← All publications

Journal · 2026

Multimedia Understanding and Safety

Reasoning-Aware Multimodal Fusion for Hateful Video Detection

Shuonan Yang, Tailin Chen, Jiangbei Yue, Guangliang Cheng, Jianbo Jiao, Zeyu Fu

Transactions on Machine Learning Research (TMLR)

Architecture of RAMF, combining local-global context fusion, semantic cross attention and VLM adversarial reasoning.

Abstract

Overview

Hate speech in online videos is posing an increasingly serious threat to digital platforms, especially as video content becomes increasingly multimodal and context-dependent. Existing methods often struggle to effectively fuse the complex semantic relationships between modalities and lack the ability to understand nuanced hateful content. To address these issues, we propose an innovative Reasoning-Aware Multimodal Fusion (RAMF) framework. To tackle the first challenge, we design Local-Global Context Fusion (LGCF) to capture both local salient cues and global temporal structures, and propose Semantic Cross Attention (SCA) to enable fine-grained multimodal semantic interaction. To tackle the second challenge, we introduce adversarial reasoning—a structured three-stage process where a vision-language model generates objective descriptions, hate-assumed inferences, and non-hate-assumed inferences—providing complementary semantic perspectives that enrich the model's contextual understanding of nuanced hateful intent. Evaluations on two real-world hateful video datasets demonstrate that our method achieves robust generalisation performance, improving upon state-of-the-art methods by 3% and 7% in Macro-F1 and hate class recall, respectively.

Citation

BibTeX

@article{yang2026reasoning,
  title = {Reasoning-Aware Multimodal Fusion for Hateful Video Detection},
  author = {Shuonan Yang and Tailin Chen and Jiangbei Yue and Guangliang Cheng and Jianbo Jiao and Zeyu Fu},
  journal = {Transactions on Machine Learning Research},
  year = {2026},
  url = {https://openreview.net/forum?id=U9KnNiuMu1},
  eprint = {2512.02743},
  archivePrefix = {arXiv}
}