| 标题 |
 2S-DGM4: A Two-Stage Framework for Detecting and Grounding Multi-Modal Media Manipulation |
| 网址 | |
| DOI | |
| 其它 | Detecting and grounding multi-modal media manipulation (DGM4) aims to identify the authenticity of media content in the form of image-text pairs, and locate forgery contents including text tokens or image regions. Existing methods adopt joint optimization frameworks to train multiple dedicated heads for different sub-tasks. This paradigm is prone to yielding models with insufficient learning regarding manipulation traces. In this paper, we propose a two-stage learning framework, named 2S-DGM4, exploiting correlations between manipulation detection and grounding for debunking manipulation content. It introduces modality-specific manipulation types into the subsequent manipulation grounding, and naturally conducts the mutual agreement among various sub-tasks. |
| 求助人 | |
| 下载 |
PDF的下载单位、IP信息已删除
(2025-6-4)
嘻嘻哈哈
渡人舟
林狗
牧青
整齐的孤菱
v0id
冷酷以山
快点毕业
谢雷XIELei
璐璐
忧心的曼凝
李杨
美好亦云
sadboy
Xixi
你嵙这个期刊没买
GingerF
七听
changping
平常迎天
皖公网安备34019202002308
