Skip to content
Preprint

Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation

Jul 2026 · 0 citations · 13 references
Computer Science

TL;DR

Experimental evaluation on the PoliMemeDecode1 dataset shows that the attention-based fusion significantly outperforms unimodal baselines and standard concatenation methods, achieving a state-of-the-art Macro-F1 of approximately 0.94.

Abstract

Automated analysis of multimodal content on social networks has become a critical task for understanding public sentiment and information diffusion in the digital age. However, classifying internet memes remains computationally challenging due to the intricate interplay between visual cues and embedded, often stylized, text, particularly in low-resource languages like Bengali Language. This paper addresses the detection of political intent in Bengali memes by introducing Multimodal Cross-Attention Fusion framework. We first leverage a Vision-Language Model to extract high-fidelity OCR text from noisy meme images. Subsequently, we encode visual and textual features and synthesize them through a cross-modal multi-head attention mechanism that aligns semantic tokens with visual regions. We also investigate the integration of a domain-specific political lexicon as a knowledge prior. Experimental evaluation on the PoliMemeDecode1 dataset shows that our attention-based fusion significantly outperforms unimodal baselines and standard concatenation methods, achieving a state-of-the-art Macro-F1 of approximately 0.94. Interpretability analyzes further confirm that the model effectively learns to ground textual semantics in visual evidence.

View source

Similar papers

Open access Jul 2026

XSentiFusionNet: An Explainable Cross-Modal Attention Framework For Audio-Visual Sentiment Analysis Using Hybrid Deep Learning

XSentiFusionNet is an end-to-end explainable multimodal framework for audio-visual sentiment analysis that incorporates cross-modal transformer-attention, reliability-aware adaptive fusion, and XAI and showed higher robustness to noise and generalization ability on different multimodal datasets.

M. Kidwai, C. Author, Dr. Faiyaz Ahmad · 0 citations
Aug 2026

MagXCL: enhanced multimodal adaptation gate and cross-modal contrastive learning for multimodal sentiment analysis

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.

Duc-Duy Duong, Cam-Van Thi Nguyen, Duc-Trong Le · 0 citations
#small language model Preprint Aug 2026

Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis

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
Conference Jul 2026

Attention and Transformer based Multimodal Framework for Fine-Grained Emotion Analysis

The increasing availability of social networking sites has ensured that memes have become a part of our daily lives to express our opinion through communication. Images or plain text are in contrast to multimodal content consisting of textual captions on images to explain emotions, opinions, and sarcasm in implicit and in some cases ambiguous ways. Identification and classification of these emotions are not a straightforward task but demand robust multimodal learning models that can glue visual as well as textual information together. This paper presents an end-to-end multimodal emotion analysis model based on the MEMotion dataset, integrating state-of-the-art deep learning structures, strict preprocessing, and extensive evaluation approaches to confront the difficulty of meme-based emotion detection. The proposed system is a formal multi-stage pipeline. Stage one delivers dataset refinement through cleaning, path correction, binarization of labels, and stratified splitting to balance classes in training and validation sets. Stage two is a hybrid approach in which ResNet-based convolutional networks learn discriminative visual features, while BERT encoders learn contextualized textual semantics. The features are then fused through dense projection layers and dropout-normalized to prevent overfitting. Stage three involves adaptive training mechanisms with the application of weighted cross-entropy, focal loss, and their hybrid forms for handling extreme class imbalance across multiple labels: humour, sarcasm, offensive, motivational, and general sentiment. Stage four enhances experimental robustness with gradient accumulation, learningrate warmup, early stopping, and misclassification grids. A broad set of per-task confusion matrix, aggregated confusion grid, ROC and precision-recall curve, loss–accuracy plot, and per-class accuracy plot outputs were generated to enable more in-depth model performance interpretability.

I. S, F. H. Fernandez · 0 citations
Aug 2026

Aspect-guided dual-branch fusion network for multimodal aspect-based sentiment analysis

An Aspect-guided dual-branch fusion network (ADFN) to enhance sentiment prediction by incorporating external knowledge and integrating coarse and fine information is proposed, which incorporates syntactic dependency information to complement and enrich the textual semantic representations.

Bin Song, Wenjing Liu, Zhipeng Liang et al. · 0 citations