CSpace

浏览/检索结果: 共2条,第1-2条 帮助

已选(0)清除 条数/页:   排序方式:
Enhancing the Robustness of Vision-Language Foundation Models by Alignment Perturbation 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2025, 卷号: 20, 页码: 7091-7105
作者:  Zhang, Cong;  Wang, Shuhui;  Li, Xiaodan;  Zhu, Yao;  Qi, Honggang;  Huang, Qingming
收藏  |  浏览/下载:44/0  |  提交时间:2025/12/03
Multimedia forensics  adversarial perturbation  robust training  robust training  vision-language models  vision-language models  vision-language models  
COMICS: End-to-End Bi-Grained Contrastive Learning for Multi-Face Forgery Detection 期刊论文
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 卷号: 34, 期号: 10, 页码: 10223-10236
作者:  Zhang, Cong;  Qi, Honggang;  Wang, Shuhui;  Li, Yuezun;  Lyu, Siwei
收藏  |  浏览/下载:94/0  |  提交时间:2024/12/06
Face recognition  Forgery  Feature extraction  Proposals  Object detection  Faces  Generators  DeepFake  multi-face forgery detection  contrastive learning  fine-grained feature learning