Avrajyoti Dutta | Video Analysis and Understanding | Excellence in Research Award

Published on by Computer Vision Awards

Excellence in Research Award

Avrajyoti Dutta — AGH University of Krakow
Research Profile
Affiliation AGH University of Krakow
Country Poland
Scopus ID 59407205300
Documents 3
Citations 2
h-index 1
Subject Area Video Analysis and Understanding
Event Global Tech Excellence Awards
ORCID Not publicly listed

The Excellence in Research Award recognizes scholarly engagement and emerging contributions in the field of Video Analysis and Understanding by Avrajyoti Dutta of AGH University of Krakow. The recognition highlights developing academic efforts in computational vision methodologies, video interpretation frameworks, and analytical technologies associated with intelligent multimedia systems. The award is associated with the Global Tech Excellence Awards platform, which acknowledges research-oriented achievements and scholarly participation in advancing interdisciplinary technology domains.[1]

Abstract

This article presents a structured academic overview of the research profile and scholarly relevance of Avrajyoti Dutta within the domain of Video Analysis and Understanding. The profile reflects participation in computational research connected to intelligent multimedia systems, visual analytics, and evolving machine learning methodologies. The recognition through the Excellence in Research Award framework illustrates academic engagement in advancing analytical technologies relevant to computer vision and video-based interpretation systems.[1][2]

Keywords

Video Analysis, Computer Vision, Multimedia Intelligence, Research Recognition, Machine Learning, Visual Understanding, Scholarly Contributions, Artificial Intelligence, Computational Imaging, Academic Excellence

Introduction

Video Analysis and Understanding has emerged as a significant interdisciplinary field combining artificial intelligence, multimedia processing, and computational perception technologies. Research activities in this domain commonly focus on automated scene interpretation, activity recognition, object tracking, and semantic analysis of dynamic visual data. Contemporary developments have expanded the applicability of video analytics to healthcare, surveillance, autonomous systems, and digital communication technologies.[2]

Within this context, the academic profile of Avrajyoti Dutta demonstrates involvement in computational and analytical research aligned with visual interpretation systems and intelligent multimedia processing. The scholarly recognition associated with the Excellence in Research Award reflects participation in emerging technological investigations and broader academic engagement within the global research ecosystem.[1]

Research Profile

Avrajyoti Dutta is affiliated with AGH University of Krakow in Poland and maintains an indexed research presence through the Scopus bibliographic database. The available profile data indicates research documentation connected to computational and analytical studies in multimedia and video understanding systems.[1]

The research metrics associated with the profile include three indexed scholarly documents, two recorded citations, and an h-index of one. While the publication volume reflects an emerging academic profile, the indexed contributions indicate participation in internationally visible scholarly communication platforms and technical research dissemination.[1]

  • Institutional affiliation with AGH University of Krakow.
  • Research visibility through indexed Scopus publications.
  • Academic engagement within Video Analysis and Understanding.
  • Participation in computational and multimedia research activities.

Research Contributions

The research contributions associated with the profile emphasize analytical and computational approaches relevant to intelligent visual systems. Video analysis research typically incorporates machine learning techniques, pattern recognition models, and automated semantic interpretation mechanisms for dynamic visual environments.[2]

Emerging scholarly efforts in this area contribute toward improved multimedia understanding, efficient information extraction, and automated decision-support technologies. Such developments are increasingly relevant to artificial intelligence applications requiring scalable visual processing capabilities and contextual scene interpretation methodologies.

  • Exploration of intelligent multimedia interpretation frameworks.
  • Participation in computational video analytics research.
  • Contribution to evolving machine learning methodologies for visual systems.
  • Support for interdisciplinary research involving artificial intelligence and multimedia processing.

Publications

The publication profile indexed under the Scopus Author ID reflects scholarly dissemination through academic and technical research channels. Indexed publications contribute to the visibility and traceability of emerging research activities in computational multimedia systems and analytical technologies.[1]

  1. Research contributions indexed within Scopus related to video analysis methodologies and multimedia systems.
  2. Conference-oriented and technical publications associated with intelligent analytical frameworks.
  3. Emerging interdisciplinary studies integrating artificial intelligence and computational perception technologies.

