Publications

@article{tian_design_2025,

title = {Design of Realistic and Artistically Expressive 3D Facial Models for Film AIGC: A Cross-Modal Framework Integrating Audience Perception Evaluation},

author = {Y. Tian and X. Li and Z. Cheng and Y. Huang and T. Yu},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105013137724&doi=10.3390%2Fs25154646&partnerID=40&md5=8508a27b693f0857ce7cb58e97a2705c},

doi = {10.3390/s25154646},

issn = {14248220 (ISSN)},

year  = {2025},

date = {2025-01-01},

journal = {Sensors},

volume = {25},

number = {15},

abstract = {The rise of virtual production has created an urgent need for both efficient and high-fidelity 3D face generation schemes for cinema and immersive media, but existing methods are often limited by lighting–geometry coupling, multi-view dependency, and insufficient artistic quality. To address this, this study proposes a cross-modal 3D face generation framework based on single-view semantic masks. It utilizes Swin Transformer for multi-level feature extraction and combines with NeRF for illumination decoupled rendering. We utilize physical rendering equations to explicitly separate surface reflectance from ambient lighting to achieve robust adaptation to complex lighting variations. In addition, to address geometric errors across illumination scenes, we construct geometric a priori constraint networks by mapping 2D facial features to 3D parameter space as regular terms with the help of semantic masks. On the CelebAMask-HQ dataset, this method achieves a leading score of SSIM = 0.892 (37.6% improvement from baseline) with FID = 40.6. The generated faces excel in symmetry and detail fidelity with realism and aesthetic scores of 8/10 and 7/10, respectively, in a perceptual evaluation with 1000 viewers. By combining physical-level illumination decoupling with semantic geometry a priori, this paper establishes a quantifiable feedback mechanism between objective metrics and human aesthetic evaluation, providing a new paradigm for aesthetic quality assessment of AI-generated content. © 2025 Elsevier B.V., All rights reserved.},

note = {Publisher: Multidisciplinary Digital Publishing Institute (MDPI)},

keywords = {3D faces, 3d facial model, 3D facial models, 3D modeling, adaptation, adult, Article, Audience perception evaluation, benchmarking, controlled study, Cross-modal, Face generation, Facial modeling, facies, Feature extraction, feedback, feedback system, female, Geometry, High-fidelity, human, illumination, Immersive media, Lighting, male, movie, Neural radiance field, Neural Radiance Fields, perception, Quality control, Rendering (computer graphics), Semantics, sensor, Three dimensional computer graphics, Virtual production, Virtual Reality},

pubstate = {published},

tppubtype = {article}

}

@article{wu_geospatial_2024,

title = {Geospatial Big Data: Survey and Challenges},

author = {J. Wu and W. Gan and H. -C. Chao and P. S. Yu},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85200804056&doi=10.1109%2FJSTARS.2024.3438376&partnerID=40&md5=63c39a7c302e6d9ff055633efab0349a},

doi = {10.1109/JSTARS.2024.3438376},

issn = {21511535 (ISSN); 19391404 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},

volume = {17},

pages = {17007–17020},

abstract = {In recent years, geospatial big data (GBD) has obtained attention across various disciplines, categorized into big Earth observation data and big human behavior data. Identifying geospatial patterns from GBD has been a vital research focus in the fields of urban management and environmental sustainability. This article reviews the evolution of GBD mining and its integration with advanced artificial intelligence techniques. GBD consists of data generated by satellites, sensors, mobile devices, and geographical information systems, and we categorize geospatial data based on different perspectives. We outline the process of GBD mining and demonstrate how it can be incorporated into a unified framework. In addition, we explore new technologies, such as large language models, the metaverse, and knowledge graphs, and how they could make GBD even more useful. We also share examples of GBD helping with city management and protecting the environment. Finally, we discuss the real challenges that come up when working with GBD, such as issues with data retrieval and security. Our goal is to give readers a clear view of where GBD mining stands today and where it might go next. © 2024 Elsevier B.V., All rights reserved.},

note = {Publisher: Institute of Electrical and Electronics Engineers Inc.},

keywords = {Artificial intelligence, artificial intelligence (AI), Behavioral Research, Big Data, Data challenges, Data Mining, Data surveys, Data visualization, Earth observation data, Environmental management, environmental protection, Geo-spatial, Geo-spatial analysis, Geo-spatial data, Geospatial big data, geospatial big data (GBD), geospatial data, GIS, Green products, Human behaviors, Knowledge graph, Knowledge graphs, satellite, sensor, spatial data, Sustainable development, urban planning},

pubstate = {published},

tppubtype = {article}

}

@article{lazaroiu_cognitive_2024,

title = {Cognitive digital twin-based Internet of Robotic Things, multi-sensory extended reality and simulation modeling technologies, and generative artificial intelligence and cyber–physical manufacturing systems in the immersive industrial metaverse},

author = {G. Lǎzǎroiu and T. Gedeon and K. Valaskova and J. Vrbka and P. Suler and K. Zvarikova and K. Kramárová and Z. Rowland and V. Stehel and L. Gajanova and J. Horák and M. Grupac and Z. Caha and R. Blazek and E. Kovalova and M. Nagy},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205958936&doi=10.24136%2Feq.3131&partnerID=40&md5=69dbbdf37b26620b052e5fd1624f7c49},

