Cunjian Chen

Ph.D. West Virginia University Postdoc Michigan State University Email / Google Scholar / Github / Group

Cunjian Chen obtained his Ph.D. in Computer Science from West Virginia University under the supervision of Arun Ross and Antitza Dantcheva. Before joining Monash, he worked as a Senior Research Associate at Michigan State University with Arun Ross. His research interests focus on Generative Models and their applications in Computer Vision. He is also a Senior Member of IEEE and leads the Image and Vision Group.

Research Interests

• Generative AI, Computer Vision, Deep Learning, Medical Image Analysis.

Research Opportunities

• Several paid RA/Intern positions are available. We seek highly motivated students interested in AI-generated content (AIGC) with a strong background in mathematics and programming. Preference will be given to applicants with publications in top venues. If you are interested, please send me your CV.

Updates

• [04/2025] Latte was accepted by TMLR!

• [03/2025] I am serving as an Associate Editor for IEEE SMC 2025.

• [03/2025] LatentSync was released on arXiv.

• [03/2025] I am serving as an Area Chair for IJCB 2025.

• [02/2025] Cinemo paper was accepted by CVPR 2025.

• [01/2025] I am serving as an Area Chair for ICIP 2025.

• [01/2025] One paper on Medical Segmentation was accepted by Neurocomputing.

• [12/2024] I am serving as a Senior Program Committee for IJCAI 2025.

• [12/2024] Invited to join as a Senior Program Committee for ECAI 2025.

• [12/2024] Invited to become an Area Chair for ICME 2025.

• [12/2024] Invited to become an Area Chair for IJCNN 2025.

• [12/2024] One paper on Multimodal Language Models was released on arXiv.

• [12/2024] One paper on Skeleton-OOD was accepted by Neurocomputing.

• [11/2024] One paper on Medical Segmentation was accepted by PAA.

• [10/2024] LaVie was accepted by IJCV.

• [09/2024] One paper on Adversarial Purification was accepted by TDSC.

• [09/2024] Our survey paper was accepted by Neurocomputing.

• [08/2024] LEO was accepted by IJCV.

• [07/2024] DiffTV was accepted by ACMMM 2024.

Selected Publications

• Latte: Latent Diffusion Transformer for Video Generation
  Xin Ma, Yaohui Wang, Gengyun Jia, Xinyuan Chen, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, Yu Qiao
  Transactions on Machine Learning Research (TMLR), April 2025
  paper | code | bib

• LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision
  Chunyu Li, Chao Zhang, Weikai Xu, Jingyu Lin, Jinghui Xie, Weiguo Feng, Bingyue Peng, Cunjian Chen, Weiwei Xing
  arXiv, March 2025
  paper | code

• Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models
  Xin Ma, Yaohui Wang, Gengyun Jia, Xinyuan Chen, Tien-Tsin Wong, Yuan-Fang Li, Cunjian Chen
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2025
  paper | code

• LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models
  Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin, Yu Qiao, Ziwei Liu
  International Journal of Computer Vision (IJCV), October 2024
  paper | code

• Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification
  Hanrui Wang, Ruoxi Sun, Cunjian Chen, Minhui Xue, Lay-Ki Soon, Shuo Wang, Zhe Jin
  IEEE Transactions on Dependable and Secure Computing (TDSC), September 2024
  paper | code

• LEO: Generative Latent Image Animator for Human Video Synthesis
  Yaohui Wang, Xin Ma, Xinyuan Chen, Cunjian Chen, Antitza Dancheva, Bo Dai, Yu Qiao
  International Journal of Computer Vision (IJCV), August 2024
  

• DiffTV: Identity-Preserved Thermal-to-Visible Face Translation via Feature Alignment and Dual-Stage Conditions
  Jingyu Lin, Guiqin Zhao, Jing Xu, Guoli Wang, Zejin Wang, Antitza Dantcheva, Lan Du, Cunjian Chen
  In Proceeding of ACM Multimedia (ACMMM), Melbourne, Australia, Oct. 2024 - Nov. 2024

>>> See full publication list

Patents

• Cross-spectral Face Recognition Training and Cross-spectral Face Recognition Method
  David Anghelone, Philippe Faure, Cunjian Chen, Arun Ross, Antitza Dantcheva
  EP4198928A1, Jun. 2023

• Thermal Face and Landmark Detection Method
  David Anghelone, Philippe Faure, Cunjian Chen, Antitza Dantcheva, Valeriya Strizhkova
  EP4198927A1, Jun. 2023

Editorial Board

• IET Image Processing (Associate Editor, 2020 - 2023)

• Neural Processing Letters (Associate Editor, 2023 - Present)

Organizing Activities

• Monash University-Chongqing University Online Workshop on Advanced Computation and Life Science [MSU-CQU Workshop]

• Advances and Challenges in Face and Gesture based Security Systems (ACFGSS 2020) [FG2020 Special Session]

• Workshop on Deepfakes and Presentation Attacks in Biometrics (DeepPAB 2020) [WACV2020 Workshop]

• Recent Advances in Heterogeneous Face Recognition (HFR): Infrared-to-Visible Matching [BTAS2019 Tutorial]

Selected Services

• IEEE International Conference on Systems, Man, and Cybernetics (SMC Associate Editor 2025)

• International Joint Conference on Artificial Intelligence (IJCAI SPC 2025)

• IEEE International Conference on Multimedia and Expo (ICME Area Chair 2018-2019, 2021-2025; ICME Session Chair 2021-2022)

• IEEE International Conference on Image Processing (ICIP Area Chair 2021-2025, Session Chair 2021)

• IEEE International Joint Conference on Biometrics (IJCB Area Chair 2025)

• IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS Area Chair 2025)

• International Joint Conference on Neural Networks (IJCNN Area Chair 2025)

• European Conference on Artificial Intelligence (ECAI SPC 2024-2025)

Teaching

• FIT 5047: Fundamentals of Artificial Intelligence (S1 2022-2025, Monash)

• FIT 5201: Machine Learning (T3 2022, S1 2023-2024, Monash)

• FIT 5217: Natural Language Processing (T3 2023-2024, Monash)

• CSE 891-002: Deep Learning in Biometrics (3.66/4.0) (Spring 2020, MSU)