Visual Framing for News Stance Detection via Image Generation

• URL: http://arxiv.org/abs/2609.00685v1
• Date: Tue, 01 Sep 2026 04:06:27 GMT
• Title: Visual Framing for News Stance Detection via Image Generation
• Abstract summary: Article-level news stance detection aims to identify the perspective of news articles toward social issues.<n>Despite advances in stance detection, news articles pose distinct challenges because their stances are often implicit, subtly conveyed through journalistic framing, and embedded in long, structurally complex texts.<n>We introduce VFStance, which leverages visual framing to make implicit stance cues more explicit via image generation.
• Score: 4.354621530888926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Article-level news stance detection aims to identify the perspective of news articles toward social issues. Despite advances in stance detection and its importance for trustworthy media environments, news articles pose distinct challenges because their stances are often implicit, subtly conveyed through journalistic framing, and embedded in long, structurally complex texts. To address these challenges, we introduce VFStance, which leverages visual framing to make implicit stance cues more explicit via image generation. In evaluation experiments, we demonstrate the effectiveness of VFStance over existing methods and the contribution of visual framing to its performance. Finally, a controlled user study (N=200) in a snippet-based news consumption setting further demonstrates that VFStance can make stance signals visually salient and highlights its potential use beyond automated stance detection.

Related papers

• Sens-VisualNews: A Benchmark Dataset for Sensational Image Detection [8.21302918994687]
  We introduce the task of sensational image detection, which aims to determine whether an image contains shocking, provocative, or emotionally charged features to grab attention and trigger strong emotional responses.<n>To support research on this task, we create a new benchmark dataset (called Sens-VisualNews) that contains 9,576 images from news items, annotated based on the (in-)existence of various sensational concepts and events in their visual content.
  arXiv  Detail & Related papers  (2026-05-11T11:38:32Z)
• DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts [11.577330098443696]
  We propose DETR-ViP, a robust object detection framework that yields class-distinguishable visual prompts.<n>On top of basic image-text contrastive learning, DETR-ViP incorporates global prompt integration and visual-textual prompt relation distillation.<n>Experiments on COCO, LVIS, ODinW, and Roboflow100 demonstrate that DETR-ViP achieves substantially higher performance in visual prompt detection.
  arXiv  Detail & Related papers  (2026-04-16T06:40:44Z)
• Steerable Visual Representations [72.39044430620977]
  We introduce Steerable Visual Representations, whose global and local features can be steered with natural language.<n>Our method also matches or outperforms dedicated approaches on anomaly detection and personalized object discrimination.
  arXiv  Detail & Related papers  (2026-04-02T17:59:49Z)
• Bridging Thoughts and Words: Graph-Based Intent-Semantic Joint Learning for Fake News Detection [16.22231659861359]
  We propose Graph-based Intent-Semantic Joint Modeling (InSide) for fake news detection.<n>InSide reformulates news semantic and intent signals into heterogeneous graph structures.
  arXiv  Detail & Related papers  (2025-09-01T17:59:18Z)
• Journalism-Guided Agentic In-Context Learning for News Stance Detection [3.9861857176369564]
  Stance detection can help enable viewpoint-aware recommendations and data-driven analyses of media bias.<n>We introduce textscK-News-Stance, the first Korean dataset for article-level stance detection.<n>We also propose textscJoA-ICL, a textbfJournalism-guided textbfAgentic textbfIn-textbfContext textbfL framework.
  arXiv  Detail & Related papers  (2025-07-15T07:22:04Z)
• KEN: Knowledge Augmentation and Emotion Guidance Network for Multimodal Fake News Detection [1.8603865942709585]
  We propose a novel Knowledge Augmentation and Emotion Guidance Network (KEN)<n>On the one hand, we effectively leverage LVLM's powerful semantic understanding and extensive world knowledge.<n>On the other hand, we consider inter-class differences between different emotional types of news through balanced learning, achieving fine-grained modeling of the relationship between emotional types and authenticity.
  arXiv  Detail & Related papers  (2025-07-13T14:28:20Z)
• A Survey of Stance Detection on Social Media: New Directions and Perspectives [50.27382951812502]
  stance detection has emerged as a crucial subfield within affective computing. Recent years have seen a surge of research interest in developing effective stance detection methods. This paper provides a comprehensive survey of stance detection techniques on social media.
  arXiv  Detail & Related papers  (2024-09-24T03:06:25Z)
• Leveraging Open-Vocabulary Diffusion to Camouflaged Instance Segmentation [59.78520153338878]
  Text-to-image diffusion techniques have shown exceptional capability of producing high-quality images from text descriptions. We propose a method built upon a state-of-the-art diffusion model, empowered by open-vocabulary to learn multi-scale textual-visual features for camouflaged object representations.
  arXiv  Detail & Related papers  (2023-12-29T07:59:07Z)
• Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection [51.66174565170112]
  We introduce a novel approach to utilize the strengths of large language models in understanding contextual appearance variations. We propose to formulate language-derived appearance elements and incorporate them with visual cues in pedestrian detection.
  arXiv  Detail & Related papers  (2023-11-02T06:38:19Z)
• Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection [50.07850264495737]
  "Prompt-and-Align" (P&A) is a novel prompt-based paradigm for few-shot fake news detection. We show that P&A sets new states-of-the-art for few-shot fake news detection performance by significant margins.
  arXiv  Detail & Related papers  (2023-09-28T13:19:43Z)
• Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations [103.00383924074585]
  Visual relationship detection aims to reason over relationships among salient objects in images. We propose a novel approach named Visual-Linguistic Representations from Transformers (RVL-BERT) RVL-BERT performs spatial reasoning with both visual and language commonsense knowledge learned via self-supervised pre-training.
  arXiv  Detail & Related papers  (2020-09-10T16:15:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.