Scholar
Jinyoung Moon
Google Scholar ID: TzK33Q0AAAAJ
ETRI
Citations & Impact
Citations
718
H-index
13
i10-index
17
Publications
20
Co-authors
13
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published several papers in international journals covering topics such as online action detection, face recognition, license plate recognition, and more.
- - A paper on online action detection was published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
- - Work exploring the combination of language and video modalities for temporal moment localization appeared in Computer Vision and Image Understanding.
- - Other research achievements include works on image super-resolution, improving efficiency in continual learning, etc.
- - Research results were also presented at international conferences, such as MPViT: Multi-Path Vision Transformer for Dense Prediction at CVPR.
Research Experience
- Involved in multiple phased research projects focusing on developing visual language technologies, memory storage networks, situational reasoning and cognition technologies, etc.
- - Phase 1 (3 years): Development of technology for expressing and retrieving visual information, and building a visual memory network for abstracting and storing visual information.
- - Phase 2 (3 years): Development of situational recognition and reasoning technologies based on long-term and short-term visual memories, improving understanding of relationships and situational cognition through contextual information fusion.
- - Phase 3 (2 years): Development of evidence-based predictive visual intelligence technology, using multi-modal meta-learning to predict future situations.
Background
- Research interests include but are not limited to: application of deep learning in visual intelligence technologies, cross-modal pre-training techniques, and edge AI-based visual intelligence solutions.
