Scholarlink

<p>Micro-expressions, subtle facial movements revealing concealed emotions, are challenging to recognize due to their short duration, low intensity, and limited balanced datasets. This paper proposes an attention-enhanced multi-branch network (AMNet) with three core innovations to overcome these limitations in micro-expression recognition. First, an improved attention mechanism is designed to dynamically emphasize discriminative facial regions critical for identifying subtle expressions. Second, a spatiotemporal fusion module, built on the synergy of lightweight STSTNet and ConvLSTM, efficiently integrates spatial and temporal information for the comprehensive micro-expression dynamics modeling. Third, a hierarchical feature fusion strategy is implemented to progressively refine multi-branch features, ensuring the robust learning of micro-expression characteristics. Extensive experiments on CASME II, SAMM, SMIC, 3DB-composite and CAS(ME)<sup>3</sup> datasets demonstrate AMNet’s superiority over state-of-the-art approaches, with exceptional accuracy and generalization. The code is available at <a href="https://github.com/yilin-succeed/AMNET">https://github.com/yilin-succeed/AMNET</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AMNet: an attention-enhanced multi-branch network for micro-expression recognition

  • 期刊论文

  • 发表日期：

    2025年5月17日

查看全文
  • Shu Liu,
  • Yilin Huang,
  • Hongyun Yu,
  • Yan Xu

摘要

Micro-expressions, subtle facial movements revealing concealed emotions, are challenging to recognize due to their short duration, low intensity, and limited balanced datasets. This paper proposes an attention-enhanced multi-branch network (AMNet) with three core innovations to overcome these limitations in micro-expression recognition. First, an improved attention mechanism is designed to dynamically emphasize discriminative facial regions critical for identifying subtle expressions. Second, a spatiotemporal fusion module, built on the synergy of lightweight STSTNet and ConvLSTM, efficiently integrates spatial and temporal information for the comprehensive micro-expression dynamics modeling. Third, a hierarchical feature fusion strategy is implemented to progressively refine multi-branch features, ensuring the robust learning of micro-expression characteristics. Extensive experiments on CASME II, SAMM, SMIC, 3DB-composite and CAS(ME)3 datasets demonstrate AMNet’s superiority over state-of-the-art approaches, with exceptional accuracy and generalization. The code is available at https://github.com/yilin-succeed/AMNET.