Related references
Note: Only part of the references are listed.
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaoyi Dong et al.
Summary: This work proposes a novel face forgery detection method called Identity Consistency Transformer, which focuses on high-level semantics, specifically identity information, and detects a suspect face by finding identity inconsistency in inner and outer face regions.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Dong-Keon Kim et al.
Summary: This paper presents a face manipulation detection method based on edge region features, which outperforms other technologies in terms of accuracy and robustness.
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yonghyun Jeong et al.
Summary: This paper proposes a Bilateral High-Pass Filters (BiHPF) method for detecting frequency-level artifacts in synthesized images of generative models. It addresses the decline in performance of conventional methods when tested in unknown domains. Experimental results demonstrate that the proposed method outperforms other methods across different domains.
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Tianchen Zhao et al.
Summary: The study introduces a novel method to detect deepfake images by leveraging the inconsistency of source features within forged images, demonstrating that unique source features can still be extracted after deepfake generation processes. Utilizing pair-wise self-consistency learning (PCL) to train ConvNets for feature extraction and an inconsistency image generator (I2G) to provide annotated data, experimental results show significant improvements in model performance.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yinglin Zheng et al.
Summary: This research introduces a novel end-to-end framework for video face forgery detection that utilizes temporal coherence. By combining a fully temporal convolution network and a Temporal Transformer network, the framework is able to extract temporal features and explore long-term temporal coherence effectively.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Davide Cozzolino et al.
Summary: ID-Reveal is a new approach for detecting DeepFake forgery by learning temporal facial features specific to how a person moves while talking, without the need for training data of fakes. It demonstrates improved generalization and robustness against low-quality videos compared to state-of-the-art methods.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zekun Sun et al.
Summary: Deepfakes is a malicious technique involving transplanting faces in videos, LRNet proposes an efficient framework for detecting such videos by utilizing temporal modeling and precise geometric features, showing robustness even with highly compressed or noise corrupted videos, with an AUC of 0.999 on the FaceForensics+ + dataset.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Loc Trinh et al.
Summary: In this paper, a novel human-centered approach using dynamic prototypes for detecting forgery in face images is proposed. The Dynamic Prototype Network (DPNet) achieves competitive predictive performance on various testing datasets and provides easy referential explanations of deepfake dynamics. The model's compliance to desired temporal behaviors is checked through temporal logic specifications, enhancing trustworthiness in critical detection systems.
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021)
(2021)
Proceedings Paper
Computer Science, Information Systems
Shruti Agarwal et al.
2020 IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY (WIFS)
(2020)
Article
Computer Science, Software Engineering
Justus Thies et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)
