Scholarlink

<p>Dynamic facial expression recognition relies heavily on subtle facial muscle movements, posing significant challenges in computer vision. This paper introduces a multi-scale spatiotemporal network based on conditional random fields (MS-CRFNet) to interpret facial expressions using features from multiple scales. The residual network (ResNet) serves as the backbone feature extractor, constructing a multi-scale two-layer feature pyramid. The conditional random field layer (CRFLayer) exchanges and fuses extracted spatiotemporal information, while the multi-scale cross-fusion module (MCFuse) progressively fuses important information across scales in a top-down manner to obtain final output features. These features are then classified by a fully convolutional (FC) layer, resulting in the recognition of seven basic expression categories. Experimental evaluations on the DFEW and FERV39K databases demonstrate the robustness and effectiveness of the proposed network, achieving a weighted average recall (WAR) of 66.81% and an unweighted average recall (UAR) of 54.00% on DFEW, and a WAR of 46.83% and a UAR of 37.72% on FERV39K. These results indicate the network’s adaptability to real-world classification scenarios. The code is available at <a href="https://github.com/025HanZheng520/MS.git">https://github.com/025HanZheng520/MS.git</a>, and the DOI is <a href="https://doi.org/10.5281/zenodo.15068420">https://doi.org/10.5281/zenodo.15068420</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

Enhanced multi-Scale Dynamic Facial Expression Recognition via Conditional Random Fields

  • 期刊论文

  • 发表日期：

    2025年9月28日

查看全文
  • Meichen Xia,
  • Han Zheng,
  • Hong Peng,
  • Zhicai Liu,
  • Jun Guo,
  • Jiangchao Long

摘要

Dynamic facial expression recognition relies heavily on subtle facial muscle movements, posing significant challenges in computer vision. This paper introduces a multi-scale spatiotemporal network based on conditional random fields (MS-CRFNet) to interpret facial expressions using features from multiple scales. The residual network (ResNet) serves as the backbone feature extractor, constructing a multi-scale two-layer feature pyramid. The conditional random field layer (CRFLayer) exchanges and fuses extracted spatiotemporal information, while the multi-scale cross-fusion module (MCFuse) progressively fuses important information across scales in a top-down manner to obtain final output features. These features are then classified by a fully convolutional (FC) layer, resulting in the recognition of seven basic expression categories. Experimental evaluations on the DFEW and FERV39K databases demonstrate the robustness and effectiveness of the proposed network, achieving a weighted average recall (WAR) of 66.81% and an unweighted average recall (UAR) of 54.00% on DFEW, and a WAR of 46.83% and a UAR of 37.72% on FERV39K. These results indicate the network’s adaptability to real-world classification scenarios. The code is available at https://github.com/025HanZheng520/MS.git, and the DOI is https://doi.org/10.5281/zenodo.15068420.