Jong Hak Moon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jong Hak Moon has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Edward Choi
KAIST, Kim Jaechul Graduate School of AI, Daejeon, Republic of Korea
3 shared publications - Hyungyung Lee
Graduate School of AI, KAIST, Daejeon, South Korea
2 shared publications - Baek Hwan Cho
Department of Biomedical Informatics, CHA University School of Medicine, CHA University, Seongnam, Republic of Korea
1 shared publication - Chan Woong Jang
Department of Physical Medicine and Rehabilitation, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang, Korea
1 shared publication - Da Young Lee
Department of Digital Health, SAIHST, Sungkyunkwan University, Seoul 06351, South Korea
1 shared publication Edward Choi
1 shared publication
Latest Publications
- 25 September 2026
- Published by Springer Nature
- p. 163-173
Clinically-Grounded Hierarchical Classification for Consistent Chest X-Ray Interpretation
- 25 September 2026
- Published by Springer Nature
- p. 163-173
Clinically-Grounded Hierarchical Classification for Consistent Chest X-Ray Interpretation
- Open Access
- 1 January 2025
- Published by XMLink in Yonsei Medical Journal
- Vol. 66 (8) , 491-501
Deep Learning-Based Landmark Detection Model for Multiple Foot Deformity Classification: A Dual-Center Study
Lee SJ, et al. Yonsei Med J. 2025 May;66:e45. https://doi.org/10.3349/ymj.2024.0246
- 1 January 2025
- Published by XMLink in Yonsei Medical Journal
- Vol. 66 (8) , 491-501
Open AccessDeep Learning-Based Landmark Detection Model for Multiple Foot Deformity Classification: A Dual-Center Study
Lee SJ, et al. Yonsei Med J. 2025 May;66:e45. https://doi.org/10.3349/ymj.2024.0246
- Open Access
Correlation between Alignment-Uniformity and Performance of Dense Contrastive Representations
Recently, dense contrastive learning has shown superior performance on dense prediction tasks compared to instance-level contrastive learning. Despite its supremacy, the properties of dense contrastive representations have not yet been carefully studied. Therefore, we analyze the theoretical ideas of dense contrastive learning using a standard CNN and straightforward feature matching scheme rather than propose a new complex method. Inspired by the analysis of the properties of instance-level contrastive representations through the lens of alignment and uniformity on the hypersphere, we employ and extend the same lens for the dense contrastive representations to analyze their underexplored properties. We discover the core principle in constructing a positive pair of dense features and empirically proved its validity. Also, we introduces a new scalar metric that summarizes the correlation between alignment-and-uniformity and downstream performance. Using this metric, we study various facets of densely learned contrastive representations such as how the correlation changes over single- and multi-object datasets or linear evaluation and dense prediction tasks. The source code is publicly available at: https://github.com/SuperSupermoon/DenseCL-analysis
Open AccessCorrelation between Alignment-Uniformity and Performance of Dense Contrastive Representations
Recently, dense contrastive learning has shown superior performance on dense prediction tasks compared to instance-level contrastive learning. Despite its supremacy, the properties of dense contrastive representations have not yet been carefully studied. Therefore, we analyze the theoretical ideas of dense contrastive learning using a standard CNN and straightforward feature matching scheme rather than propose a new complex method. Inspired by the analysis of the properties of instance-level contrastive representations through the lens of alignment and uniformity on the hypersphere, we employ and extend the same lens for the dense contrastive representations to analyze their underexplored properties. We discover the core principle in constructing a positive pair of dense features and empirically proved its validity. Also, we introduces a new scalar metric that summarizes the correlation between alignment-and-uniformity and downstream performance. Using this metric, we study various facets of densely learned contrastive representations such as how the correlation changes over single- and multi-object datasets or linear evaluation and dense prediction tasks. The source code is publicly available at: https://github.com/SuperSupermoon/DenseCL-analysis
- Top Cited Papers
- 19 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (12) , 6070-6080
Multi-Modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training
Recently a number of studies demonstrated impressive performance on diverse vision-language multi-modal tasks such as image captioning and visual question answering by extending the BERT architecture with multi-modal pre-training objectives. In this work we explore a broad set of multi-modal representation learning tasks in the medical domain, specifically using radiology images and the unstructured report. We propose Medical Vision Language Learner (MedViLL), which adopts a BERT-based architecture combined with a novel multi-modal attention masking scheme to maximize generalization performance for both vision-language understanding tasks (diagnosis classification, medical image-report retrieval, medical visual question answering) and vision-language generation task (radiology report generation). By statistically and rigorously evaluating the proposed model on four downstream tasks with three radiographic image-report datasets (MIMIC-CXR, Open-I, and VQA-RAD), we empirically demonstrate the superior downstream task performance of MedViLL against various baselines, including task-specific architectures. The source code is publicly available at: https://github.com/SuperSupermoon/MedViLL
