Welcome to My Homepage!

I’m Zuheng Ming, a tenured assistant professor (Maître de conférences) of computer science with L2TI of Institut Galilée in Université Sorbonne Paris Nord (formerly Université Paris-XIII). Before, I was a lecturer-researcher (Enseignant-Cheurcheur Contactuel) in the computer science department with L3i at La Rochelle University. I have been also a postdoc in the L3i Lab of La Rochelle University supervised by Pr. Jean-Christophe Burie and Pr. Muriel Visani. I spent also one year and a half as a postdoc in the LaBRI of the University of Bordeaux supervised by Pr. Aurélie Bugeau. I obtained my Ph.D. degree from the Gipsa-lab of the University of Grenoble Alpes supervised by Pr. Gang Feng and Dr. Denis Beautemps. Prior to coming to France, I obtained the MSc degree from Beijing Institute of Technology and BSc degree from Hunan University in China.

Research Interests:

• computer vision, multimodal learning, deep learning
• document analysis, biometric, remote sensing, medical image processing

News :

• [11/2024]: Our paper GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification has been accepted by WACV 2025 !
• [06/2024]: Our paper MULTIMODAL TRANSFORMER USING CROSS-CHANNEL ATTENTION FOR OBJECT DETECTION IN REMOTE SENSING IMAGES has been accepted by ICIP 2024(Oral presentation)! Congratulations Bissmella Bahaduri !
• [05/2024]: I will be serving as Technical Committee of NeurIPS 2024!
• [02/2024]: We are organizing the 12th European Workshop on Visual Information Processing (EUVIP 2024, IEEE) which will be held on 8th-11th September 2024, in Geneva, Swissland. Welcome to submit!
• [02/2024]: I will be serving as Program Committee of ICDAR 2024!
• [01/2024]: I will be serving as Technical Committee of ICIP 2024!
• [05/2023]: I will serve as a session chair at Symposium International Francophone sur l'Ecrit et le Document (SIFED 2023)!
• [02/2023]: We are organizing the ICIP2023 Challenge Object Detection Under Uncontrolled Acquisition Environment and Scene Context Constraints with University Paris Scalay and NTNU ! Welcome to submit!
• [02/2023]: Our paper of multimodal learning for document image classification VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification has been accepted by Pattern Recognition (JCR Q1, IF 8.51)!
• [01/2023]: We are organizing the 11th European Workshop on Visual Information Processing (EUVIP, IEEE) which will be held on 11th-14th September 2023, in Gjøvik, Norway. Welcome to submit!
• 07/2022: We are organizing a Special Issue "Deep Learning Approach for Secure and Trustworthy Biometric System" on Electronics. Welcome to submit!
• [06/2022]: Our paper Video-based Transformer for face anti-spoofing entitled ViTransPAD has been accepted in ICIP2022!
• [05/2022]: Our work VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification is submitted to Pattern Recognition!
• [03/2022]: Our work using firstly Video-based Transformer for face anti-spoofing entitled ViTransPAD is online!
• [03/2022]: Our paper working on multimodal cross self-attention for document images classification passes to the second round review of IJCAI-ECAI 2022.
• [02/2022]: Our paper entitled "Exploring Multi-Tasking Learning in Document Attribute Classification" is accepted at Pattern Recognition Lettres.
• [01/2022]: I will be serving as Technical Committee of ICPR 2022!
• [01/2022]: I will be serving to organize DAS 2022, hope to meet more researchers in La Rochelle, France!
• [10/2021]: Our paper entitled "MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis" is accepted at Jounal of Computer Optics.
• [09/2021]: Our paper entitled "EAML: ensemble self-attention-based mutual learning network for document image classification" is accepted at International Journal on Document Analysis and Recognition .
• [08/2021]: We release the new benchmark for Identity Document Analysis: MIDV-2020! [Download].
• [06/2021]: Our paper entitled "Cross-modal photo-caricature face recognition based on dynamic multi-task learning" is accepted at International Journal on Document Analysis and Recognition .

Academic Activities :

Guest Editor:

• Special Issue "Deep Learning Approach for Secure and Trustworthy Biometric System" on MDPI Electronics (IF=2.69)

Organising scientific activities:

• 12th European Workshop on Visual Information Processing (EUVIP 2024, IEEE)
• ICIP2023 Challenge Object Detection Under Uncontrolled Acquisition Environment and Scene Context Constraints
• 11th European Workshop on Visual Information Processing (EUVIP 2023, IEEE)
• 15TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS2022)
• 20th International Conference on Computational Linguistics and Intelligent Text Processing, 2019]

Invited Conference Reviewer:

• ICASSP 2025
• ICLR 2025
• NeurIPS 2025
• DAS 2024
• ICIP 2024, 2023
• ICDAR 2024, 2019, 2017
• ICPR 2022,2020,2018
• PRICAI 2022,2021

Invited Journal Reviewer:

• IEEE Transactions on Information Forensics and Security (IEEE TIFS, JCR Q1)
• IEEE Transactions on Multimedia (IEEE TMM, JCR Q1)
• IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT, JCR Q1)
• Pattern Recognition (PR, JCR Q1)
• Neural Networks (NN, JCR Q1)
• EURASIP Journal on Image and Video Processing(Springer, JCR Q2)
• Neurocomputing (Springer, JCR Q2)
• Signal Processing (ELSEVIER, JCR Q2)
• Computer Vision and Image Understanding (Springer, JCR Q2)
• International Journal on Document Analysis and Recognition (Springer IJDAR, JCR Q2)
• Signal Image and Video Processing (Springer, JCR Q4)