Metraipolis › archive › dc_b69a73ebaf8b

ReH-FUSE: Reliability-Aware Hierarchical Fusion of Experts for Multimodal Emotion Recognition in Conversation — arXiv:2609.13857

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13857
License (as archived)
CC0-1.0
Archived
2026-10-16T00:10:30.913Z
SHA-256 of the archived text
6dc8decffc75a347cb497b45c7b55248729685ecb63c3c4a862ff9a309bd8421
Stable URL of this page
https://metraipolis.com/documento/dc_b69a73ebaf8b

How to cite

ReH-FUSE: Reliability-Aware Hierarchical Fusion of Experts for Multimodal Emotion Recognition in Conversation — arXiv:2609.13857 — arXiv (en), https://arxiv.org/abs/2609.13857 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b69a73ebaf8b (Metraipolis archive dc_b69a73ebaf8b, sha256 6dc8decffc75a347cb497b45c7b55248729685ecb63c3c4a862ff9a309bd8421)
BibTeX
@misc{dcb69a73ebaf8b,
  title = {ReH-FUSE: Reliability-Aware Hierarchical Fusion of Experts for Multimodal Emotion Recognition in Conversation — arXiv:2609.13857},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13857},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b69a73ebaf8b; sha256 6dc8decffc75a347cb497b45c7b55248729685ecb63c3c4a862ff9a309bd8421},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13857. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal emotion recognition in conversation (ERC) requires adapting to the instance-dependent reliability of different evidence sources. Lexical content may be decisive, vocal expression may provide complementary cues, or accurate recognition may require cross-modal interaction; fixed fusion does not explicitly account for this variation. We propose ReH-FUSE, a reliability-aware framework with dialogue-aware text, audio, and cross-modal experts. Its decision-level router first models the relative preference between text and audio and then balances the resulting unimodal mixture against the cross-modal expert. This factorization separates unimodal competition from cross-modal selection. Across three independent runs on IEMOCAP, ReH-FUSE achieves 74.34% weighted F1 and 73.11% macro F1; on MELD, it achieves 68.03% weighted F1. Controlled ablations show that learned routing outperforms uniform expert averaging and benefits from cross-modal interaction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.13857 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T23:54:14.645Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).