Research Impact

Research impact within early-stage academic profiles is commonly evaluated through indexed publications, citation visibility, collaborative participation, and thematic relevance within evolving scientific domains. The profile associated with Avrajyoti Dutta demonstrates initial citation activity and ongoing scholarly engagement in computational visual analysis.[1]

The broader field of Video Analysis and Understanding continues to experience substantial growth due to increasing industrial and scientific demand for automated visual intelligence systems. Contributions within this domain support advancements in intelligent surveillance, autonomous systems, healthcare diagnostics, multimedia indexing, and digital communication technologies.[2]

Award Suitability

The Excellence in Research Award framework is aligned with recognizing scholarly participation, technical innovation, and emerging research visibility within advanced scientific domains. The profile of Avrajyoti Dutta demonstrates compatibility with such recognition criteria through indexed academic contributions, institutional affiliation, and engagement with computational multimedia research themes.[1]

The association with the Global Tech Excellence Awards platform further positions the profile within an international context emphasizing technological advancement, interdisciplinary collaboration, and scholarly visibility in rapidly evolving research sectors.

  • Indexed academic presence in an internationally recognized database.
  • Research alignment with emerging artificial intelligence technologies.
  • Institutional participation in higher education and research activities.
  • Demonstrated scholarly engagement within computational multimedia domains.

Conclusion

The academic profile of Avrajyoti Dutta reflects developing scholarly engagement in Video Analysis and Understanding, supported by indexed research visibility and institutional affiliation with AGH University of Krakow. The Excellence in Research Award recognition framework acknowledges participation in advancing computational and multimedia analytical systems within contemporary technology-oriented research environments.[1]

As the field of intelligent visual analytics continues to evolve, emerging contributions in computational perception, machine learning, and multimedia understanding are expected to remain central to interdisciplinary scientific and technological progress. The documented research profile contributes to this broader academic landscape through visible participation in internationally indexed scholarly activities.[2]

References

  1. Elsevier. (n.d.). Scopus author details: Avrajyoti Dutta, Author ID 59407205300. Scopus.
    https://www.scopus.com/authid/detail.uri?authorId=59407205300
  2. Global Tech Excellence Awards. (n.d.). Official Award Platform and Recognition Program.
    https://globaltechexcellence.com/

Faisal Alamri | Object Detection for Security and Surveillance | Best Researcher Award

Published on by Computer Vision Awards

Dr. Faisal Alamri | Object Detection for Security and Surveillance | Best Researcher Award

Chairperson of the Department of Computer Science and Information Technology | Jubail Industrial College (JIC) | Saudi Arabia

Dr. Faisal Alamri is an accomplished artificial intelligence researcher specializing in computer vision, machine learning, object detection, classification, segmentation, similarity search, adversarial perturbation, and zero-shot learning. He holds a Ph.D. in Computer Science with a focus on computer vision and machine learning from the University of Exeter, and completed his undergraduate and master’s degrees in computer systems engineering and networking. He currently serves as the Computer Science Department Chairperson at Jubail Industrial College, where he oversees academic and administrative activities and leads departmental initiatives. Previously, he worked as a machine learning engineer developing practical AI solutions, a postdoctoral research fellow, and a teaching assistant, and has also contributed as an online tutor and teaching volunteer. His research interests include developing innovative approaches for object detection, image analysis, and real-world AI applications. Dr. Alamri has been recognized for his achievements through multiple certifications and active participation in international conferences, workshops, and professional communities such as IEEE, Kaggle, NVIDIA, and MATLAB. He possesses strong technical skills in Python, MATLAB, C#, SPSS, AWS, Google Cloud ML Engine, and other platforms, and has completed various professional courses in deep learning, AI, cybersecurity, and digital analytics. His dedication to research, education, and community engagement reflects his commitment to advancing both science and society. He has a total of 49 citations, 7 documents, and an h-index of 5.

