A-Seong Moon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
A-Seong Moon has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Jaesung Lee
Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea
5 shared publications - Bong-Soo Sohn
Department of Computer Science, Chung-Ang University, Seoul, South Korea
1 shared publication Dahyun Song
Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea
1 shared publication- Hyeonji Moon
Department of Biology, Sungshin Women's University, Seoul 01133, Korea
1 shared publication - Jeongwon Lee
Department of Artificial Intelligence, Chung-Ang University, Seoul 06974, Republic of Korea
1 shared publication - Kunho Lee
Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea
1 shared publication
Latest Publications
- 22 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
Effective audio-visual event localization using CLIP-based global context regulation for mitigating event overconfidence
- 22 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
Effective audio-visual event localization using CLIP-based global context regulation for mitigating event overconfidence
- Open Access
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 13783-13797
Effective Encoder-Decoder Network for Multiple Multi-Scale Jagged Masks in Vehicle Damage Segmentation
The segmentation of damaged areas in vehicle images is essential for practical applications such as automated insurance processing, vehicle resale evaluation, and maintenance support. Damage patterns often appear in different forms and sizes, and exhibit irregular shapes, which makes consistent segmentation difficult. These characteristics tend to occur simultaneously in real-world environments, resulting in conditions referred to as multiple multi-scale jagged masks. To address this problem, this study designed a model to separate overlapping regions, extract features across multiple spatial resolutions, and enhance uncertain boundaries through attention-guided refinement. The proposed model was evaluated on a large-scale public dataset of annotated vehicle surface damage images using four standard metrics: intersection over union, F1-Score, precision, and recall. Comparative experiments with damage-specific and general-purpose segmentation models revealed that the proposed model achieved the highest performance across all metrics and maintained stability across repeated trials.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 13783-13797
Open AccessEffective Encoder-Decoder Network for Multiple Multi-Scale Jagged Masks in Vehicle Damage Segmentation
The segmentation of damaged areas in vehicle images is essential for practical applications such as automated insurance processing, vehicle resale evaluation, and maintenance support. Damage patterns often appear in different forms and sizes, and exhibit irregular shapes, which makes consistent segmentation difficult. These characteristics tend to occur simultaneously in real-world environments, resulting in conditions referred to as multiple multi-scale jagged masks. To address this problem, this study designed a model to separate overlapping regions, extract features across multiple spatial resolutions, and enhance uncertain boundaries through attention-guided refinement. The proposed model was evaluated on a large-scale public dataset of annotated vehicle surface damage images using four standard metrics: intersection over union, F1-Score, precision, and recall. Comparative experiments with damage-specific and general-purpose segmentation models revealed that the proposed model achieved the highest performance across all metrics and maintained stability across repeated trials.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 1
Effective Mel-Spectrogram Synthesis for Multi-Speaker Text-to-Speech with Band-Specific Acoustic Modeling
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 1
Open AccessEffective Mel-Spectrogram Synthesis for Multi-Speaker Text-to-Speech with Band-Specific Acoustic Modeling
- 23 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
A survey of neural network segmentation and validation on plant specimen images of Korean Violaceae
- 23 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
A survey of neural network segmentation and validation on plant specimen images of Korean Violaceae
- Open Access
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 114595-114607
Survey on 3D Anomaly Detection Regarding Defect Size: Tradeoff Between Accuracy and Efficiency With Future Research Direction
Recent advancements in neural networks has enhanced image anomaly detection in different industries such as manufacturing, reduced human intervention, and boosted productivity and quality. However, there are still some challenges in using point cloud and RGB data for anomaly detection across varying defect sizes. This study explores such challenges and and highlights the importance of high-quality data for effective training. It also highlights the trade-off between detection accuracy and inference speed, where faster models tend to sacrifice performance on smaller defects due to the use of general loss functions that do not sufficiently capture fine-grained anomalies. This work suggests that future research should focus on improving the models that efficiently detect small defects while ensuring high-speed inference and bridging the gap between accuracy and efficiency for real-world industrial applications.
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 114595-114607
Open AccessSurvey on 3D Anomaly Detection Regarding Defect Size: Tradeoff Between Accuracy and Efficiency With Future Research Direction
Recent advancements in neural networks has enhanced image anomaly detection in different industries such as manufacturing, reduced human intervention, and boosted productivity and quality. However, there are still some challenges in using point cloud and RGB data for anomaly detection across varying defect sizes. This study explores such challenges and and highlights the importance of high-quality data for effective training. It also highlights the trade-off between detection accuracy and inference speed, where faster models tend to sacrifice performance on smaller defects due to the use of general loss functions that do not sufficiently capture fine-grained anomalies. This work suggests that future research should focus on improving the models that efficiently detect small defects while ensuring high-speed inference and bridging the gap between accuracy and efficiency for real-world industrial applications.