Scholarlink

<p>Facial expression recognition (FER) remains a challenging problem in computer vision due to variations in illumination, pose, and occlusion under complex real-world conditions. To address these issues, this paper presents a Multiscale and Permute Attention Network (MPA-Net) that jointly models global, local, and salient features for robust emotion recognition. Specifically, a pre-extraction block captures low-level visual patterns, while a multiscale block enhances feature representation by integrating information from multiple receptive fields, improving robustness to occlusion and pose changes. Furthermore, a space-wise split block enables the network to emphasize discriminative local regions, and a permute attention mechanism establishes interactions among channel, spatial, and height dimensions to achieve comprehensive feature fusion. Extensive experiments on three benchmark datasets-FER2013, RAF-DB, and AffectNet-demonstrate that MPA-Net achieves competitive performance (72.28%, 87.39%, and 57.07%, respectively) without relying on pretraining, validating its effectiveness and robustness in real-world FER scenarios.</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

MPA-Net: a multiscale and permute attention network for occlusion and pose robust facial expression recognition in the wild

  • 期刊论文

  • 发表日期：

    2026年7月3日

查看全文
  • Huang Shui Hu,
  • Yu Cao,
  • Fu Jun Wang,
  • Xing Shuo Qi

摘要

Facial expression recognition (FER) remains a challenging problem in computer vision due to variations in illumination, pose, and occlusion under complex real-world conditions. To address these issues, this paper presents a Multiscale and Permute Attention Network (MPA-Net) that jointly models global, local, and salient features for robust emotion recognition. Specifically, a pre-extraction block captures low-level visual patterns, while a multiscale block enhances feature representation by integrating information from multiple receptive fields, improving robustness to occlusion and pose changes. Furthermore, a space-wise split block enables the network to emphasize discriminative local regions, and a permute attention mechanism establishes interactions among channel, spatial, and height dimensions to achieve comprehensive feature fusion. Extensive experiments on three benchmark datasets-FER2013, RAF-DB, and AffectNet-demonstrate that MPA-Net achieves competitive performance (72.28%, 87.39%, and 57.07%, respectively) without relying on pretraining, validating its effectiveness and robustness in real-world FER scenarios.