Metraipolis › archive › dc_d8dfa4e43e29

Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition — arXiv:2608.03475

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03475
License (as archived)
CC0-1.0
Archived
2026-10-31T12:19:23.508Z
SHA-256 of the archived text
63ca792c613b5db425f253956b426eee54f0dcfdf801dbcccf22b98f4c6025d3
Stable URL of this page
https://metraipolis.com/documento/dc_d8dfa4e43e29

How to cite

Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition — arXiv:2608.03475 — arXiv (en), https://arxiv.org/abs/2608.03475 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8dfa4e43e29 (Metraipolis archive dc_d8dfa4e43e29, sha256 63ca792c613b5db425f253956b426eee54f0dcfdf801dbcccf22b98f4c6025d3)
BibTeX
@misc{dcd8dfa4e43e29,
  title = {Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition — arXiv:2608.03475},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03475},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8dfa4e43e29; sha256 63ca792c613b5db425f253956b426eee54f0dcfdf801dbcccf22b98f4c6025d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03475. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal intent recognition combines linguistic, acoustic, and visual evidence, but individual modalities may be noisy, missing, semantically conflicting, or disproportionately dominant. Existing methods typically infer modality importance implicitly and either reweight or suppress unreliable inputs, without determining whether a degraded modality can be repaired and subsequently trusted. We propose PRIME (Precision-weighted Reliability Inference and Modality rEstoration), a closed-loop reliability guided framework that jointly diagnoses, restores, and reassesses modality quality at the sample level. PRIME represents the weakness of each modality through a contextual log-variance estimated from complementary diagnostic evidence, including predictive confidence, epistemic disagreement, cross-modal consensus, and feature degeneracy. Because modality-reliability annotations are unavailable, the estimator is explicitly trained using controlled modality corruption with known degradation severity, together with a heteroscedastic uncertainty objective. Rather than directly discarding an unreliable modality, PRIME uses its estimated weakness to control a prototype-conditioned variational restoration module that reconstructs the degraded representation from complementary modalities. Crucially, reliability is re-estimated after restoration, allowing the model to determine whether the repaired representation has become sufficiently trustworthy to contribute to prediction. The resulting post-restoration precisions are used for inverse-variance multimodal fusion. Experiments on multimodal intent-recognition benchmarks show that PRIME maintains competitive clean-data performance while improving robustness under missing, noisy, conflicting, and modality-imbalanced conditions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Multimedia (cs.MM) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.03475 — 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 2026-10-31T12:05:53.048Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).