CASIA OpenIR

浏览/检索结果: 共6条,第1-6条 帮助

限定条件                    
已选(0)清除 条数/页:   排序方式:
Invisible Intruders: Label-Consistent Backdoor Attack using Re-parameterized Noise Trigger 期刊论文
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 卷号: 14, 期号: 8, 页码: 1-13
作者:  Bo Wang;  Fei Yu;  Fei Wei;  Yi Li;  Wei Wang
Adobe PDF(1364Kb)  |  收藏  |  浏览/下载:55/17  |  提交时间:2024/06/21
Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networks 期刊论文
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023, 页码: 1-14
作者:  Junfei Wu;  Weizhi Xu;  Qiang Liu;  Shu Wu;  Liang Wang
Adobe PDF(4374Kb)  |  收藏  |  浏览/下载:35/8  |  提交时间:2024/06/21
FedBrain: A robust multi-site brain network analysis framework based on federated learning for brain disease diagnosis 期刊论文
NEUROCOMPUTING, 2023, 卷号: 559, 页码: 13
作者:  Zhang, Chang;  Meng, Xiangzhu;  Liu, Qiang;  Wu, Shu;  Wang, Liang;  Ning, Huansheng
Adobe PDF(3483Kb)  |  收藏  |  浏览/下载:154/4  |  提交时间:2023/11/16
Functional magnetic resonance image  Brain network  Federated learning  Deep neural networks  Brain disease diagnosis  
Dynamic video mix-up for cross-domain action recognition 期刊论文
Neurocomputing, 2022, 卷号: 471, 期号: 2022, 页码: 358-368
作者:  Han Wu;  Chunfeng Song;  Shaolong Yue;  Zhenyu Wang;  Jun Xiao;  Yanyang Liu
Adobe PDF(2148Kb)  |  收藏  |  浏览/下载:96/41  |  提交时间:2023/05/04
Theme-Aware Aesthetic Distribution Prediction With Full-Resolution Photographs 期刊论文
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 页码: 15
作者:  Jia, Gengyun;  Li, Peipei;  He, Ran
Adobe PDF(10845Kb)  |  收藏  |  浏览/下载:298/51  |  提交时间:2022/06/06
Aesthetic quality assessment (AQA)  full resolution  region of image (RoM) pooling  theme  
Exploring DCT Coefficient Quantization Effects for Local Tampering Detection 期刊论文
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2014, 卷号: 9, 期号: 10, 页码: 1653-1666
作者:  Wang, Wei;  Dong, Jing;  Tan, Tieniu
浏览  |  Adobe PDF(6342Kb)  |  收藏  |  浏览/下载:477/141  |  提交时间:2015/08/12
Image Forensics  Local Tampering Detection  Double Quantization  Graph Cut