Jiho Lee
Research Subjects
Jiho Lee has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Dongjin Lee
Pohang University of Science and Technology (POSTECH), Pohang 37673, Republic of Korea
1 shared publication - Eon-Suk Ko
Department of English Language and Literature, Chosun University, Gwangju, South Korea
1 shared publication - Jae-Hun Jung
Pohang University of Science and Technology (POSTECH), Pohang 37673, Republic of Korea
1 shared publication - Rajalakshmi Madhavan
Chosun University 1
1 shared publication
Latest Publications
- Open Access
- 9 March 2026
- Published by Elsevier in SSRN Electronic Journal
Cross-Domain Evaluation and Fine-Tuned Adaptation of iCatcher+ for Korean Infant Gaze Data
This study evaluates the cross-domain generalisability of three iCatcher+ gaze classification models on a dataset of Korean infants. Applying the pretrained models to the Korean dataset resulted in a substantial decline in accuracy across all models. Performance was systematically modulated by developmental mismatch: accuracy declined as the age distribution of the target dataset diverged from that of the training data. In contrast, experiment-level factors such as stimulus type and temporal progression had limited effects. Fine-tuning the Lookit model on Korean data improved target-domain performance, but at the cost of reduced accuracy on the original source dataset, consistent with catastrophic forgetting. Our findings highlight that deep learning-based gaze classifiers remain sensitive to domain shift. Although fine-tuning can partially mitigate performance loss, robust generalisation requires closer alignment between training and deployment contexts.
- 9 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCross-Domain Evaluation and Fine-Tuned Adaptation of iCatcher+ for Korean Infant Gaze Data
This study evaluates the cross-domain generalisability of three iCatcher+ gaze classification models on a dataset of Korean infants. Applying the pretrained models to the Korean dataset resulted in a substantial decline in accuracy across all models. Performance was systematically modulated by developmental mismatch: accuracy declined as the age distribution of the target dataset diverged from that of the training data. In contrast, experiment-level factors such as stimulus type and temporal progression had limited effects. Fine-tuning the Lookit model on Korean data improved target-domain performance, but at the cost of reduced accuracy on the original source dataset, consistent with catastrophic forgetting. Our findings highlight that deep learning-based gaze classifiers remain sensitive to domain shift. Although fine-tuning can partially mitigate performance loss, robust generalisation requires closer alignment between training and deployment contexts.