EUVIMEDEUVIMED entdecken
Crossref

RF-REN: RGB-Frequency Relation Exploration Network for Micro-Expression Recognition

Jiateng Liu, Hengcan Shi, Yaonan Wang, Yuan Zong

IEEE Signal Processing Letters · 2025 · 32 · 4439-4443

DOI: 10.1109/lsp.2025.3630085 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2025. Verfasst von Jiateng Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Key R&D Project, National Natural Science Foundation of China, YESS Program by CAST.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Micro-expression recognition (MER) has drawn increasing attention in recent years due to its ability to reveal the true feelings people want to hide. The key challenge in MER is subtle motions, which are hard to capture but crucial for MER. Existing methods usually solve this problem by magnifying all motions in the whole face and temporal sequence. However, micro-expressions (MEs) only involve a few facial areas and several temporal snippets. The all-motion magnification in previous methods cannot precisely capture these local ME motion patterns, and can easily cause spatial as well as temporal distortions, which significantly decrease the MER accuracy. In this paper, we propose an RGB-Frequency Relation Exploration Network (RF-REN), which enhances the subtle motions in refined local ME cues by exploring spatial and temporal relations in both RGB and frequency domains. Specifically, we first decompose the ME video into RGB as well as frequency domains, and conduct temporal division according to different motion stages to cover various ME local patterns. Secondly, we construct an adaptive local-global relation exploration (LGRE) module to explore the local relation cues in the spatial appearance and temporal dynamics in both domains. Finally, we propose an RGB-Frequency routing strategy to fuse the RGB and frequency cues, aiming to aggregate spatial-temporal local-global information and enhance subtle motions for MER. Extensive experiments on three databases (CASME II, SAMM and SMIC) show that the proposed model outperforms other state-of-the-art methods.

Förderung

  • National Key R&D Project
  • National Natural Science Foundation of China
  • YESS Program by CAST
  • ASFC
  • Zhishan Young Scholar Program of Southeast University

Zitieren

APA

Liu, J., Shi, H., Wang, Y., & Zong, Y. (2025). RF-REN: RGB-Frequency Relation Exploration Network for Micro-Expression Recognition. IEEE Signal Processing Letters, 32, 4439-4443. https://doi.org/10.1109/lsp.2025.3630085

Vancouver

Liu J, Shi H, Wang Y, Zong Y. RF-REN: RGB-Frequency Relation Exploration Network for Micro-Expression Recognition. IEEE Signal Processing Letters. 2025;32:4439-4443. doi:10.1109/lsp.2025.3630085

BibTeX
@article{Liu2025,
  author = {Liu, Jiateng and Shi, Hengcan and Wang, Yaonan and Zong, Yuan},
  title = {RF-REN: RGB-Frequency Relation Exploration Network for Micro-Expression Recognition},
  journal = {IEEE Signal Processing Letters},
  year = {2025},
  volume = {32},
  pages = {4439--4443},
  doi = {10.1109/lsp.2025.3630085}
}
Kostenlos starten →