Embodied intelligence
Visual perception and multimodal learning for robots, with an interest in vision–language–action models and perception–decision systems.
ASSOCIATE PROFESSOR · NJUST
WeiZhou周威
Seeing the world.
Learning to act.
Embodied intelligence, computer vision &
multimodal foundation models.
PERCEPTION / LEARNING / ACTION
COMPUTER VISION & ROBOTICS
A LITTLE HELLO
Hi, I’m Wei Zhou. I work on vision, robotics, and multimodal AI. Helping machines see, understand, and act. One idea at a time.
CLAWD AT THE KEYBOARDHELLO, WORLD
RESEARCH WITH A REAL-WORLD PERSPECTIVEScroll to explore ↓
60+Papers in the past five years
6Research projects as principal investigator
6Journal editorial board roles
PUBLISHED IN
- NeurIPS
- ACM Computing Surveys
- IEEE Trans. Industrial Informatics
- IEEE Trans. Intelligent Transportation Systems
- IEEE Trans. Intelligent Vehicles
- Robotics and Computer-Integrated Manufacturing
- Advanced Engineering Informatics
- Automation in Construction
- Engineering Applications of AI
- NeurIPS
- ACM Computing Surveys
- IEEE Trans. Industrial Informatics
- IEEE Trans. Intelligent Transportation Systems
- IEEE Trans. Intelligent Vehicles
- Robotics and Computer-Integrated Manufacturing
- Advanced Engineering Informatics
- Automation in Construction
- Engineering Applications of AI
01 / ABOUTIntelligence beyond
Intelligence beyond
the screen.
I am an Associate Professor in the School of Automation at Nanjing University of Science and Technology (NJUST). My research focuses on embodied intelligence, computer vision, and multimodal foundation models, with applications in robotics and autonomous driving.
I received my Ph.D. from the School of Transportation at Southeast University in 2025 and my B.S. from NJUST in 2019. I joined NJUST in April 2025.
Research directions
Visual perception
Object detection, scene understanding, and learning with limited or cross-domain data in complex real-world environments.
Intelligent transportation
Traffic event understanding, pedestrian intention prediction, and visual perception for autonomous driving and road infrastructure.
From the labNEWS & MILESTONES
Our paper “CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors” is accepted at NeurIPS 2026. Publications ↗
Our paper on knowledge-guided soft-consensus learning for pavement crack inspection is published in Advanced Engineering Informatics. Paper ↗
Our review of closed-loop intelligent quality control for robotic welding is announced in Robotics and Computer-Integrated Manufacturing. Paper ↗
Our holistic survey of vision technologies in traffic surveillance is published online in ACM Computing Surveys. Paper ↗
I joined the School of Automation at Nanjing University of Science and Technology as an Associate Professor. Faculty profile ↗
Selected publications
Browse publications →-
2026
CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors
Advances in Neural Information Processing Systems (NeurIPS) (2026).
Accepted at NeurIPS 2026; proceedings details to appear.
BibTeX
@inproceedings{c-neurips-2026-carve, title = {{CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors}}, author = {Wei Zhou and Chenyiming and Xu Jinwei and Yang Zhou and Quan Gan and Li Yang}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2026} } -
2026online
Closed-loop intelligent quality control for robotic welding: A survey on architecture, technologies, and system integration
Robotics and Computer-Integrated Manufacturing, 103: 103375, 2027.
Online publication announced in 2026; assigned to the 2027 journal volume.
Paper ↗BibTeX
@article{j-rcim-2026-103375, title = {{Closed-loop intelligent quality control for robotic welding: A survey on architecture, technologies, and system integration}}, author = {Cheng Qiu and Wei Zhou and Li Yang and Yong Peng and Kehong Wang}, journal = {Robotics and Computer-Integrated Manufacturing}, year = {2027}, volume = {103}, pages = {103375}, doi = {10.1016/j.rcim.2026.103375} } -
2026online
Knowledge-guided soft-consensus learning for ambiguity-aware pavement crack inspection
Advanced Engineering Informatics, 77: 105264, 2027.
Online publication announced in 2026; assigned to the 2027 journal volume.
Paper ↗BibTeX
@article{j-aei-2026-105264, title = {{Knowledge-guided soft-consensus learning for ambiguity-aware pavement crack inspection}}, author = {Wei Zhou and Zhenwei Zhou and Jing Lu and Li Yang}, journal = {Advanced Engineering Informatics}, year = {2027}, volume = {77}, pages = {105264}, doi = {10.1016/j.aei.2026.105264} } -
2026
Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey
ACM Computing Surveys, 58(3): 1-47, 2026.
First published online in September 2025; volume 58, issue 3 (2026).
Paper ↗Preprint ↗BibTeX
@article{3760525, title = {{Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey}}, author = {Wei Zhou and Li Yang and Lei Zhao and Runyu Zhang and Yifan Cui and Hongpu Huang and Kun Qie and Chen Wang}, journal = {ACM Computing Surveys}, year = {2026}, volume = {58}, number = {3}, pages = {1--47}, doi = {10.1145/3760525} } -
2025
Data-Efficient Object Detection on Construction Sites Using Reweighting Mechanism and Cross-Batch Contrastive Learning
IEEE Transactions on Industrial Informatics, 21(8): 6028-6037, 2025.
Paper ↗BibTeX
@article{tii-2025-3558311, title = {{Data-Efficient Object Detection on Construction Sites Using Reweighting Mechanism and Cross-Batch Contrastive Learning}}, author = {Wei Zhou and Lei Zhao and Hongpu Huang and Chen Wang}, journal = {IEEE Transactions on Industrial Informatics}, year = {2025}, volume = {21}, number = {8}, pages = {6028--6037}, doi = {10.1109/tii.2025.3558311} } -
2024
Teaching Segment-Anything-Model Domain-Specific Knowledge for Road Crack Segmentation From On-Board Cameras
IEEE Transactions on Intelligent Transportation Systems, 25(12): 20588-20601, 2024.
Paper ↗BibTeX
@article{tits-2024-3475371, title = {{Teaching Segment-Anything-Model Domain-Specific Knowledge for Road Crack Segmentation From On-Board Cameras}}, author = {Wei Zhou and Hongpu Huang and Hancheng Zhang and Chen Wang}, journal = {IEEE Transactions on Intelligent Transportation Systems}, year = {2024}, volume = {25}, number = {12}, pages = {20588--20601}, doi = {10.1109/tits.2024.3475371} }
Academic service
Editorial and young editorial board service for journals in intelligent vehicles, robotics, and transportation.
Service & experience →Beyond research
I share ideas and practical resources on visual perception and intelligent transportation through Deep Traffic, my WeChat public account.
Get in touch →