Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.10394 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917480555872256 |
|---|---|
| author | Goulas, Andreas Galanopoulos, Damianos Apostolidis, Evlampios Mezaris, Vasileios |
| author_facet | Goulas, Andreas Galanopoulos, Damianos Apostolidis, Evlampios Mezaris, Vasileios |
| contents | The detection of sensational content in media items can be a critical filtering mechanism for identifying check-worthy content and flagging potential disinformation, since such content triggers physiological arousal that often bypasses critical evaluation and accelerates viral sharing. In this paper 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. 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. Finally, using Sens-VisualNews, we study the prompt sensitivity, performance and robustness of a wide range of open SotA Multimodal LLMs, across both zero-shot and fine-tuned settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10394 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sens-VisualNews: A Benchmark Dataset for Sensational Image Detection Goulas, Andreas Galanopoulos, Damianos Apostolidis, Evlampios Mezaris, Vasileios Computer Vision and Pattern Recognition The detection of sensational content in media items can be a critical filtering mechanism for identifying check-worthy content and flagging potential disinformation, since such content triggers physiological arousal that often bypasses critical evaluation and accelerates viral sharing. In this paper 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. 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. Finally, using Sens-VisualNews, we study the prompt sensitivity, performance and robustness of a wide range of open SotA Multimodal LLMs, across both zero-shot and fine-tuned settings. |
| title | Sens-VisualNews: A Benchmark Dataset for Sensational Image Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.10394 |