Profiles: Google Scholar | Scopus | ORCID | LinkedIn

Featured Publications

  1. Alamri, F., & Dutta, A. (2021). Multi-head self-attention via vision transformer for zero-shot learning. arXiv preprint arXiv:2108.00045.

  2. Alamri, F., & Pugeault, N. (2020). Improving object detection performance using scene contextual constraints. IEEE Transactions on Cognitive and Developmental Systems, 14(4), 1320–1330.

  3. Alamri, F., & Dutta, A. (2021). Implicit and explicit attention for zero-shot learning. In DAGM German Conference on Pattern Recognition (pp. 467–483).

  4. Alamri, F., & Dutta, A. (2023). Implicit and explicit attention mechanisms for zero-shot learning. Neurocomputing, 534, 55–66.

  5. Alamri, F., Kalkan, S., & Pugeault, N. (2021). Transformer-encoder detector module: Using context to improve robustness to adversarial attacks on object detection. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 9577–9584). IEEE.

Xinrong Hu | Object Detection and Recognition | Women Researcher Award

Published on by Computer Vision Awards

Prof. Xinrong Hu | Object Detection and Recognition | Women Researcher Award

Dean of Computer Science and Artificial Intelligence | Wuhan Textile University | China

Prof. Xinrong Hu is a distinguished researcher and academic leader in computer vision, natural language processing, virtual reality, and machine learning. She serves as Dean of the School of Computer and Artificial Intelligence at Wuhan Textile University and is a doctoral supervisor, leading an innovative research team at the Hubei Provincial Engineering Technology Research Center for Garment Informatization. She holds a Ph.D. and has extensive experience in guiding research projects, including over 30 funded initiatives, some with national and international significance. Her research interests focus on advancing artificial intelligence applications in real-world scenarios, combining theoretical innovation with practical solutions. She has authored more than 100 academic papers, edited six textbooks, translated a book, and holds 26 invention patents, demonstrating her strong research skills and contribution to knowledge dissemination. Prof. Hu has been recognized with multiple awards and honors, including provincial and ministerial-level scientific research awards, teaching achievement awards, and prestigious titles such as Hubei Provincial Distinguished Teacher and recipient of the Special Government Allowance from the State Council. Her professional engagement includes leadership in academic communities, mentorship of young researchers, and active participation in advancing the field of AI through both education and research initiatives. Her comprehensive expertise, innovative contributions, and dedication to fostering academic excellence make her a leading figure in her field. Her research impact is reflected in 1,044 citations, 209 documents, and an h-index of 16.

Profiles: Scopus | ResearchGate 

Featured Publications

  1. Hu, X., et al. (2025). CDPMF-DDA: Contrastive deep probabilistic matrix factorization for drug-disease association prediction. BMC Bioinformatics.

  2. Hu, X., et al. (2025). Source-free cross-modality medical image synthesis with diffusion priors. Journal of King Saud University – Computer and Information Sciences.

  3. Hu, X., et al. (2025). TADUFMA: Transformer-based adaptive denoising and unified feature modeling for multi-condition anomaly detection in computerized flat knitting machines. Measurement Science and Technology.

  4. Hu, X., et al. (2025). ViT-BF: Vision transformer with border-aware features for visual tracking. Visual Computer.

  5. Hu, X., et al. (2025). Adaptive debiasing learning for drug repositioning. Journal of Biomedical Informatics.

Jong-Hyun Kim | Applied Visual Computing | Best Researcher Award

Published on by Computer Vision Awards

Prof. Jong-Hyun Kim | Applied Visual Computing | Best Researcher Award

Associate Professor at Inha University, South Korea

Prof. Jong-Hyun Kim is an Associate Professor at the College of Software and Convergence, Department of Artificial Intelligence, Design Technology at Inha University, with a joint appointment at the Graduate School of Electrical and Computer Engineering. He is a distinguished researcher with expertise spanning computer graphics, visual effects, physically based simulation, physics engines, artificial intelligence, VR/AR, geometry processing, and GPU optimization. His career bridges academia and industry, having led and participated in numerous national research projects and industry collaborations in areas such as digital twin technology, immersive simulation systems, and AI convergence. With an impressive record of award-winning publications in reputed conferences and journals indexed in IEEE and Scopus, he has contributed significantly to advancing emerging technologies. His leadership in collaborative initiatives and dedication to innovative research continue to strengthen his impact on both scientific communities and practical applications.

