M4-BLIP: Advancing Multi-Modal Media Manipulation Detection through Face-Enhanced Local Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909937373806592 |
|---|---|
| author | Wu, Hang Sun, Ke Ji, Jiayi Sun, Xiaoshuai Ji, Rongrong |
| author_facet | Wu, Hang Sun, Ke Ji, Jiayi Sun, Xiaoshuai Ji, Rongrong |
| contents | In the contemporary digital landscape, multi-modal media manipulation has emerged as a significant societal threat, impacting the reliability and integrity of information dissemination. Current detection methodologies in this domain often overlook the crucial aspect of localized information, despite the fact that manipulations frequently occur in specific areas, particularly in facial regions. In response to this critical observation, we propose the M4-BLIP framework. This innovative framework utilizes the BLIP-2 model, renowned for its ability to extract local features, as the cornerstone for feature extraction. Complementing this, we incorporate local facial information as prior knowledge. A specially designed alignment and fusion module within M4-BLIP meticulously integrates these local and global features, creating a harmonious blend that enhances detection accuracy. Furthermore, our approach seamlessly integrates with Large Language Models (LLM), significantly improving the interpretability of the detection outcomes. Extensive quantitative and visualization experiments validate the effectiveness of our framework against the state-of-the-art competitors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_01214 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | M4-BLIP: Advancing Multi-Modal Media Manipulation Detection through Face-Enhanced Local Analysis Wu, Hang Sun, Ke Ji, Jiayi Sun, Xiaoshuai Ji, Rongrong Computer Vision and Pattern Recognition Artificial Intelligence In the contemporary digital landscape, multi-modal media manipulation has emerged as a significant societal threat, impacting the reliability and integrity of information dissemination. Current detection methodologies in this domain often overlook the crucial aspect of localized information, despite the fact that manipulations frequently occur in specific areas, particularly in facial regions. In response to this critical observation, we propose the M4-BLIP framework. This innovative framework utilizes the BLIP-2 model, renowned for its ability to extract local features, as the cornerstone for feature extraction. Complementing this, we incorporate local facial information as prior knowledge. A specially designed alignment and fusion module within M4-BLIP meticulously integrates these local and global features, creating a harmonious blend that enhances detection accuracy. Furthermore, our approach seamlessly integrates with Large Language Models (LLM), significantly improving the interpretability of the detection outcomes. Extensive quantitative and visualization experiments validate the effectiveness of our framework against the state-of-the-art competitors. |
| title | M4-BLIP: Advancing Multi-Modal Media Manipulation Detection through Face-Enhanced Local Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.01214 |