Jiaya Jia (賈佳亞) is a Chinese researcher holding a PhD who is affiliated with Fudan University and The Hong Kong University of Science and Technology (HKUST).^[1] He serves as a Chair Professor of the Department of Computer Science and Engineering at HKUST, Director of the university's John von Neumann Institute, and Chairman of SmartMore.^[1,12] An IEEE Fellow, Jia is the associate editor-in-chief of the IEEE journal Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and serves on the editorial board of the International Journal of Computer Vision (IJCV).^[2,12]

From March 2003 to August 2004, he was a visiting scholar at Microsoft. He obtained his PhD degree in computer science jointly from Hong Kong University of Science and Technology and Microsoft Research in 2004. Jiaya Jia joined CUHK in 2004 as an assistant professor, and was promoted to full professor in 2015. He conducted collaborative research at Adobe Research in 2007.

In 2000, Jiaya Jia obtained his bachelor's degree from Fudan University and subsequently pursued a Ph.D. in computer vision at the Hong Kong University of Science and Technology (HKUST). He is a distinguished scientist, Fellow of the Institute of Electrical and Electronics Engineers (IEEE), Chair Professor at HKUST, and Dean of the Von Neumann Institute of HKUST, recognized as a leading international expert in computer vision, artificial intelligence, and computational imaging. Jia has led research in computer vision and related algorithm development since 2000 according to English Wikipedia, or starting in 2004 according to Chinese Wikipedia; his research team at HKUST, the DV Lab, is one of the world's largest vision AI research teams, focusing on image and video understanding, detection and segmentation, multi-modal AI, computational imaging, practical optimization, and advanced learning for visual content.^[3] Over his research career of more than 20 years, he has published more than 200 top-tier papers, with his work cited over 80,000 times on Google Scholar with an H-index of 110+ according to English Wikipedia, compared to over 100,000 citations and an H-index exceeding 120 according to Chinese Wikipedia. He has also been selected multiple times for the "World's Top 2% Scientists" career-long and single-year scientific impact rankings by Stanford University and the Elsevier database.

Jia has served as an associate editor of IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)—becoming the first Chinese associate editor in the vision field since the journal's founding 42 years ago—and as its associate editor-in-chief since 2021, while also serving on the editorial board of the International Journal of Computer Vision (IJCV). He has served for years as an area chair for major international AI conferences, including ICCV, CVPR, AAAI, and ECCV, and on the program committees of major graphics and computational imaging conferences such as ICCP, SIGGRAPH, and SIGGRAPH Asia. Jia has mentored over 40 to 50 PhDs, fellows, and master's students who are active in academia and industry and have become prominent AI tech leaders as professors, directors in major research labs, and founders of successful startups. Among his former students, Xu Li serves as the Co-founder, Executive Chairman of the Board, and CEO of SenseTime; Lu Cewu is a professor in the Department of Computer Science and Engineering at Shanghai Jiao Tong University; and Liu Shu and Li Ruiyu joined Jia in founding SmartMore.

Professor Jia is also a leading figure in Hong Kong's science and technology innovation. In 2019, seizing transformative opportunities in global Industry 4.0, he founded SmartMore Group, serving as its Chairman, and led a research team applying artificial intelligence and advanced large language model technologies to smart manufacturing by developing next-generation smart manufacturing platforms, highly intelligent manufacturing R&D systems, and industrial foundation models to promote intelligent upgrades and digital transformation in the industrial manufacturing sector. SmartMore rapidly became a unicorn enterprise within 18 months, has served nearly 300 large global manufacturing enterprises, and in June 2024 became the first strategic partner enterprise of the Hong Kong SAR Government's wholly owned Hong Kong Investment Corporation (HKIC), contributing to Hong Kong's "new industrialization." For his contributions, Jia received the "Hong Kong Innovation Leader Award 2021", was honored in 2022 as a "Distinguished Leader" and "Young Science and Technology Innovation Pioneer" in Hong Kong, and in February 2023 was awarded the "Hong Kong Innovation Entrepreneur of the Year Award," the highest accolade of the inaugural Hong Kong Innovation Entrepreneur Awards.

