Yihua Cheng is a Tenure-Track Professor at the School of Computer Science, Beijing Institute of Technology. He is working on various research topics including computer vision, human-computer interaction and autonomous driving. His research focuses on understanding human behaviour and human-object interaction, generating realistic digital humans, and applying these advancements across various domains.

Yihua Cheng has published high-quality papers in top-tier venues, including TPAMI, TIP, Nature Communications, CVPR, ICCV, ECCV, AAAI, and ACM MM. He serves as a reviewer for high-level journals such as TPAMI, TIP, and Nature Human Behaviour, and was recognized as an Outstanding Reviewer for ICCV 2023. Yihua is the organizer of the Gaze Workshop at CVPR and the Autonomous Driving Workshop at WACV. He leads a Ramsay Funding project and collaborates with industry partners in autonomous driving.

Yihua Cheng was a Senior Research Fellow at the University of Birmingham. He obtained Ph.D. degree in Computer Science from Beihang University in December 2022. His Ph.D. supervisor was Prof. Feng Lu. He received B.S. degree of Computer Science from Beijing University of Posts and Telecommunications in 2017.

Please feel free to contact me for any academic or bussiness collobration.

If you are interested in Master’s, Ph.D., or internship opportunities, please feel free to contact me and attach your CV.

News

[2026-07]: 🔥I joined the School of Computer Science at Beijing Institute of Technology as a Tenure-Track Professor, beginning an exciting new chapter in my academic career.
[2026-06]: 🔥I organized the 7th International Workshop on Eye and Gaze in Computer Vision (GAZE 2026) at CVPR 2026. Thanks to all the participants for making the workshop a success.
[2026-02]: 🔥‘FoSS: Modeling Long Range Dependencies and Multimodal Uncertainty in Trajectory Prediction via Fourier State Space Integration’ is accepted to CVPR 2026.
[2025-11]: 🔥‘Force-aware 3D contact modeling for stable grasp generation’ is accpeted to AAAI 2026.
[2025-11]: 🔥‘RTGaze: Real-Time 3D-Aware Gaze Redirection from a Single Image’ is accpeted to AAAI 2026.
[2025-08]: ‘Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball Rotation’ is accepted to ACM MM 2025.
[2025-07]: ‘Efficient driving behavior narration and reasoning on edge device using large language models’ is accepted to IEEE Transactions on Vehicular Technology.
[2025-05]: I am glad to be invited to give a talk at Tsinghua University!
[2025-05]: ‘Behavior-aware Knowledge-embedded Model for Driver Attention Prediction’ is accepted to IEEE Transactions on Circuits and Systems for Video Technology.
[2025-04]: I am invited to give a talk titled “Visual Learning Towards Human Understanding, Generation, and Interaction” at the University of Southampton. It is a pleasure to meet members of the VLC group during my visit！
[2025-04]: I am invited by the Chen Institute to deliver a keynote talk entitled “Introduction to Mobile Eye Tracking Algorithms”.
[2025-03]: Multi-Hypothesis 3D Hand Mesh Recovering from a Single Blurry Image is accepted to ICME 2025.
[2025-02]: “3D Prior Is All You Need: Cross-Task Few-shot 2D Gaze Estimation” is accepted to CVPR 2025, Please find the project Here.
[2025-02]: “PersonaBooth: Personalized Text-to-Motion Generation” is accepted to CVPR 2025.
[2025-02]: “Trajectory-Mamba: An Efficient Attention-Mamba Forecasting Model Based on Selective SSM” is accepted to CVPR 2025.
[2025-01]: “Single-view Image to Novel-view Generation for Hand-Object Interactions” is accepted to AAAI 2025.
[2025-01]: “Meta-learning enables complex cluster-specific few-shot binding affinity prediction for protein-protein interactions” is accepted to JCML.
[2024-10]: Call for Paper, DDL November 22! We are organizing Human-Autonomous Vehicle Interaction Workshop (HAVI) at WACV 2025.
[2024-10]: I am invited by Prof. Yoichi Sato to give a talk titled “Eye Tracking and Generation: Challenges and Future” at the University of Tokyo.
[2024-09]: “Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction” is accepted to Nature Communication (Featured Article).
[2024-07]: “TextGaze: Gaze-Controllable Face Generation with Natural Language” is accepted to ACM MM24.
[2024-07]: “NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model” is accepted to ECCV24 (Oral Presentation).
[2024-04]: “Appearance-Based Gaze Estimation with Deep Learning: A Review and Benchmark” is accepted to TPAMI.
[2024-03]: “What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation” is accepted to CVPR2024, Please find the project Here.
[2024-03]: Call for Paper, DDL March 15 ! We are organizing GAZE Workshop at CVPR 2024. [2023-10]: One paper is accepted to WACV 2024.
[2023-08]: One paper is accepted to BMVC 2023 (Oral Presentation).
[2023-07]: “DVGaze: Dual-View Gaze Estimation” is accepted to ICCV 2023.
[2023-02]: I jointed University of Birmingham as a Postdoc.