discriminative action tubelet detector for weakly-supervised action detection

   Jiyoung Lee, Seungryong Kim , Sunok Kim, and Kwanghoon Sohn

   Pattern Recognition, 2024

   Paper
3. Bridging Vision and Language Spaces with Assignment Prediction

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

   In International Conference on Learning Representations (ICLR), 2024

   Code Paper
4. Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

   Junyoung Seo, Wooseok Jang, Min-Seop Kwak , Hyeonsu Kim, Jaehoon Ko , Junho Kim , Jin-Hwa Kim^*, Jiyoung Lee^*, and Seungryong Kim^*

   In International Conference on Learning Representations (ICLR), 2024

   Code Project Paper

2023

1. Robust camera pose refinement for multi-resolution hash encoding

   Hwan Heo , Taekyung Kim, Jiyoung Lee , Jaewon Lee , Soohyun Kim , Hyunwoo J Kim^* , and Jin-Hwa Kim^*

   In International Conference on Machine Learning (ICML), 2023

   Paper
2. Midms: Matching interleaved diffusion models for exemplar-based image translation

   Junyoung Seo , Gyuseong Lee, Seokju Cho, Jiyoung Lee, and Seungryong Kim

   In AAAI Conference on Artificial Intelligence (AAAI), 2023

   Code Project Paper
3. Imaginary voice: Face-styled diffusion model for text-to-speech

   Jiyoung Lee, Joon Son Chung, and Soo-Whan Chung

   In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023

   Code Project Paper
4. Panoramic Image-to-Image Translation

   Soohyun Kim , Junho Kim , Taekyung Kim, Hwan Heo, Seungryong Kim^*, Jiyoung Lee^* , and Jin-Hwa Kim^*

   arXiv preprint arXiv:2304.04960, 2023

   Paper
5. Semi-parametric video-grounded text generation

   Sungdong Kim , Jin-Hwa Kim, Jiyoung Lee, and Minjoon Seo

   arXiv preprint arXiv:2301.11507, 2023

   Paper
6. Dense text-to-image generation with attention modulation

   Yunji Kim, Jiyoung Lee , Jin-Hwa Kim, Jung-Woo Ha, and Jun-Yan Zhu

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

   Code Demo Paper
7. Hierarchical visual primitive experts for compositional zero-shot learning

   Hanjae Kim, Jiyoung Lee , Seongheon Park, and Kwanghoon Sohn

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

   Code Paper
8. Three recipes for better 3d pseudo-gts of 3d human mesh estimation in the wild

   Gyeongsik Moon, Hongsuk Choi, Sanghyuk Chun, Jiyoung Lee, and Sangdoo Yun

   In IEEE/CVF International Conference on Computer Vision Pattern Recognition Workshops (CVPRW), 2023

   Project Paper
9. Dual-path adaptation from image to video transformers

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

   In IEEE/CVF International Conference on Computer Vision Pattern Recognition (CVPR), 2023

   Paper
10. Language-free training for zero-shot video grounding

    Dahye Kim, Jungin Park, Jiyoung Lee , Seongheon Park, and Kwanghoon Sohn

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

    Paper

2022

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

   Kwonyoung Kim, Jungin Park, Jiyoung Lee, Dongbo Min, and Kwanghoon Sohn

   In European Conference on Computer Vision (ECCV), 2022

   Paper
2. Causalcity: Complex simulations with agency for causal discovery and reasoning

   Daniel McDuff, Yale Song, Jiyoung Lee, Vibhav Vineet, Sai Vemprala, Nicholas Alexander Gyde, Hadi Salman, Shuang Ma, Kwanghoon Sohn, and Ashish Kapoor

   In Conference on Causal Learning and Reasoning, 2022

   Project Paper
3. Mutual information divergence: A unified metric for multimodal generative models

   Jin-Hwa Kim , Yunji Kim, Jiyoung Lee, Kang Min Yoo , and Sang-Woo Lee

   In Advances in Neural Information Processing Systems (NeurIPS), 2022

   Code Paper
4. Multi-domain unsupervised image-to-image translation with appearance adaptive convolution

