文章总览 - 139
LiDiNet
LiDiNet

31
Finding Incompatible Blocks for Reliable JPEG Steganalysis
Finding Incompatible Blocks for Reliable JPEG Steganalysis

32
Image-based_Freeform_Handwriting_Authentication_with_Energy-oriented_Self-Supervised_Learning
Image-based_Freeform_Handwriting_Authentication_with_Energy-oriented_Self-Supervised_Learning

33
Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning
Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning

发表于TIP 2024,图像复制-移动伪造检测方向的图像篡改检测方法。

34
DiRLoc:Disentanglement Representation Learning for Robust Image Forgery Localization
DiRLoc:Disentanglement Representation Learning for Robust Image Forgery Localization

发表于TDSC2024,针对JPEG压缩导致的性能下降,使用解纠缠的方法,分离出jpeg压缩对篡改痕迹的影响,提出了一种鲁棒的图像伪造定位框架。

35
IMDL-BenCo:A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
IMDL-BenCo:A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization

发表于NeurIPS 2024,因为图像篡改检测没有统一的标准,所以构建一个全面的基准,并且设计了一个框架将部分sota网络集成:Mantra-Net,MVSS-net,CAT-Net,ObjectFormer,PSCC-Net,NCL-IML,Trufor和IML-ViT。

36
边界引导
边界引导

37
DBSCAN
DBSCAN

38
Image as Set of Points
Image as Set of Points

发表于ICLR2023,将图像视为一组无组织的点,并通过简化的聚类算法提取特征。具体地说,每个点都包括原始特征(如颜色)和位置信息(如坐标),并采用简化的聚类算法对深度特征进行分层分组和提取。

39
可微深度聚类
可微深度聚类

40