MViR: Multi-View Visual-Semantic Representation for Fake News Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912928220839936 |
|---|---|
| author | Liang, Haochen Su, Xinqi Wang, Jun Chen, Chaomeng Yu, Zitong |
| author_facet | Liang, Haochen Su, Xinqi Wang, Jun Chen, Chaomeng Yu, Zitong |
| contents | With the rise of online social networks, detecting fake news accurately is essential for a healthy online environment. While existing methods have advanced multimodal fake news detection, they often neglect the multi-view visual-semantic aspects of news, such as different text perspectives of the same image. To address this, we propose a Multi-View Visual-Semantic Representation (MViR) framework. Our approach includes a Multi-View Representation module using pyramid dilated convolution to capture multi-view visual-semantic features, a Multi-View Feature Fusion module to integrate these features with text, and multiple aggregators to extract multi-view semantic cues for detection. Experiments on benchmark datasets demonstrate the superiority of MViR. The source code of FedCoop is available at https://github.com/FlowerinZDF/FakeNews-MVIR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22944 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MViR: Multi-View Visual-Semantic Representation for Fake News Detection Liang, Haochen Su, Xinqi Wang, Jun Chen, Chaomeng Yu, Zitong Multimedia With the rise of online social networks, detecting fake news accurately is essential for a healthy online environment. While existing methods have advanced multimodal fake news detection, they often neglect the multi-view visual-semantic aspects of news, such as different text perspectives of the same image. To address this, we propose a Multi-View Visual-Semantic Representation (MViR) framework. Our approach includes a Multi-View Representation module using pyramid dilated convolution to capture multi-view visual-semantic features, a Multi-View Feature Fusion module to integrate these features with text, and multiple aggregators to extract multi-view semantic cues for detection. Experiments on benchmark datasets demonstrate the superiority of MViR. The source code of FedCoop is available at https://github.com/FlowerinZDF/FakeNews-MVIR. |
| title | MViR: Multi-View Visual-Semantic Representation for Fake News Detection |
| topic | Multimedia |
| url | https://arxiv.org/abs/2602.22944 |