activity
20162023
most citedSecond-order asymptotics on distributions of maxima of bivariate elliptical arrays

1 citations · 1 across the 5 of their papers we have counts for

collaborators

11 papers

cs.CV2024

Compressed Deepfake Video Detection Based on 3D Spatiotemporal Trajectories

Zongmei Chen, Xin Liao, Xiaoshuai Wu +1

The misuse of deepfake technology by malicious actors poses a potential threat to nations, societies, and individuals. However, existing methods for detecting deepfakes primarily f…

cs.CV20241 cited

Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics

Xiaoshuai Wu, Xin Liao, Bo Ou +2

AI-generated content has accelerated the topic of media synthesis, particularly Deepfake, which can manipulate our portraits for positive or malicious purposes. Before releasing th…

math.NT2024

Common substring with shifts in b-ary expansions

Xin Liao, Dingding Yu

Denote by the length of the longest common substring of and with shifts in their first digits of -ary expansions. We show that the sets of pairs ,…

cs.CV2023

Recap: Detecting Deepfake Video with Unpredictable Tampered Traces via Recovering Faces and Mapping Recovered Faces

Juan Hu, Xin Liao, Difei Gao +4

The exploitation of Deepfake techniques for malicious intentions has driven significant research interest in Deepfake detection. Deepfake manipulations frequently introduce random…

cs.CV20231 cited

CTP-Net: Character Texture Perception Network for Document Image Forgery Localization

Xin Liao, Siliang Chen, Jiaxin Chen +2

Due to the progression of information technology in recent years, document images have been widely disseminated on social networks. With the help of powerful image editing tools, d…

cs.CV2023

Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions

Lanfeng Zhong, Xin Liao, Shaoting Zhang +1

Segmentation of pathological images is a crucial step for accurate cancer diagnosis. However, acquiring dense annotations of such images for training is labor-intensive and time-co…