Jiaya Jia is among the world's leading experts in computer vision, having made outstanding contributions to computer vision technology, algorithms, and engineering, and has been selected for consecutive years into the "World's Top 2% Scientists" list jointly released by Stanford University and the Elsevier Data Repository, securing spots each year on both the "Career Long" and "Single Year" scientific impact lists. Over a research career spanning more than 20 years, he has published over 200 top-tier papers, with citations exceeding 100,000 and an H-index surpassing 120. His research partners include numerous renowned multinational technology companies, such as Microsoft, Qualcomm, Adobe, Intel, NVIDIA, Amazon, and Lenovo. Jia has also cultivated a number of outstanding talents with Master's and PhD degrees who continue to engage in scientific research and development in computer vision.^[4]

His research directions encompass computer vision, large X models, deep learning, machine learning, and computational imaging. These topics include semantic segmentation and instance segmentation, image recognition and classification, 3D detection, segmentation, and reconstruction, filtering, deblurring, and super-resolution, motion estimation, depth estimation, and general image matching. Many technologies in image analysis and processing developed by Jia remain leading in the field worldwide. His achievements in image deblurring, filtering, image sparse processing, multi-band image signal fusion and enhancement, large-scale motion estimation, and texture- and structure-based layering have been published in top industry conferences and publications and implemented in real-world technologies. These achievements have demonstrated outstanding performance and effectiveness in deployed systems, and most have been open-sourced to enable wider applications across industries such as aviation, medical imaging, safety and security management, robotic design, and meteorological analysis.

In 2011, Professor Jiaya Jia's team published the paper "Image Smoothing via L0 Gradient Minimization," innovatively proposing a gradient-based smoothing method that removes smaller gradients while preserving larger gradients (image edges), implemented with extremely simple code, making it the most cited paper of SIGGRAPH Asia 2011. On December 12, 2023, Jia's team won the inaugural "Test of Time Award" established by the premier computer graphics conference SIGGRAPH Asia for this paper. This award aims to recognize papers that have had a sustained impact on the field of computer graphics and interactive techniques over the past decade. On December 3, 2024, as SIGGRAPH Asia 2024 was held in Tokyo, Japan, Jia's team once again won the "Test of Time Award" for their paper "Structure Extraction from Texture via Relative Total Variation".

In his over 20 years of research experience, Jiaya Jia has published more than 200 top papers that have been cited more than 80,000 times. According to the website of The Chinese University of Hong Kong in August 2021 and the HKUST website in August 2024, he has published over 200 scientific papers in books, journals, and academic conferences, such as "Motion Deblurring: Algorithms and Systems", "Computer Vision - A Reference Guide", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Journal of Computer Vision (IJCV), Conference on Computer Vision and Pattern Recognition (CVPR), International Conference on Computer Vision (ICCV), and European Conference on Computer Vision (ECCV).

Representative papers include: Jiaya Jia: Mathematical Models and Practical Solvers for Uniform Motion Deblurring (in Motion Deblurring: Algorithms and Systems), Cambridge University Press, ISBN 9781107044364, 2014; Jiaya Jia: "Matte Extraction" Book: Computer Vision - A Reference Guide, Springer, ISBN 9780387307718 Editor-in-chief: Ikeuchi, Katsushi; Jiaya Jia, Chi-Keung Tang: Image Stitching Using Structure Deformation, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Vol. 30, No. 4, 2008; Jiaya Jia, Jian Sun, Chi-Keung Tang, Heung-Yeung Shum: Drag-and-Drop Pasting, ACM Transactions on Graphics (also in SIGGRAPH 2006), Vol. 25, No. 3, 2006; Xiaojuan Qi, Zhengzhe Liu, Renjie Liao, Philip HS Torr, Raquel Urtasun, Jiaya Jia: GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Accepted.

Honors and awards include being named an ACM Fellow. In competitive benchmarks, achievements include winning 1st Place in the ImageNet Scene Parsing Challenge 2016 with the paper PSPNet presented in CVPR 2017. In 2017, achievements included 1st Place in the LSUN'17 Instance and Semantic Segmentation Challenges, 1st Place in the COCO Instance Segmentation Challenge 2017, and 2nd Place in the COCO Detection Challenge 2017. Additionally, 1st Place was achieved in the WAD Drivable Area Segmentation Challenge 2018.