doi = {10.24136/eq.3131},

issn = {1689765X (ISSN); 23533293 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {Equilibrium. Quarterly Journal of Economics and Economic Policy},

volume = {19},

number = {3},

pages = {719–748},

abstract = {Research background:Connected Internet of Robotic Things (IoRT) and cyber-physical process monitoring systems, industrial big data and real-time event analytics, and machine and deep learning algorithms articulate digital twin smart factories in relation to deep learning-assisted smart process planning, Internet of Things (IoT)-based real-time production logistics, and enterprise resource coordination. Robotic cooperative behaviors and 3D assembly operations in collaborative industrial environments require ambient environment monitoring and geospatial simulation tools, computer vision and spatial mapping algorithms, and generative artificial intelligence (AI) planning software. Flexible industrial and cloud computing environments necessitate sensing and actuation capabilities, cognitive data visualization and sensor fusion tools, and image recognition and computer vision technologies so as to lead to tangible business outcomes. Purpose of the article: We show that generative AI and cyber–physical manufacturing sys-tems, fog and edge computing tools, and task scheduling and computer vision algorithms are instrumental in the interactive economics of industrial metaverse. Generative AI-based digital twin industrial metaverse develops on IoRT and production management systems, multi-sensory extended reality and simulation modeling technologies, and machine and deep learning algorithms for big data-driven decision-making and image recognition processes. Virtual simulation modeling and deep reinforcement learning tools, autonomous manufacturing and virtual equipment systems, and deep learning-based object detection and spatial computing technologies can be leveraged in networked immersive environments for industrial big data processing. Methods: Evidence appraisal checklists and citation management software deployed for justifying inclusion or exclusion reasons and data collection and analysis comprise: Abstrackr, Colandr, Covidence, EPPI Reviewer, JBI-SUMARI, Rayyan, RobotReviewer, SR Accelerator, and Systematic Review Toolbox. Findings & value added: Modal actuators and sensors, robot trajectory planning and computational intelligence tools, and generative AI and cyber–physical manufacturing systems enable scalable data computation processes in smart virtual environments. Ambient intelligence and remote big data management tools, cloud-based robotic cooperation and industrial cyber-physical systems, and environment mapping and spatial computing algorithms improve IoT-based real-time production logistics and cooperative multi-agent controls in smart networked factories. Context recognition and data acquisition tools, generative AI and cyber– physical manufacturing systems, and deep and machine learning algorithms shape smart factories in relation to virtual path lines, collision-free motion planning, and coordinated and unpredictable smart manufacturing and robotic perception tasks, increasing economic per-formance. This collective writing cumulates and debates upon the most recent and relevant literature on cognitive digital twin-based Internet of Robotic Things, multi-sensory extended reality and simulation modeling technologies, and generative AI and cyber–physical manufacturing systems in the immersive industrial metaverse by use of evidence appraisal checklists and citation management software. © 2024 Elsevier B.V., All rights reserved.},

note = {Publisher: Institute of Economic Research},

keywords = {cognitive digital twin, cyber–physical manufacturing system, Extended reality, generative artificial intelligence, immersive industrial metaverse, Internet of Robotic Things, sensor, simulation modeling},

pubstate = {published},

tppubtype = {article}

}

@article{gura_mobile_2023,

title = {Mobile Biometric and Sentiment Data, Generative Artificial Intelligence and Behavior Tracking Tools, and Wearable Sensor-based and Connected Monitoring Devices in Immersive Interconnected 3D Worlds},

author = {K. Gura and A. Alakoum and M. Melenciuc and S. Henley},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85183910376&doi=10.22381%2Fam22202314&partnerID=40&md5=922b56d89b74d73accdb0bc587c5570f},

doi = {10.22381/am22202314},

issn = {15848574 (ISSN); 24710849 (ISSN)},

year  = {2023},

date = {2023-01-01},

journal = {Analysis and Metaphysics},

volume = {22},

pages = {255–273},

abstract = {Despite the relevance of generative artificial intelligence and virtual reality immersive training tools shaping virtual employee engagement, productivity improvements, and long-term talent pipelines, only limited research has been conducted on this topic. The contribution to the literature is by showing that Web3 technology-based immersive remote work experiences can be achieved by use of generative artificial intelligence and mobile analytics algorithms, text mining and analytics, and body-tracking data metrics. Throughout July 2023, a quantitative literature review of the Web of Science, Scopus, and ProQuest databases was performed, with search terms including “generative artificial intelligence and behavior tracking tools” + “mobile biometric and sentiment data,” “wearable sensorbased and connected monitoring devices,” and “immersive interconnected 3D worlds.” As research published in 2023 was inspected, only 167 articles satisfied the eligibility criteria, and 51 mainly empirical sources were selected. Data visualization tools: Dimensions (bibliometric mapping) and VOSviewer (layout algorithms). Reporting quality assessment tool: PRISMA. Methodological quality assessment tools include: AXIS, Dedoose, Distiller SR, and MMAT. © 2024 Elsevier B.V., All rights reserved.},

note = {Publisher: Addleton Academic Publishers},

keywords = {behavior tracking tool, connected monitoring devices, generative artificial intelligence, Immersive, mobile biometric and sentiment data, sensor, wearable},

pubstate = {published},

tppubtype = {article}

}