6 papers
When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection
Chao Shuai, Shaojing Fan, Chenlin Zou +6
The growing realism of generative models has blurred the boundary between real and synthetic content, posing significant challenges to reliable AI-generated image detection. Althou…
Deepfake Synthesis vs. Detection: An Uneven Contest
Md. Tarek Hasan, Sanjay Saha, Shaojing Fan +2
The rapid advancement of deepfake technology has significantly elevated the realism and accessibility of synthetic media. Emerging techniques, such as diffusion-based models and Ne…
Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models
Zhenguang Liu, Chao Shuai, Shaojing Fan +4
Diffusion models have achieved remarkable success in novel view synthesis, but their reliance on large, diverse, and often untraceable Web datasets has raised pressing concerns abo…
Multi-Grained Feature Pruning for Video-Based Human Pose Estimation
Zhigang Wang, Shaojing Fan, Zhenguang Liu +3
Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods fo…
SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos
Yingying Jiao, Zhigang Wang, Sifan Wu +4
Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermo…
Optimizing Human Pose Estimation Through Focused Human and Joint Regions
Yingying Jiao, Zhigang Wang, Zhenguang Liu +4
Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accu…