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

arXiv: https://arxiv.org/abs/2607.23493 · HTML: https://mlsanity.com/paper/2607.23493/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2109.05184/) (2021)
- [Prompting for Multimodal Hateful Meme Classification](https://mlsanity.com/paper/2302.04156/) (2023)
- [DISARM: Detecting the Victims Targeted by Harmful Memes](https://mlsanity.com/paper/2205.05738/) (2022)
- [Mapping Memes to Words for Multimodal Hateful Meme Classification](https://mlsanity.com/paper/2310.08368/) (2023)
- [Deciphering Hate: Identifying Hateful Memes and Their Targets](https://mlsanity.com/paper/2403.10829/) (2024)
- [Multimodal and Explainable Internet Meme Classification](https://mlsanity.com/paper/2212.05612/) (2022)

## Abstract (arXiv)

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.