activity
20122023
most citedExposing DeepFake Videos By Detecting Face Warping Artifacts

684 citations · 1.6k across the 40 of their papers we have counts for

collaborators
Showing 2018Show all

15 papers · 1 filter

cs.CV2018★ 6 cited

Residual Attention based Network for Hand Bone Age Assessment

Eric Wu, Bin Kong, Xin Wang +8

Computerized automatic methods have been employed to boost the productivity as well as objectiveness of hand bone age assessment. These approaches make predictions according to the…

cs.CV2018★ 9 cited

Learning Non-Uniform Hypergraph for Multi-Object Tracking

Longyin Wen, Dawei Du, Shengkun Li +2

The majority of Multi-Object Tracking (MOT) algorithms based on the tracking-by-detection scheme do not use higher order dependencies among objects or tracklets, which makes them l…

cs.CV2018★ 22 cited

Exposing Deep Fakes Using Inconsistent Head Poses

Xin Yang, Yuezun Li, Siwei Lyu

In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes). Our method is based on the observations that Deep Fakes…

cs.CV2018★ 2 cited

Evolvement Constrained Adversarial Learning for Video Style Transfer

Wenbo Li, Longyin Wen, Xiao Bian +1

Video style transfer is a useful component for applications such as augmented reality, non-photorealistic rendering, and interactive games. Many existing methods use optical flow t…

cs.CV2018★ 684 cited

Exposing DeepFake Videos By Detecting Face Warping Artifacts

Yuezun Li, Siwei Lyu

In this work, we describe a new deep learning based method that can effectively distinguish AI-generated fake videos (referred to as {\em DeepFake} videos hereafter) from real vide…

cs.CV2018★ 24 cited

Exploring the Vulnerability of Single Shot Module in Object Detectors via Imperceptible Background Patches

Yuezun Li, Xiao Bian, Ming-ching Chang +1

Recent works succeeded to generate adversarial perturbations on the entire image or the object of interests to corrupt CNN based object detectors. In this paper, we focus on explor…