Shantao Ping | Computer Vision | Best Researcher Award

Mr. Shantao Ping | Computer Vision | Best Researcher Award

Associate Senior Engineer, Qiyuan Lab, China

Shantao Ping is an Associate Senior Engineer at Qiyuan Lab, specializing in computer vision, artificial intelligence, and large-scale model algorithms. With a Master’s degree in Computer Science, Shantao has a proven track record of driving innovation through cutting-edge research and development. He has contributed to over 28 research and industry projects and holds 14 national invention patents. His collaborative project with Baidu, an AI-powered medical question-answering system, significantly enhanced user engagement and earned him the prestigious Baidu Best Engineer Award. Shantao is also an active member of the Chinese Institute of Command and Control, where he continuously advances the frontiers of intelligent simulation, image processing, and natural language processing. His work focuses on solving complex engineering problems and has made substantial contributions to simulation scene construction and few-shot object recognition. Passionate about applied research, Shantao Ping is committed to shaping the future of intelligent computing through practical and scalable solutions.

Publication Profile

Education

Shantao Ping holds a Master’s degree in Computer Science from an esteemed institution, equipping him with solid expertise in artificial intelligence, computer vision, and advanced computational algorithms. He also holds the professional qualification of Associate Senior Engineer, recognized by the Ministry of Human Resources and Social Security (MOHRSS), Beijing, China. This designation reflects his deep technical proficiency and leadership in engineering research and development. Throughout his academic and professional training, Shantao focused on bridging theoretical foundations with real-world applications, emphasizing innovation in structured light calibration, simulation modeling, and machine learning-based image processing. His educational journey laid the groundwork for his current role as a highly effective engineer, capable of contributing to both research excellence and industrial breakthroughs. Shantao’s education emphasizes interdisciplinary collaboration, practical application, and a research-driven approach that aligns perfectly with his long-standing commitment to technological advancement and cutting-edge innovation in the rapidly evolving fields of AI and computer vision.

Experience

Shantao Ping is currently an Associate Senior Engineer at Qiyuan Lab, where he has spearheaded numerous high-impact projects in computer vision, AI, and simulation technologies. Over his career, he has successfully completed 28 research and consultancy projects, including a notable collaboration with Baidu to develop an AI-powered medical Q&A system that significantly improved user engagement metrics. His career highlights include leading teams in the development of large-scale model algorithms, simulation scene construction, and few-shot object recognition frameworks. Shantao’s practical experience is reinforced by 14 published or in-process patents and multiple software development achievements, including tools for multi-type algorithm execution and sonar simulation imaging. His work has consistently demonstrated high relevance to industry needs and national innovation strategies. Recognized with the Baidu Best Engineer Award, Shantao continues to push the boundaries of applied AI and intelligent systems. He is also actively involved in the Chinese Institute of Command and Control, enhancing his contributions to the field.

Research Focus

Shantao Ping’s research is primarily centered on computer vision, image processing, natural language processing (NLP), and foundation models. His work addresses critical challenges in simulation scene reconstruction, few-shot object recognition, structured light calibration, and human-computer interaction assisted by large models. He focuses on developing algorithms that integrate simulation with AI to achieve realistic scene modeling and real-time data processing. Shantao is particularly interested in the intersection of AI and simulation, leveraging intelligent algorithms to enhance perception, decision-making, and scene understanding in complex environments. His innovative research in multi-object tracking and global graph matching is paving the way for advanced applications in autonomous systems and smart interaction platforms. Through national patents and practical deployments, he has made significant strides in developing intelligent, scalable solutions that are not only theoretically sound but also practically impactful, contributing directly to the fields of healthcare, simulation technology, and large-scale data interaction.

Publication Top Notes

  1. Multi-view Multi-object Tracking Based on Global Graph Matching Structure (Conference Paper)

    • Authors: Shantao Ping, Chao Li, Hao Sheng, Jiahui Chen, Zhang Xiong

    • Summary: This work proposes a novel global graph matching framework for tracking multiple objects across multiple viewpoints, significantly improving tracking accuracy in complex scenes.