Professional Profile 

ORCID Profile

Education

Prof. Jong-Hyun Kim completed his Ph.D. in Computer Science and Engineering from Korea University, following his master’s degree and bachelor’s degree in the same field from Korea University and Sejong University, respectively. His academic journey reflects a strong foundation in both theoretical and applied aspects of computer science, equipping him with advanced skills in simulation, visualization, and artificial intelligence. His studies covered a broad spectrum of technical disciplines, from physics-based modeling and geometry processing to interactive graphics and human-computer interaction. The rigorous academic training at prestigious institutions provided him with the expertise to excel in interdisciplinary research and to address complex computational challenges. This solid educational background has enabled him to integrate advanced computing techniques with creative technological solutions, laying the groundwork for his influential research contributions in academia and his ability to collaborate effectively with industry partners on innovative projects.

Professional Experience

Prof. Jong-Hyun Kim currently serves as an Associate Professor at Inha University, having previously held the same position at Kangnam University. He has also served as a lecturer and teaching fellow at Korea University, contributing to the development of academic programs and mentoring students in advanced computing topics. Before his academic career, he worked extensively in the industry as a senior research engineer and research engineer at multiple companies, gaining hands-on experience in simulation technologies, visual effects, and interactive systems. His professional trajectory reflects a balance between academic scholarship and practical application, with roles that involved designing innovative solutions, leading research teams, and collaborating on both government-funded and industry-driven projects. His combined academic and industrial experience has strengthened his expertise in bridging theoretical research with real-world implementation, enhancing his ability to deliver impactful outcomes in both educational and technological domains.

Research Interest

Prof. Jong-Hyun Kim’s research interests cover a broad and interdisciplinary range of topics, including computer graphics, visual effects, physically based simulation, physics engines, and game physics. He actively explores artificial intelligence techniques for scientific visualization, geometry processing, image processing, and immersive VR/AR experiences. His work often focuses on GPU optimization to achieve real-time performance in complex simulations, enabling practical applications in gaming, virtual reality, and industrial simulations. Additionally, he is interested in human-computer interaction, particularly in developing intuitive interfaces for creative expression and realistic virtual environments. His projects integrate physics-based modeling with AI-driven approaches to address challenges in simulation accuracy, interactivity, and scalability. By combining deep technical expertise with creativity, his research aims to advance the capabilities of simulation and visualization technologies, making them more efficient, accessible, and adaptable for diverse fields ranging from entertainment and education to engineering and healthcare.

Award and Honor

Prof. Jong-Hyun Kim has received numerous awards and honors recognizing his excellence in research, innovation, and academic contributions. His accolades include multiple Best Paper Awards from prestigious conferences such as those organized by the Korea Society of Computer and Information and the Korean Association of Data Science, acknowledging his groundbreaking work in simulations, VR frameworks, AI-driven modeling, and GPU optimization. He has been honored by the Ministry of Science and ICT and the Korean Ministry of Education for his creative and impactful research ideas. His achievements extend beyond academia, with awards recognizing his leadership in industry-academic cooperation and excellence in teaching. These recognitions reflect his sustained contributions to advancing cutting-edge technologies, fostering collaboration between academia and industry, and mentoring future innovators. His consistent recognition at national and professional levels underscores his influence in both research and education, and his ongoing commitment to delivering impactful technological advancements.

