Renshuai Tao

I am an Associate Professor at the School of Computer Science and Technology, BJTU, working in collaboration with Prof. Yao Zhao (IEEE Fellow). I received my B.S. and Ph.D. degrees from BUAA in 2017 and 2022, respectively, under the supervision of Prof. Wei Li (Academician of Chinese Academy of Sciences) and Prof. Xianglong Liu. Previously, I was a Senior Researcher at Noah’s Ark Lab, Huawei, collaborating with Dr. Yunhe Wang.

My research focuses on two major directions: AI Robustness and Generalization and Vision-Language Models and Benchmarking. The first direction encompasses AI Safety and Security, including Digital Image Content Forensics, DeepFake Detection, and Forensic Watermarking, as well as Open-world Learning, which aims to improve machine learning adaptability in real-world scenarios through Open-set Learning, Domain Adaptation, and Few-shot Learning. The second direction focuses on Vision-Language Models, leveraging large-scale pre-training approaches like CLIP and ALIGN to enhance cross-modal understanding, alongside Evaluation Benchmarking, where I develop rigorous assessments for critical yet underexplored areas to advance research and innovation.

[Prospective students] Our group (BJTU) has positions for PhD students, Master students, and visiting students. If you are interested, please feel free to send me an email with your CV and publications (if any).

news

Feb 27, 2025	One paper is accepted by CVPR 2025. Congrates to Haoyu, Yuzhe, Hairong and other co-authors!
Dec 14, 2024	One paper is accepted by IEEE TMM.
Dec 10, 2024	Four papers are accepted by AAAI 2025 (oral presentation, 4.6%). Congrates to Manyi, Chuangchuang and other co-authors!
Apr 16, 2024	One paper is accepted by IJCAI 2024.
Nov 07, 2023	I join BJTU as an Associate Professor.

selected publications

AAAI

ODDN: Adddressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks

Renshuai Tao, Manyi Le, Chuangchuang Tan, Huan Liu, Haotong Qin, and Yao Zhao

In Proceedings of the AAAI Conference on Artificial Intelligence, 2025

Bib PDF

@inproceedings{tao2025oddn,
  title = {ODDN: Adddressing Unpaired Data Challenges in Open-World Deepfake Detection on Online Social Networks},
  author = {Tao, Renshuai and Le, Manyi and Tan, Chuangchuang and Liu, Huan and Qin, Haotong and Zhao, Yao},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
}

CVPR

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?

Renshuai Tao, Haoyu Wang, Yuzhe Guo, Hairong Chen, Li Zhang, Xianglong Liu, Yunchao Wei, and Yao Zhao

In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Bib PDF

@inproceedings{tao2025dual,
  title = {Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?},
  author = {Tao, Renshuai and Wang, Haoyu and Guo, Yuzhe and Chen, Hairong and Zhang, Li and Liu, Xianglong and Wei, Yunchao and Zhao, Yao},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2025},
  organization = {IEEE},
}

AAAI

C2p-clip: Injecting category common prompt in clip to enhance generalization in deepfake detection

Chuangchuang Tan^*, Renshuai Tao^*, Huan Liu, Guanghua Gu, Baoyuan Wu, Yao Zhao, and Yunchao Wei

In Proceedings of the AAAI Conference on Artificial Intelligence, 2025

Bib

@inproceedings{tan2025c2p,
  title = {C2p-clip: Injecting category common prompt in clip to enhance generalization in deepfake detection},
  author = {Tan, Chuangchuang and Tao, Renshuai and Liu, Huan and Gu, Guanghua and Wu, Baoyuan and Zhao, Yao and Wei, Yunchao},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
}

ACM MM

Few-shot x-ray prohibited item detection: A benchmark and weak-feature enhancement network

Renshuai Tao, Tianbo Wang, Ziyang Wu, Cong Liu, Aishan Liu, and Xianglong Liu

In Proceedings of the 30th ACM international conference on multimedia, 2022

Bib PDF

@inproceedings{tao2022few,
  title = {Few-shot x-ray prohibited item detection: A benchmark and weak-feature enhancement network},
  author = {Tao, Renshuai and Wang, Tianbo and Wu, Ziyang and Liu, Cong and Liu, Aishan and Liu, Xianglong},
  booktitle = {Proceedings of the 30th ACM international conference on multimedia},
  pages = {2012--2020},
  year = {2022},
}

CVPR

Exploring endogenous shift for cross-domain detection: A large-scale benchmark and perturbation suppression network

Renshuai Tao, Hainan Li, Tianbo Wang, Yanlu Wei, Yifu Ding, Bowei Jin, Hongping Zhi, Xianglong Liu, and Aishan Liu

In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Bib PDF

@inproceedings{tao2022exploring,
  title = {Exploring endogenous shift for cross-domain detection: A large-scale benchmark and perturbation suppression network},
  author = {Tao, Renshuai and Li, Hainan and Wang, Tianbo and Wei, Yanlu and Ding, Yifu and Jin, Bowei and Zhi, Hongping and Liu, Xianglong and Liu, Aishan},
  booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {21157--21167},
  year = {2022},
  organization = {IEEE},
}

ICCV

Towards real-world X-ray security inspection: A high-quality benchmark and lateral inhibition module for prohibited items detection

Renshuai Tao, Yanlu Wei, Xiangjian Jiang, Hainan Li, Haotong Qin, Jiakai Wang, Yuqing Ma, Libo Zhang, and Xianglong Liu

In Proceedings of the IEEE/CVF international conference on computer vision, 2021

Bib PDF

@inproceedings{tao2021towards,
  title = {Towards real-world X-ray security inspection: A high-quality benchmark and lateral inhibition module for prohibited items detection},
  author = {Tao, Renshuai and Wei, Yanlu and Jiang, Xiangjian and Li, Hainan and Qin, Haotong and Wang, Jiakai and Ma, Yuqing and Zhang, Libo and Liu, Xianglong},
  booktitle = {Proceedings of the IEEE/CVF international conference on computer vision},
  pages = {10923--10932},
  year = {2021},
  organization = {IEEE},
}

ACM MM

Occluded prohibited items detection: An x-ray security inspection benchmark and de-occlusion attention module

Yanlu Wei^*, Renshuai Tao^*, Zhangjie Wu, Yuqing Ma, Libo Zhang, and Xianglong Liu

In Proceedings of the 28th ACM international conference on multimedia, 2020

Bib PDF

@inproceedings{wei2020occluded,
  title = {Occluded prohibited items detection: An x-ray security inspection benchmark and de-occlusion attention module},
  author = {Wei, Yanlu and Tao, Renshuai and Wu, Zhangjie and Ma, Yuqing and Zhang, Libo and Liu, Xianglong},
  booktitle = {Proceedings of the 28th ACM international conference on multimedia},
  pages = {138--146},
  year = {2020},
}