  2. A Method and Apparatus for Specific Target Reconnaissance by Unmanned Aerial Vehicle (Patent)

    • Authors: Shantao Ping, Ying He

    • Summary: Introduces a UAV-based reconnaissance system with enhanced precision for specific target detection in dynamic environments.

  3. A Method, Apparatus, and Device for 3D Scene Construction (Patent)

    • Authors: Shantao Ping, Xulong Ma, Ying He

    • Summary: Details a system for efficient 3D scene modeling using intelligent algorithms, optimizing both speed and accuracy.

  4. Method for Human-Computer Interaction Assisted by Large Models (Patent)

    • Authors: Shantao Ping, Xulong Ma, Ying He, Xiaoqiang Jin, Pinjie Li, Qianchuan Zhao

    • Summary: Presents a human-computer interaction framework enhanced by large foundational models for improved user experience and system adaptability.

  5. Method, Apparatus, Device, and Storage Medium for Generating Sonar Simulated Images (Patent)

    • Authors: Shantao Ping, Xulong Ma, Ying He, Jiacheng Li

    • Summary: Describes a sonar image simulation method that increases the fidelity and reliability of underwater detection simulations.

Conclusion

Shantao Ping is a highly capable, application-driven researcher with an impressive track record of industry-relevant projects, innovative patents, and impactful collaborations, particularly in AI and computer vision. The strong applied research portfolio and demonstrated ability to solve real-world problems make him a solid candidate for the Best Researcher Award. However, to fully align with the traditional benchmarks of this award (which often emphasize academic citations and international recognition), increasing the number of SCI/Scopus journal publications, improving citation metrics, and pursuing more visible academic leadership roles would be beneficial.

Amine Mansouri | Computer Vision | Best Researcher Award

Mr Amine Mansouri | Computer Vision | Best Researcher Award

Mr Amine Mansouri, University of Burgundy, France

Amine Mansouri is a dedicated Ph.D. candidate in Instrumentation and Image Computing at SPIM Doctoral School, affiliated with the ImViA Research Laboratory, Université de Bourgogne. Supervised by Toufik Bakir, his research focuses on advancing computer vision and machine learning models for image recognition and signal processing. Amine’s expertise spans multiple disciplines, including electronics, control systems, and automation. He holds multiple degrees in these fields from both Université de Bourgogne and USTHB, Algeria. Throughout his academic journey, he has published several influential research papers in reputable journals and presented at international conferences. In addition to his research contributions, Amine has experience teaching advanced topics like medical imaging, multispectral imaging, and control systems to undergraduate and master’s students. His deep passion for machine learning and computer vision drives his ambition to contribute to technological innovations that enhance automation and intelligent systems.

Strengths For the Award

  1. Academic Excellence: Mansouri has consistently performed well academically, ranking at the top of his classes during his studies in France and Algeria.
  2. Research Contributions: His publications in high-impact journals, including works on human action recognition, deep learning applications, and machine vision, display expertise in a niche area of AI and image processing.
  3. Technical Skills: Proficiency in multiple programming languages and tools such as Python, C/C++, Matlab, and LabVIEW. He has practical experience in computer vision, machine learning, and instrumentation.
  4. Project Work: Demonstrated hands-on experience with various projects related to detection and tracking using advanced technologies such as YOLO-v3 and OpenCV, along with hardware implementation experience.
  5. Teaching and Mentorship: Extensive teaching experience at Université de Bourgogne, supervising engineering interns, and playing a vital role in academic jury responsibilities.
  6. Involvement in Conferences and Community Engagement: Active participation in international conferences, organization committees, and peer-review work enhances his reputation in the research community.

