The paper introduces TAME, a Text‑Anchored Modality Experts framework that treats language as a fixed, always‑active expert and routes audio‑textual and video‑textual cross‑modal branches as dynamic auxiliary experts. It incorporates lightweight Prophet Heads to estimate sample‑level uncertainty for each modality, guiding a reliability‑aware routing mechanism for expert aggregation. Experiments on CMU‑MOSI, CMU‑MOSEI, and CH‑SIMS show that TAME achieves state‑of‑the‑art performance while reducing parameters by up to 78.7% and FLOPs by up to 41.2% compared to a mixture‑of‑experts baseline.
arXiv:2607. 10599v1 Announce Type: new Abstract: Multimodal sentiment analysis relies on language, visual, and acoustic cues, but utterance-level modality quality may vary due to occlusion, background noise, motion blur, or imperfect transcripts, causing conventional fusion to over-trust unreliable modalities.
Reliability-aware Cross-sample Enhancement (RCE) is a framework for multimodal sentiment analysis that tackles noise and missing modalities by first applying an adaptive variational information bottleneck to compress unreliable modality information. It then retrieves high‑confidence, semantically consistent neighbors from a large candidate pool to enrich current representations, and finally fuses cross‑modal interactions through a multilevel reliability‑aware mechanism. Experiments show RCE consistently outperforms state‑of‑the‑art methods in full, noisy, and missing‑modality scenarios.
The paper proposes a Mixture-of-Bottleneck (MoB) framework for video-based multimodal sentiment analysis that treats sentiment as an ordinal regression problem, splitting it into polarity recognition and intensity prediction. MoB assigns modality‑specific latent experts to each sub‑task, learns compact, task‑relevant representations via an information bottleneck, and fuses these experts with a multimodal bottleneck routing module and hard mining strategy. Experiments on four datasets and language models demonstrate that MoB captures fine‑grained intra‑ and inter‑modal dynamics, improving performance and enabling more trustworthy localization of nuanced sentiment signals.
arXiv:2608.30726v1 Announce Type: new Abstract: Multimodal Sentiment Analysis (MSA) is a fundamental component of affective computing that aims to decipher complex emotional states by integrating ver...
arXiv:2610.31731v1 Announce Type: new Abstract: Multimodal sentiment analysis (MSA) aims to predict human sentiments by integrating signals from different modalities such as text, video, and audio. H...
arXiv:2608. 03611v1 Announce Type: new Abstract: Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete.
arXiv:2610.20543v1 Announce Type: new Abstract: Multimodal sentiment models are usually evaluated on complete utterances, yet streams often lose a contiguous span of text, audio, or video. We study l...
ReH-FUSE is a reliability‑aware hierarchical fusion framework for multimodal emotion recognition in conversation. It uses a decision‑level router to first compare the relative preference between text and audio, then balances this unimodal mixture with a cross‑modal expert, thereby separating unimodal competition from cross‑modal selection. Experiments on IEMOCAP and MELD show that ReH-FUSE achieves state‑of‑the‑art weighted and macro F1 scores, and ablation studies confirm that learned routing outperforms uniform expert averaging and benefits from cross‑modal interaction.
The paper introduces Uncertainty‑Guided Multimodal Consensus (UMC) for multimodal sentiment analysis. UMC first recovers continuous unimodal pseudo‑labels using Continuous Prototype‑Guided Label Recovery (CPLR), which blends heteroscedastic predictions with ordered sentiment prototypes and refines them with confidence and label conflict. It then forms a reliability‑aware consensus across modalities via Reliability and Precision Consensus (RPC), which estimates sample‑dependent modality reliability from predictive statistics and cross‑modal disagreement and combines it with predictive precision through a closed‑form solver. Experiments on four public MSA datasets show that UMC outperforms existing methods.
arXiv:2606. 02679v1 Announce Type: new Abstract: Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed.
arXiv:2606. 15694v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in understanding complex multimodal content.
arXiv:2601. 07565v2 Announce Type: replace-cross Abstract: Multimodal emotion understanding requires the integration of heterogeneous data sources, including text, audio, and visual modalities, while simultaneously addressing discrete emotion recognition and continuous sentiment analysis.