DualScope is proposed, a novel model that combines a global-local fusion strategy with bidirectional image-text generation for semantically consistent data augmentation and introduces both label contrastive learning and data contrastive learning to align heterogeneous modalities and enhance model robustness.
Abstract
With the rise of social media, multimodal sentiment analysis has gained increasing attention due to the rich and diverse ways users express emotions through text and images. However, existing methods often ignore fine-grained sentiment cues and semantic misalignment across modalities, limiting this task effectiveness. To address these challenges, we propose DualScope, a novel model that combines a global-local fusion strategy with bidirectional image-text generation for semantically consistent data augmentation. Furthermore, we introduce both label contrastive learning and data contrastive learning to align heterogeneous modalities and enhance model robustness. The fusion module integrates global and local features in a progressive manner under global semantic guidance. Extensive experiments on two widely used datasets, MVSA-Single and MVSA-Multiple, demonstrate that the proposed method achieves superior performance, confirming its effectiveness in handling fine-grained semantics and cross-modal inconsistency.
A Modality Dropout strategy is first introduced at the input stage to alleviate over-reliance on a sin-gle modality and improve robustness and the proposed Hierarchical Global-Local Interaction and Refinement framework for Multimodal Sentiment Analysis (HGLIR) is proposed.
yuanyuan zhou· Poster Volume 0007 The 2026...· 0 citations
Multimodal sentiment analysis (MSA) is a popular research topic particularly for predicting human emotional attitudes. However, most existing methods fail to learn the multi-level nonlinear information in MSA due to their usually adopting single-level representation learning, and alternatively suffer from insufficiently extracting the comprehensive correlation features among the triple modalities. Here, to address these issues, we propose a MSA network with Multi-Level representation learning and global Tri-Modality unified fusion, termed as MLTM. Specifically, we devise a multi-level encoding strategy with a hierarchical progressive encoder and multi-level perceptual attention to dynamically weight the information at each level, thereby enhancing the nonlinear representation ability. Furthermore, a dynamic representation optimization mechanism is developed to enhance the semantic relevance of shared features while preserving the uniqueness of private ones. Subsequently, we design a Global Tri-Modality Transformer (GTMT) that first performs parallel fusion of the three modalities and then conducts deep integration guided by the textual modality to achieve the cross-modal semantic alignment and correlation, significantly improving the global unified fusion effectiveness of the tri-modality information. Extensive experiments on three public MSA datasets demonstrate that MLTM outperforms various state-of-the-art methods by a wide margin across various evaluation metrics, indicating its effectiveness and robustness. Specifically, MLTM achieves a superior Acc7 of 55.10 and 48.98, an enhancement of 2.39% and 2.44% compared to the second-best baselines on CMU-MOSEI and CMU-MOSI. Moreover, it reduces MAE to 0.502 and 0.590, improving by 2.14% and 15.7%, on the above two datasets, respectively.
Zelong Li, Shuhua Lu, Cui Fang et al.· Neural Networks· 0 citations
The high rate of social media content development causes an increase in multimodal data, such that modeling relationships between visual and textual data is challenging. Nevertheless, most of the available methods cannot capture fine-grained text-to-visual or visual-to-text interaction, resulting in lower sentiment performance. A Contrastive Bidirectional Cross-Modal Attention (C-BCMA) model is presented to enhance the correspondence of textual and visual representations by acquiring a common latent space. An attention method inspired by CLIP is utilized to produce robust cross-modal latent features to enhance their joint representation. Textual features are derived using ALBERT, whereas EfficientNet-B2 is applied to obtain visual representations. Interactions between modalities are learned using a multi-head attention mechanism. Textual and visual information is handled jointly during learning. This helps reduce gaps between the two modalities. This enables the model to process various semantic cues at once. Contrastive learning is used in the model to align similar text-image pairs and to separate unrelated text-image pairs so that better multimodal representations are achieved. The model has a better performance than baseline approaches on both single and multiple annotation versions of MVSA datasets. It achieves better performance across various evaluation metrics. Less obvious expressions like sarcasm and implicit sentiment are handled more effectively in this work, improving interpretation in multimodal sentiment analysis of social media data.
Prashant Adakane, Amit Gaikwad· international journal of eng...· 0 citations
MGSI first encodes audio and visual streams at short-, medium-, and long-range temporal scales, preserving both local variations and global affective trends, and applies polarity- and intensity-aware enhancement to better handle ambiguous and near-neutral samples.
Shanshan Lin, Yuesheng Wu, Chao Chen et al.· 0 citations
Multimodal sentiment analysis has attracted increasing attention due to the prevalence of text-image content on social media. A central challenge is to design fusion mechanisms that are both expressive and parameter-efficient, especially for small-scale datasets where heavy cross-modal attention can easily overfit. In this paper, we present Consistency-Aware Gated Fusion (CAGF), a lightweight and fusion module tailored to Mamba-based architectures. Our key idea is to exploit Mamba's bidirectional scanning mechanism: forward and backward hidden states from text and image encoders are concatenated to form enhanced representations, and a cosine-based semantic consistency score is computed between modalities. This score is then passed through a fixed sigmoid gate to adaptively weight text and image features, without introducing any additional learnable parameters. CAGF is plug-and-play compatible with dual-stream Mamba encoders and incurs negligible computational overhead compared with attention-based fusion. Experiments on the MVSA-Single dataset show that CAGF achieves state-of-the-art performance (Acc=82.54%, F1=84.82%), outperforming strong multimodal baselines such as CLIP, MISA, DLF, AoM, and SFTTR, while remaining more efficient and interpretable. Extensive ablations and sensitivity analyses further validate that bidirectional scanning, enhanced representations, and consistency-aware gating are all critical to the observed gains.
Jian Hu· Poster Volume 0008 The 2026...· 0 citations
MagXCL, a unified framework designed to improve multimodal integration through more effective interaction between verbal and non-verbal modalities, is proposed, demonstrating the effectiveness of combining AMag with CrossCL to produce more accurate and robust multimodal sentiment predictions.