Areas for Improvement

  1. Broader Application of Research: Expanding the practical applications of his work beyond image processing, such as exploring interdisciplinary areas, might increase the impact of his research.
  2. Collaborations: Greater international collaborations or partnerships with industry could further enhance his research’s visibility and applicability.

Education 

Amine Mansouri pursued an extensive academic path that led to his Ph.D. in Instrumentation and Image Computing from Université de Bourgogne (2021-2024). His research, under the supervision of Toufik Bakir, focuses on advanced computer vision and machine learning models. Prior to this, Amine completed two master’s degrees: one in Image and Vision (2020-2021), where he ranked 3rd in a cohort of 12, and another in Electronics, Signal, and Image (EEA/TSI) (2019-2020), where he ranked 3rd out of 36 students. He also obtained a bachelor’s degree in Electronics from the same institution, achieving the highest rank (1st out of 30) in his class. Amine’s early education includes a master’s degree in Industrial Automation and Process (2017-2018) and a bachelor’s degree in Control Systems (2016-2017) from USTHB, Algeria. His consistent academic performance reflects a strong foundation in electronics, automation, and signal processing.

Experience 

Amine Mansouri brings a wealth of academic and research experience, particularly in the fields of computer vision and automation. He has been involved in numerous teaching roles at Université de Bourgogne, handling tutorials and practicals for modules like Medical Imaging, Multispectral Imaging, Control Systems, Signal Processing, and Electronics. In addition to teaching, Amine actively participates in research and conference activities, having served on organizing committees and as a reviewer for journals such as Elsevier’s Image and Vision Computing. He also contributes to student supervision, overseeing final-year engineering interns working on computer vision projects. Beyond his academic engagements, Amine has worked on innovative projects, including the design and hardware implementation of computer vision systems for human action recognition and concrete structure inspections. His expertise in both research and hands-on projects demonstrates a commitment to bridging theoretical knowledge with practical applications.

Research Focus 

Amine Mansouri’s research primarily revolves around the development of computer vision algorithms, machine learning models, and their applications in signal processing. His Ph.D. work at the Université de Bourgogne delves into improving human action recognition systems by integrating deep learning techniques with advanced image processing models. His recent projects include developing YOLO-v3 models for bird detection and tracking, skeleton-based action recognition using CNN-GCN models, and deep learning approaches for concrete structure inspection. Amine is particularly interested in fusing different data modalities, such as infrared and radar images, to enhance the accuracy of recognition systems. His research also extends into time series analysis, forecasting trends in financial markets using deep learning architectures. Through his publications, Amine explores the intersection of computer vision, deep learning, and signal processing, aiming to contribute to innovations that address real-world challenges in automation and intelligent systems.

Publication Top Notes

  • 🖼️ Human Action Recognition with Skeleton and Infrared Fusion Model – Journal of Image and Graphics, 2023
  • 🤖 Improved Semantic Guided Network for Skeleton-Based Action Recognition – Journal of Visual Communication and Image Representation, 2024
  • 💻 Design and Hardware Implementation of CNN-GCN Model for Skeleton-Based Human Action Recognition – IEEE CSCC Conference, Heraklion, 2024
  • 📊 A Contribution to Time Series Analysis and Forecasting Using Deep Learning Approaches – IEEE ICCAD Conference, Paris, 2024
  • 🏗️ Concrete Structure Inspection Based on Deep Learning Approaches from Visible and Radar Images – Sixteenth International Conference on Quality Control by Artificial Vision, 2023
  • 💸 Ethereum Cryptocurrency Entry Point and Trend Prediction using Bitcoin Correlation and Multiple Data Combination – International Journal of Advanced Computer Science and Applications, 2023

Conclusion

Amine Mansouri demonstrates remarkable research ability and commitment to academic excellence, making him well-suited for the Best Researcher Award. He excels in technical skills, academic teaching, and impactful research contributions. With slight improvements in broader application and collaborations, his work could achieve even greater influence in the field.