ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Enhancing Dimensional Image Emotion Detection With a Low-Resource Dataset via Two-Stage Training
Cited 1 time in scopus Share share facebook twitter linkedin kakaostory
Authors
SangEun Lee, Seoyun Kim, Yubeen Lee, Jufeng Yang, Eunil Park
Issue Date
2025-06
Citation
IEEE Transactions on Cognitive and Developmental Systems, v.17, no.3, pp.455-464
ISSN
2379-8920
Publisher
IEEE
Language
English
Type
Journal Article
DOI
https://dx.doi.org/10.1109/TCDS.2024.3465602
Abstract
Image emotion analysis has gained notable attention owing to the growing importance of computationally modeling human emotions. Most previous studies have focused on classifying the feelings evoked by an image into predefined emotion categories. Compared with these categorical approaches which cannot address the ambiguity and complexity of human emotions, recent studies have taken dimensional approaches to address these problems. However, there is still a limitation in that the number of dimensional datasets is significantly smaller for model training, compared with many available categorical datasets. We propose four types of frameworks that use categorical datasets to predict emotion values for a given image in the valence–arousal (VA) space. Specifically, our proposed framework is trained to predict continuous emotion values under the supervision of categorical labels. Extensive experiments demonstrate that our approach showed a positive correlation with the actual VA values of the dimensional dataset. In addition, our framework improves further when a small number of dimensional datasets are available for the fine-tuning process.
KSP Keywords
Categorical datasets, Emotion analysis, Fine-tuning, Human emotions, Low-Resource, Positive correlation, Training image, Tuning process, Two-Stage, emotion detection