HADUA: Hierarchical Attention and Dynamic Uniform Alignment for Robust Cross-Subject Emotion Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917231360737280 |
|---|---|
| author | Tang, Jiahao Li, Youjun Zheng, Yangxuan Fan, Xiangting Lu, Siyuan Zhang, Nuo Huang, Zi-Gang |
| author_facet | Tang, Jiahao Li, Youjun Zheng, Yangxuan Fan, Xiangting Lu, Siyuan Zhang, Nuo Huang, Zi-Gang |
| contents | Robust cross-subject emotion recognition from multimodal physiological signals remains a challenging problem, primarily due to modality heterogeneity and inter-subject distribution shift. To tackle these challenges, we propose a novel adaptive learning framework named Hierarchical Attention and Dynamic Uniform Alignment (HADUA). Our approach unifies the learning of multimodal representations with domain adaptation. First, we design a hierarchical attention module that explicitly models intra-modal temporal dynamics and inter-modal semantic interactions (e.g., between electroencephalogram(EEG) and eye movement(EM)), yielding discriminative and semantically coherent fused features. Second, to overcome the noise inherent in pseudo-labels during adaptation, we introduce a confidence-aware Gaussian weighting scheme that smooths the supervision from target-domain samples by down-weighting uncertain instances. Third, a uniform alignment loss is employed to regularize the distribution of pseudo-labels across classes, thereby mitigating imbalance and stabilizing conditional distribution matching. Extensive experiments on multiple cross-subject emotion recognition benchmarks show that HADUA consistently surpasses existing state-of-the-art methods in both accuracy and robustness, validating its effectiveness in handling modality gaps, noisy pseudo-labels, and class imbalance. Taken together, these contributions offer a practical and generalizable solution for building robust cross-subject affective computing systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21488 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HADUA: Hierarchical Attention and Dynamic Uniform Alignment for Robust Cross-Subject Emotion Recognition Tang, Jiahao Li, Youjun Zheng, Yangxuan Fan, Xiangting Lu, Siyuan Zhang, Nuo Huang, Zi-Gang Multimedia Robust cross-subject emotion recognition from multimodal physiological signals remains a challenging problem, primarily due to modality heterogeneity and inter-subject distribution shift. To tackle these challenges, we propose a novel adaptive learning framework named Hierarchical Attention and Dynamic Uniform Alignment (HADUA). Our approach unifies the learning of multimodal representations with domain adaptation. First, we design a hierarchical attention module that explicitly models intra-modal temporal dynamics and inter-modal semantic interactions (e.g., between electroencephalogram(EEG) and eye movement(EM)), yielding discriminative and semantically coherent fused features. Second, to overcome the noise inherent in pseudo-labels during adaptation, we introduce a confidence-aware Gaussian weighting scheme that smooths the supervision from target-domain samples by down-weighting uncertain instances. Third, a uniform alignment loss is employed to regularize the distribution of pseudo-labels across classes, thereby mitigating imbalance and stabilizing conditional distribution matching. Extensive experiments on multiple cross-subject emotion recognition benchmarks show that HADUA consistently surpasses existing state-of-the-art methods in both accuracy and robustness, validating its effectiveness in handling modality gaps, noisy pseudo-labels, and class imbalance. Taken together, these contributions offer a practical and generalizable solution for building robust cross-subject affective computing systems. |
| title | HADUA: Hierarchical Attention and Dynamic Uniform Alignment for Robust Cross-Subject Emotion Recognition |
| topic | Multimedia |
| url | https://arxiv.org/abs/2601.21488 |