Learning emotional representations in oil paintings via knowledge distillation and multi-granularity semantic alignment
International Journal of Information and Communication Technology · 2026 · 27 (85) · 70-94
DOI: 10.1504/ijict.2026.155483 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Information and Communication Technology, 2026. Verfasst von Renjiao Wang.
Abstract (Originalsprache)
Oil painting emotion recognition faces two challenges: the excessive number of model parameters makes deployment difficult, and the granularity of emotion semantic understanding is coarse.To address this issue, this paper proposes a lightweight representation learning method that integrates knowledge distillation and multi-granularity semantic alignment.The teacher network guides the lightweight student network to learn, and performs feature alignment at two granularities: global image semantics and local emotional attributes, enabling the compact model to accurately capture the subtle emotions in the paintings while maintaining efficiency.Experiments show that, with 84.7% reduction in parameters, the classification accuracy only drops by 1.2%, and the normalised discounted cumulative gain for emotion intensity ranking reaches 0.893, significantly outperforming the lightweight baseline models of the same scale.This research provides a technical solution that balances efficiency and accuracy for the practical implementation of emotion computing in the field of digital humanities.
Zitieren
APA
Wang, R. (2026). Learning emotional representations in oil paintings via knowledge distillation and multi-granularity semantic alignment. International Journal of Information and Communication Technology, 27(85), 70-94. https://doi.org/10.1504/ijict.2026.155483
Vancouver
Wang R. Learning emotional representations in oil paintings via knowledge distillation and multi-granularity semantic alignment. International Journal of Information and Communication Technology. 2026;27(85):70-94. doi:10.1504/ijict.2026.155483
BibTeX
@article{Wang2026,
author = {Wang, Renjiao},
title = {Learning emotional representations in oil paintings via knowledge distillation and multi-granularity semantic alignment},
journal = {International Journal of Information and Communication Technology},
year = {2026},
volume = {27},
number = {85},
pages = {70--94},
doi = {10.1504/ijict.2026.155483}
}
EUVIMED