arXiv：cs.AI· Chunlei Meng, Jacqueline J. Pang, Pengbin Feng, Zhenyu Yu, Chun Ouyang, Zhongxue Gan·· 6 小时前AI 评分28
重新思考不完整观测下多模态情感分析的模态可靠性：MRCF 框架
Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations
AI 导读
针对不完整观测下的多模态情感分析，研究者提出 MRCF（Modality Reliability-Calibrated Framework），显式建模模态可靠性。该框架包含可靠性感知分支、可靠性引导交互分支与可靠性校准融合模块，用于缓解可靠性失配与可靠性传播偏差。在 CMU-MOSI、CMU-MOSEI 和 CH-SIMS 上，MRCF 在标准不完整观测协议下取得强劲表现。
正文
Abstract:Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete. Existing methods for incomplete-observation MSA mainly follow two paradigms. Reconstruction-based methods recover missing information from observed modalities, while joint-representation methods learn directly from incomplete inputs. Although effective, these methods usually treat modality reliability only implicitly within representation learning or fusion design rather than modeling it explicitly. We argue that modality reliability is a central variable in incomplete-observation settings. Failure to model it explicitly gives rise to two related issues. The first is reliability mismatch, in which the affective evidence retained by each modality varies across samples and missing rates. The second is reliability propagation bias, in which messages from degraded modalities may adversely affect cross-modal interaction and predictive performance. To address these issues, we propose MRCF, a Modality Reliability-Calibrated Framework for MSA with incomplete observations. MRCF contains a Reliability-Aware Branch that estimates sample-specific modality reliability from intramodal quality cues and cross-modal semantic consistency, a Reliability-Guided Interaction Branch that uses the estimated scores to modulate cross-modal information flow, and a Reliability-Calibrated Fusion Module that integrates reliability and semantic cues for final prediction. Experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS show that MRCF achieves strong performance under standard incomplete-observation protocols. Further analyses provide evidence that explicit reliability modeling helps mitigate reliability mismatch and reliability propagation bias during interaction and fusion.
| Subjects: | Artificial Intelligence (cs.AI); Multimedia (cs.MM) |
| Cite as: | arXiv:2608.03611 [cs.AI] |
| (or arXiv:2608.03611v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.03611 arXiv-issued DOI via DataCite |
Submission history
From: Chunlei Meng [view email]
[v1]
Tue, 4 Aug 2026 13:02:48 UTC (3,331 KB)
[v2]
Thu, 27 Aug 2026 11:17:58 UTC (3,332 KB)
[v3]
Tue, 6 Oct 2026 07:00:00 UTC (3,332 KB)
来源：arXiv：cs.AI · arxiv.org