Qiang Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qiang Zeng has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Hongxia Wang
Sichuan University
4 shared publications - Rui Zhang
School of Cyber Science and Engineering and the Key Laboratory of Data Protection and Intelligent Management, Ministry of Education, Sichuan University, Chengdu, China
4 shared publications - Yang Zhou
MiLM Plus, Xiaomi Inc
3 shared publications Hanqing Liu
1 shared publication- Hanqing Liu
School of Cyber Science and Engineering and the Key Laboratory of Data Protection and Intelligent Management, Ministry of Education, Sichuan University, Chengdu, China
1 shared publication - Mingshan Du
Sichuan University, Chengdu, China
1 shared publication
Latest Publications
- 29 November 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
Dual-decoding branch contrastive augmentation for image manipulation localization
- 29 November 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
Dual-decoding branch contrastive augmentation for image manipulation localization
- 2 September 2024
- Published by Elsevier in Applied Soft Computing
- Vol. 166
Generalized face forgery detection with self-supervised face geometry information analysis network
- 2 September 2024
- Published by Elsevier in Applied Soft Computing
- Vol. 166
Generalized face forgery detection with self-supervised face geometry information analysis network
- 14 May 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 252
Semi-supervised image manipulation localization with residual enhancement
- 14 May 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 252
Semi-supervised image manipulation localization with residual enhancement
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8749-8759
UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization
The emergence of artificial intelligence-generated content (AIGC) has raised concerns about the authenticity of multimedia content in various fields. However, existing research for forgery content detection has focused mainly on binary classification tasks of complete videos, which has limited applicability in industrial settings. To address this gap, we propose UMMAFormer, a novel universal transformer framework for temporal forgery localization (TFL) that predicts forgery segments with multimodal adaptation. Our approach introduces a Temporal Feature Abnormal Attention (TFAA) module based on temporal feature reconstruction to enhance the detection of temporal differences. We also design a Parallel Cross-Attention Feature Pyramid Network (PCA-FPN) to optimize the Feature Pyramid Network (FPN) for subtle feature enhancement. To evaluate the proposed method, we contribute a novel Temporal Video Inpainting Localization (TVIL) dataset specifically tailored for video inpainting scenes. Our experiments show that our approach achieves state-of-the-art performance on benchmark datasets, including Lav-DF, TVIL, and Psynd, significantly outperforming previous methods. The code and data are available at https://github.com/ymhzyj/UMMAFormer/.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8749-8759
Open AccessUMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization
The emergence of artificial intelligence-generated content (AIGC) has raised concerns about the authenticity of multimedia content in various fields. However, existing research for forgery content detection has focused mainly on binary classification tasks of complete videos, which has limited applicability in industrial settings. To address this gap, we propose UMMAFormer, a novel universal transformer framework for temporal forgery localization (TFL) that predicts forgery segments with multimodal adaptation. Our approach introduces a Temporal Feature Abnormal Attention (TFAA) module based on temporal feature reconstruction to enhance the detection of temporal differences. We also design a Parallel Cross-Attention Feature Pyramid Network (PCA-FPN) to optimize the Feature Pyramid Network (FPN) for subtle feature enhancement. To evaluate the proposed method, we contribute a novel Temporal Video Inpainting Localization (TVIL) dataset specifically tailored for video inpainting scenes. Our experiments show that our approach achieves state-of-the-art performance on benchmark datasets, including Lav-DF, TVIL, and Psynd, significantly outperforming previous methods. The code and data are available at https://github.com/ymhzyj/UMMAFormer/.