Research Skill

Prof. Jong-Hyun Kim possesses advanced research skills in multiple technical domains, including physically based simulation, visual effects, GPU optimization, and complex animation systems. He is proficient in designing real-time interactive environments, implementing physics engines, and integrating artificial intelligence into simulation and visualization frameworks. His expertise includes scientific visualization, geometry processing, VR/AR development, and image processing, enabling him to create innovative solutions that merge creativity with computational precision. He has extensive experience managing large-scale research projects funded by national agencies and industry partners, demonstrating strong project management, team leadership, and cross-disciplinary collaboration skills. His technical abilities are complemented by his capacity to translate theoretical models into practical applications across entertainment, engineering, and scientific research. By combining analytical thinking, problem-solving, and creative design, he continues to push the boundaries of simulation and visualization technologies, contributing significantly to both academic advancements and industry innovation.

Publications Top Notes

Title: A Geometric Approach to Efficient Modeling and Rendering of Opaque Ice With Directional Air Bubbles
Authors: Jong-Hyun Kim
Year: 2025

Title: Advanced GPU Techniques for Dynamic Remeshing and Self-Collision Handling in Real-Time Cloth Tearing
Authors: Jong-Hyun Kim; Jung Lee
Year: 2025

Title: Improved Air Mesh Refinement for Accurate Strand-Solid and Self-Collision Handling
Authors: Jong-Hyun Kim
Year: 2025

Title: Neural Network-Based Projective Grid Model for Learning Representation of Surface and Wave Foams
Authors: Jong-Hyun Kim
Year: 2025

Title: Porous Models for Enhanced Representation of Saturated Curly Hairs: Simulation and Learning
Authors: Jong-Hyun Kim; Jung Lee
Year: 2025

Title: A 3D Visual Tool for Analyzing Changes in Hair Volume and Length Caused by Medications
Authors: Jong‐Hyun Kim; Jung Lee; Seungbin Kwon; Minji Jo; Yunjin Hwang; In‐Sook An
Year: 2025

Title: Numerical Dispersed Flow Simulation of Fire-Flake Particle Dynamics and Its Learning Representation
Authors: Jong-Hyun Kim; Jung Lee
Year: 2025

Title: Unified GPU Framework for Simulating Wave Turbulence, Diffusion, and Wrinkling in Fluid-Cloth Interaction
Authors: Eun Su Park; Juyong Lee; In Kyu Park; Jong-Hyun Kim
Year: 2025

Title: Scalable and Rapid Nearest Neighbor Particle Search Using Adaptive Disk Sector
Authors: Jong-Hyun Kim; Shaofeng Xu; Jung Lee
Year: 2025

Title: Depth-of-Field Region Detection and Recognition From a Single Image Using Adaptively Sampled Learning Representation
Authors: Jong-Hyun Kim; Youngbin Kim
Year: 2024

Title: Motion Generation and Analyzing the User’s Arm Muscles via Leap Motion and Its Data-Driven Representations
Authors: Jong-Hyun Kim; Jung Lee; Youngbin Kim
Year: 2024

Title: Visualization of Vector Fields from Density Data Using Moving Least Squares Based on Monte Carlo Method
Authors: Jong-Hyun Kim
Year: 2024

Title: Isoline Tracking in Particle-Based Fluids Using Level-Set Learning Representation
Authors: Jun Yeong Kim; Chang Geun Song; Jung Lee; Jong-Hyun Kim; Jong Wan Lee; Sun-Jeong Kim
Year: 2024

Title: Efficient and Stable Generation of High-Resolution Hair and Fur With ConvNet Using Adaptive Strand Geometry Images
Authors: Jong-Hyun Kim; Jung Lee
Year: 2023

Conclusion

Prof. Jong-Hyun Kim is highly deserving of the Best Researcher Award for his outstanding contributions to cutting-edge research in computer graphics, AI-driven simulation, and immersive technologies, as well as his significant role in bridging academia and industry through impactful collaborative projects. His innovative work has advanced both scientific understanding and practical applications, benefiting diverse sectors and inspiring the next generation of researchers. With a proven track record of excellence, leadership, and innovation, he holds strong potential to make even greater contributions to research and society in the future.