Mr. chao zheng, manager, tencent, China.
Chao Zhen is a leading researcher in computer vision and artificial intelligence, currently heading the Computer Vision Research team at Tencent Map. He is widely recognized for his expertise in autonomous driving and machine perception. Over the years, he has driven innovation in 3D perception and semantic understanding within autonomous systems. His work regularly appears in prestigious conferences such as AAAI, ICCV, ECCV, and WACV. With a growing impact in AI and computer vision, he continues to push the boundaries of real-world applications. His collaborative research has earned accolades like the IAAI Application Innovation Award.
Publication Profile
Scopus
Google Scholar
🎓 Education Background
Chao Zhen holds a solid academic foundation in artificial intelligence and computer vision. While specific institutional details of his degrees are not publicly listed, his prolific publication record in high-impact conferences like ICCV, ECCV, and AAAI indicates deep formal training, likely at top-tier universities or research institutes. His education has equipped him with advanced theoretical and practical knowledge in machine learning, 3D scene understanding, and multimodal AI—forming the cornerstone of his success in autonomous driving research. Through continuous learning and collaboration, he has established himself as a technical leader in AI and robotics.
💼 Professional Experience
Chao Zhen currently leads the Computer Vision Research team at Tencent Map, focusing on enabling intelligent mapping and scene understanding for autonomous vehicles. His professional journey spans several years of active involvement in cutting-edge research and development of AI-powered vision systems. Under his leadership, the team contributes to next-gen perception modules and vision-language systems for driving environments. He actively collaborates with academic and industrial partners, guiding projects from prototype to deployment. His role integrates both technical depth and strategic foresight in aligning AI research with scalable real-world applications.
🏆 Awards and Honors
Chao Zhen’s outstanding contributions have been recognized with several prestigious honors, most notably the IAAI Application Innovation Award, awarded for impactful AI-driven applications. His co-authored work has gained traction in premier AI and computer vision conferences, a testament to its relevance and innovation. These accolades highlight his contributions to advancing practical autonomous driving solutions using sophisticated machine perception models. Beyond awards, his publications continue to receive high citation counts, reflecting his influence in the research community and his pivotal role in shaping the future of AI-driven transportation systems.
🔬 Research Focus
Chao Zhen’s research centers around artificial intelligence, computer vision, and machine learning, with a strong focus on 3D perception and reconstruction for autonomous driving. His work bridges data-driven learning techniques with real-world challenges, such as lidar-based segmentation, topological reasoning, and vision-language integration. He explores multimodal systems that combine point cloud data, semantic maps, and language to build robust scene understanding. Through projects like MapLM and 2DPASS, he advances scalable solutions for urban mobility. His innovations pave the way for safer, smarter, and more interpretable autonomous systems leveraging the synergy of AI modalities.
📌 Conclusion
Chao Zhen stands out as a forward-thinking AI researcher and industry leader in the realm of autonomous driving. His innovative vision and commitment to research excellence have resulted in influential publications, impactful industry contributions, and prestigious recognitions. By fusing deep technical insights with real-world needs, he is helping shape the next generation of intelligent vehicles. His ongoing efforts in 3D scene understanding, multimodal AI, and semantic modeling are not only transforming how machines perceive the world but also driving the future of intelligent transportation.
📚 Top Publications Notes
-
A Survey on Multimodal Large Language Models for Autonomous Driving
Year: 2024
Journal/Conference: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Cited by: 426 articles
-
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
Year: 2022
Journal/Conference: European Conference on Computer Vision (ECCV)
Cited by: 326 articles
-
MapLM: A Real-World Large-Scale Vision-Language Dataset for Map and Traffic Scene Understanding
Year: 2024
Journal/Conference: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by: 10 articles
-
MapLM Benchmark: Real-World Vision-Language Benchmark for Traffic Scene Understanding
Year: 2024
Journal/Conference: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by: 35 articles
-
RelTopo: Enhancing Relational Modeling for Driving Scene Topology Reasoning
Year: 2025
Journal: arXiv preprint
Cited by: In press (citation data to be updated)
-
Cross-Modal Semantic Transfer for Point Cloud Semantic Segmentation
Year: 2025
Journal: ISPRS Journal of Photogrammetry and Remote Sensing
Cited by: 1 article
-
Topo2Seq: Enhanced Topology Reasoning via Topology Sequence Learning
Year: 2025
Journal: arXiv preprint
Cited by: 1 article
-
Position: Autonomous Driving & Multimodal LLMs
Year: 2025
Journal: Winter Conference on Applications of Computer Vision (WACV)
Cited by: 8 articles