Search Results for author: Shan Jia

Found 15 papers, 8 papers with code

Exposing Lip-syncing Deepfakes from Mouth Inconsistencies

no code implementations18 Jan 2024 Soumyya Kanti Datta, Shan Jia, Siwei Lyu

A lip-syncing deepfake is a digitally manipulated video in which a person's lip movements are created convincingly using AI models to match altered or entirely new audio.

DeepFake Detection Face Swapping

Improving Fairness in Deepfake Detection

1 code implementation29 Jun 2023 Yan Ju, Shu Hu, Shan Jia, George H. Chen, Siwei Lyu

Despite the development of effective deepfake detectors in recent years, recent studies have demonstrated that biases in the data used to train these detectors can lead to disparities in detection accuracy across different races and genders.

DeepFake Detection Face Swapping +1

UPDExplainer: an Interpretable Transformer-based Framework for Urban Physical Disorder Detection Using Street View Imagery

no code implementations4 May 2023 Chuanbo Hu, Shan Jia, Fan Zhang, Changjiang Xiao, Mindi Ruan, Jacob Thrasher, Xin Li

Experimental results on the re-annotated Place Pulse 2. 0 dataset demonstrate promising detection performance of the proposed method, with an accuracy of 79. 9%.

Semantic Segmentation

AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensics

1 code implementation14 Apr 2023 Shan Jia, Mingzhen Huang, Zhou Zhou, Yan Ju, Jialing Cai, Siwei Lyu

To achieve this, we propose a new approach that leverages the DALL-E2 language-image model to automatically generate and splice masked regions guided by a text prompt.

Image and Video Forgery Detection Image Generation

GLFF: Global and Local Feature Fusion for AI-synthesized Image Detection

1 code implementation16 Nov 2022 Yan Ju, Shan Jia, Jialing Cai, Haiying Guan, Siwei Lyu

To address this issue, we propose a Global and Local Feature Fusion (GLFF) framework to learn rich and discriminative representations by combining multi-scale global features from the whole image with refined local features from informative patches for AI synthesized image detection.

Fusion-based Few-Shot Morphing Attack Detection and Fingerprinting

1 code implementation27 Oct 2022 Na Zhang, Shan Jia, Siwei Lyu, Xin Li

Our technical contributions include: 1) We propose a fusion-based few-shot learning (FSL) method to learn discriminative features that can generalize to unseen morphing attack types from predefined presentation attacks; 2) The proposed FSL based on the fusion of the PRNU model and Noiseprint network is extended from binary MAD to multiclass morphing attack fingerprinting (MAF).

Face Recognition Few-Shot Learning

Joint Learning of Deep Texture and High-Frequency Features for Computer-Generated Image Detection

1 code implementation7 Sep 2022 Qiang Xu, Shan Jia, Xinghao Jiang, Tanfeng Sun, Zhe Wang, Hong Yan

Based on the finding that multiple different modules in image acquisition will lead to different sensitivity inconsistencies to the convolutional neural network (CNN)-based rendering in images, we propose a deep texture rendering module for texture difference enhancement and discriminative texture representation.

Generative Adversarial Network Semantic Segmentation

A Saliency-Guided Street View Image Inpainting Framework for Efficient Last-Meters Wayfinding

1 code implementation14 May 2022 Chuanbo Hu, Shan Jia, Fan Zhang, Xin Li

However, due to the large diversity of geographic context and acquisition conditions, the captured SVI always contains various distracting objects (e. g., pedestrians and vehicles), which will distract human visual attention from efficiently finding the destination in the last few meters.

Image Inpainting object-detection +2

Fusing Global and Local Features for Generalized AI-Synthesized Image Detection

1 code implementation26 Mar 2022 Yan Ju, Shan Jia, Lipeng Ke, Hongfei Xue, Koki Nagano, Siwei Lyu

Specifically, we design a two-branch model to combine global spatial information from the whole image and local informative features from multiple patches selected by a novel patch selection module.

Model Attribution of Face-swap Deepfake Videos

1 code implementation25 Feb 2022 Shan Jia, Xin Li, Siwei Lyu

Then we take Deepfakes model attribution as a multiclass classification task and propose a spatial and temporal attention based method to explore the differences among Deepfakes in the new dataset.

Attribute Face Swapping

Detection of Genuine and Posed Facial Expressions of Emotion: A Review

no code implementations26 Aug 2020 Shan Jia, Shuo Wang, Chuanbo Hu, Paula Webster, Xin Li

Facial expressions of emotion play an important role in human social interactions.

3D Face Anti-spoofing with Factorized Bilinear Coding

no code implementations12 May 2020 Shan Jia, Xin Li, Chuanbo Hu, Guodong Guo, Zhengquan Xu

We have witnessed rapid advances in both face presentation attack models and presentation attack detection (PAD) in recent years.

Face Anti-Spoofing Face Presentation Attack Detection +1

Spoofing and Anti-Spoofing with Wax Figure Faces

no code implementations12 Oct 2019 Shan Jia, Xin Li, Chuanbo Hu, Zhengquan Xu

In this work, we introduce a wax figure face database (WFFD) as a novel and super-realistic 3D face presentation attack.

Face Detection Face Recognition +1

A database for face presentation attack using wax figure faces

no code implementations6 Jun 2019 Shan Jia, Chuanbo Hu, Guodong Guo, Zhengquan Xu

Compared to 2D face presentation attacks (e. g. printed photos and video replays), 3D type attacks are more challenging to face recognition systems (FRS) by presenting 3D characteristics or materials similar to real faces.

Face Presentation Attack Detection Face Recognition +1

Cannot find the paper you are looking for? You can Submit a new open access paper.