Navigating the Emotion Tree: Hierarchical Hyperbolic RAG for Multimodal 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_ | 1866911696081125376 |
|---|---|
| author | Wang, Zeheng Zhao, Bo Zhu, Yijie Liu, Zhishu Ma, Hui Zhang, Ruixin Ding, Shouhong Xie, Qianyu Yu, Zitong |
| author_facet | Wang, Zeheng Zhao, Bo Zhu, Yijie Liu, Zhishu Ma, Hui Zhang, Ruixin Ding, Shouhong Xie, Qianyu Yu, Zitong |
| contents | Multimodal emotion recognition aims to integrate text, audio, and video sources to understand human affective states. Although multimodal large language models excel at multimodal reasoning, they typically treat emotion categories as independent labels, ignoring the rich hierarchical taxonomy of human psychology. Moreover, lacking external contextual knowledge makes them highly susceptible to over-interpreting noisy cues, further complicating fine-grained emotion classification. To address these issues, we propose \textbf{HyperEmo-RAG}, a retrieval-augmented generation framework that leverages a structured emotional knowledge base. Our framework introduces two key innovations. 1) Hierarchical hyperbolic grounding. Recognizing the inherent hierarchical tree structure of emotion taxonomies, we jointly embed hierarchical emotion labels and multimodal samples into a continuous hyperbolic space (Poincaré ball) and design a hierarchical beam-search deliberation process that progressively retrieves samples from coarse to fine-grained levels. 2) Structured evidence injection. Based on the retrieved evidence, we construct an evidence graph and inject the structured knowledge as explicit cognitive context into the LLM through a Tree-Aware Attention mechanism and an EmotionGraphFormer, preserving the integrity of graph-structured information. Experiments on multiple datasets demonstrate that HyperEmo-RAG significantly outperforms existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18884 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Navigating the Emotion Tree: Hierarchical Hyperbolic RAG for Multimodal Emotion Recognition Wang, Zeheng Zhao, Bo Zhu, Yijie Liu, Zhishu Ma, Hui Zhang, Ruixin Ding, Shouhong Xie, Qianyu Yu, Zitong Machine Learning Computer Vision and Pattern Recognition Multimodal emotion recognition aims to integrate text, audio, and video sources to understand human affective states. Although multimodal large language models excel at multimodal reasoning, they typically treat emotion categories as independent labels, ignoring the rich hierarchical taxonomy of human psychology. Moreover, lacking external contextual knowledge makes them highly susceptible to over-interpreting noisy cues, further complicating fine-grained emotion classification. To address these issues, we propose \textbf{HyperEmo-RAG}, a retrieval-augmented generation framework that leverages a structured emotional knowledge base. Our framework introduces two key innovations. 1) Hierarchical hyperbolic grounding. Recognizing the inherent hierarchical tree structure of emotion taxonomies, we jointly embed hierarchical emotion labels and multimodal samples into a continuous hyperbolic space (Poincaré ball) and design a hierarchical beam-search deliberation process that progressively retrieves samples from coarse to fine-grained levels. 2) Structured evidence injection. Based on the retrieved evidence, we construct an evidence graph and inject the structured knowledge as explicit cognitive context into the LLM through a Tree-Aware Attention mechanism and an EmotionGraphFormer, preserving the integrity of graph-structured information. Experiments on multiple datasets demonstrate that HyperEmo-RAG significantly outperforms existing methods. |
| title | Navigating the Emotion Tree: Hierarchical Hyperbolic RAG for Multimodal Emotion Recognition |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.18884 |