   Somi Jeong, Jiyoung Lee, and Kwanghoon Sohn

   In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022

   Paper
5. Pin the memory: Learning to generalize semantic segmentation

   Jin Kim, Jiyoung Lee, Jungin Park, Dongbo Min, and Kwanghoon Sohn

   In IEEE/CVF International Conference on Computer Vision Pattern Recognition (CVPR), 2022

   Code Paper
6. Probabilistic representations for video contrastive learning

   Jungin Park, Jiyoung Lee , Ig-Jae Kim, and Kwanghoon Sohn

   In IEEE/CVF International Conference on Computer Vision Pattern Recognition (CVPR), 2022

   Paper

2021

1. Wide and Narrow: Video Prediction from Context and Motion

   Jaehoon Cho, Jiyoung Lee, Changjae Oh, Wonil Song, and Kwanghoon Sohn

   In British Machine Vision Conference (BMVC), 2021

   Paper
2. Self-balanced learning for domain generalization

   Jin Kim, Jiyoung Lee, Jungin Park, Dongbo Min, and Kwanghoon Sohn

   In IEEE international conference on image processing (ICIP), 2021

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

   Jungin Park, Jiyoung Lee, and Kwanghoon Sohn

   In IEEE/CVF International Conference on Computer Vision Pattern Recognition (CVPR), 2021

   Paper
4. Looking into your speech: Learning cross-modal affinity for audio-visual speech separation

   Jiyoung Lee^*, Soo-Whan Chung^* , Sunok Kim, Hong-Goo Kang^*, and Kwanghoon Sohn^*

   In IEEE/CVF International Conference on Computer Vision Pattern Recognition (CVPR), 2021

   Paper

2020

1. Multi-modal recurrent attention networks for facial expression recognition

   Jiyoung Lee , Sunok Kim, Seungryong Kim, and Kwanghoon Sohn

   IEEE Transactions on Image Processing, 2020

   Paper
2. Sumgraph: Video summarization via recursive graph modeling

   Jungin Park^*, Jiyoung Lee^* , Ig-Jae Kim, and Kwanghoon Sohn

   In European Conference on Computer Vision (ECCV), 2020

   Paper

2019

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

   Jungin Park, Jiyoung Lee, Sangryul Jeon, Seungryong Kim, and Kwanghoon Sohn

   In IEEE International conference on image processing (ICIP), 2019

   Paper
2. Video summarization by learning relationships between action and scene

   Jungin Park, Jiyoung Lee, Sangryul Jeon, and Kwanghoon Sohn

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

   3rd place Bib Paper

   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 = {IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
     year = {2019},
     paper = {https://openaccess.thecvf.com/content_ICCVW_2019/papers/CoView/Park_Video_Summarization_by_Learning_Relationships_between_Action_and_Scene_ICCVW_2019_paper.pdf},
   }

3. Context-aware emotion recognition networks

   Jiyoung Lee, Seungryong Kim , Sunok Kim, Jungin Park, and Kwanghoon Sohn^*

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

   Bib Project Paper

   @inproceedings{lee2019context,
     title = {Context-aware emotion recognition networks},
     author = {Lee, Jiyoung and Kim, Seungryong and Kim, Sunok and Park, Jungin and Sohn, Kwanghoon},
     booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
     year = {2019},
     paper = {https://arxiv.org/abs/1908.05913},
   }

2018

1. Audio-visual attention networks for emotion recognition

   Jiyoung Lee , Sunok Kim, Seungryong Kim, and Kwanghoon Sohn

   In Proceedings of the 2018 Workshop on Audio-Visual Scene Understanding for Immersive Multimedia, 2018
2. Learning to detect, associate, and recognize human actions and surrounding scenes in untrimmed videos

   Jungin Park, Sangryul Jeon, Seungryong Kim, Jiyoung Lee , Sunok Kim, and Kwanghoon Sohn

   In Proceedings of the 1st Workshop and Challenge on Comprehensive Video Understanding in the Wild, 2018
3. Spatiotemporal attention based deep neural networks for emotion recognition

   Jiyoung Lee , Sunok Kim, Seungryong Kiim, and Kwanghoon Sohn

   In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2018

   Paper

2017

1. Automatic 2d-to-3d conversion using multi-scale deep neural network

   Jiyoung Lee, Hyungjoo Jung , Youngjung Kim, and Kwanghoon Sohn

   In IEEE International Conference on Image Processing (ICIP), 2017