- 19 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (12) , 6070-6080
Top Cited PapersMulti-Modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training
Recently a number of studies demonstrated impressive performance on diverse vision-language multi-modal tasks such as image captioning and visual question answering by extending the BERT architecture with multi-modal pre-training objectives. In this work we explore a broad set of multi-modal representation learning tasks in the medical domain, specifically using radiology images and the unstructured report. We propose Medical Vision Language Learner (MedViLL), which adopts a BERT-based architecture combined with a novel multi-modal attention masking scheme to maximize generalization performance for both vision-language understanding tasks (diagnosis classification, medical image-report retrieval, medical visual question answering) and vision-language generation task (radiology report generation). By statistically and rigorously evaluating the proposed model on four downstream tasks with three radiographic image-report datasets (MIMIC-CXR, Open-I, and VQA-RAD), we empirically demonstrate the superior downstream task performance of MedViLL against various baselines, including task-specific architectures. The source code is publicly available at: https://github.com/SuperSupermoon/MedViLL
- Open Access
- 29 June 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training: Development of Deep Learning Algorithm Study (Preprint)
BACKGROUND Recently a number of studies demonstrated impressive performance on diverse vision-language multi-modal tasks such as image captioning and visual question answering by extending the self-attention based Transformer architecture with multi-modal pre-training objectives. Despite its huge potential, vision-language multi-modal pre-training in the medical domain has only recently received attention, only demonstrated improved diagnosis accuracy of vision-language pre-trained models. OBJECTIVE In this work we explore a broad set of multi-modal representation learning tasks in the medical domain, specifically using radiology images and the unstructured report. METHODS We propose Medical Vision Language Learner (MedViLL) which adopts a Transformer-based architecture combined with a novel multi-modal attention masking scheme to maximize generalization performance for both vision-language understanding tasks (disease classification, medical image-report retrieval, and medical visual question answering) and vision-language generation task (radiology report generation). RESULTS By rigorously evaluating the proposed model on four downstream tasks with three radiographic image-text datasets (MIMIC-CXR, Open-I, and VQA-RAD), we empirically demonstrate the superior downstream task performance and generality of MedViLL against various baselines including task-specific architectures. In addition, we qualitatively analyze MedViLL by showing the results of retrieved image-report pair, the attention map visualization, and generated reports. CONCLUSIONS Our proposed multi-modal pre-training model MedViLL could flexibly adapt to multiple downstream tasks of vision-language understanding and generation with a novel self-attention scheme. We believe that our approach can provide the basis for a wide range of interpretations of vision-language multi-modal in the medical domain.
- 29 June 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessMulti-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training: Development of Deep Learning Algorithm Study (Preprint)
BACKGROUND Recently a number of studies demonstrated impressive performance on diverse vision-language multi-modal tasks such as image captioning and visual question answering by extending the self-attention based Transformer architecture with multi-modal pre-training objectives. Despite its huge potential, vision-language multi-modal pre-training in the medical domain has only recently received attention, only demonstrated improved diagnosis accuracy of vision-language pre-trained models. OBJECTIVE In this work we explore a broad set of multi-modal representation learning tasks in the medical domain, specifically using radiology images and the unstructured report. METHODS We propose Medical Vision Language Learner (MedViLL) which adopts a Transformer-based architecture combined with a novel multi-modal attention masking scheme to maximize generalization performance for both vision-language understanding tasks (disease classification, medical image-report retrieval, and medical visual question answering) and vision-language generation task (radiology report generation). RESULTS By rigorously evaluating the proposed model on four downstream tasks with three radiographic image-text datasets (MIMIC-CXR, Open-I, and VQA-RAD), we empirically demonstrate the superior downstream task performance and generality of MedViLL against various baselines including task-specific architectures. In addition, we qualitatively analyze MedViLL by showing the results of retrieved image-report pair, the attention map visualization, and generated reports. CONCLUSIONS Our proposed multi-modal pre-training model MedViLL could flexibly adapt to multiple downstream tasks of vision-language understanding and generation with a novel self-attention scheme. We believe that our approach can provide the basis for a wide range of interpretations of vision-language multi-modal in the medical domain.
- Open Access
- 1 January 2021
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 198, 105819
Automatic stenosis recognition from coronary angiography using convolutional neural networks
- 1 January 2021
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 198, 105819
Open AccessAutomatic stenosis recognition from coronary angiography using convolutional neural networks