Yunfa Li | Semantic Segmentation | Best Researcher Award

Published on by Computer Vision Awards

Best Researcher Award

Yunfa Li — Hangzhou Dianzi University, China

Yunfa Li
Affiliation Hangzhou Dianzi University
Country China
Scopus ID 8731557900
Documents 52
Citations 261
h-index 7
Subject Area Semantic Segmentation
Event Global Tech Excellence Awards
ORCID 0000-0002-6889-8481

Yunfa Li is a researcher affiliated with Hangzhou Dianzi University whose documented scholarly profile includes work spanning semantic segmentation, few-shot learning, and recommendation systems. The research record includes studies addressing lightweight segmentation architectures and meta-learning-based recommendation, reflecting methodological interests in machine learning and intelligent information processing. [1] [2] [3]

Abstract

Yunfa Li’s research profile reflects scholarly activity in semantic segmentation, few-shot learning, meta-learning, and recommendation systems. His work includes lightweight semantic segmentation through dynamic prototype flow and synergistic optimization, together with studies addressing cross-domain recommendation and user cold-start recommendation. These contributions indicate an interest in developing adaptable machine learning methods that improve representation, knowledge transfer, model efficiency, and generalization under limited-data conditions. His documented publication record, citation activity, and research outputs provide a basis for considering his work within contemporary artificial intelligence research, particularly where semantic understanding and learning efficiency intersect with practical intelligent information processing applications. [1] [2] [3]

Keywords

  • Semantic Segmentation
  • Few-Shot Learning
  • Dynamic Prototype Learning
  • Meta-Learning
  • Cross-Domain Recommendation
  • Cold-Start Recommendation
  • Artificial Intelligence

Introduction

Semantic segmentation requires models to assign meaningful labels to image regions while maintaining discrimination between classes. Recent few-shot approaches seek effective segmentation despite limited annotated examples. Li and collaborators address this challenge through DPFNet, which uses dynamic prototype flow and synergistic optimization to connect prototype refinement, feature fusion, adaptive decoding, and contrastive learning within a lightweight architecture. [1]

Research Profile

Li’s documented research profile encompasses computer vision and recommendation-oriented machine learning. The publication set demonstrates engagement with semantic segmentation, cross-domain recommendation, and user cold-start recommendation, linking visual recognition with adaptive learning methods. This combination suggests a research direction centered on representation learning, model adaptation, and improving performance when training information is constrained or heterogeneous. [1] [2] [3]

Research Contributions

A principal contribution is the development of DPFNet for lightweight few-shot semantic segmentation, where dynamic prototypes are progressively refined and used across processing stages. The research also addresses recommendation through meta-learning approaches that select interests across domains and enhance knowledge transfer for cold-start users. [1] [2] [3]

Publications

The identified publications illustrate methodological breadth across semantic segmentation and recommendation. DPFNet presents a lightweight few-shot segmentation framework, while Meta-Learning Based Interest Selection examines interest selection for cross-domain recommendation. KEML develops a knowledge-enhanced meta-learning approach for user cold-start recommendation. Together, these studies represent complementary applications of adaptive learning and representation-based modeling. [1] [2] [3]

Research Impact

The research addresses practical machine learning challenges involving limited supervision, domain differences, and insufficient information about new users. DPFNet emphasizes computational efficiency alongside segmentation performance, while recommendation studies investigate adaptive knowledge transfer and preference modeling. These themes are relevant to scalable artificial intelligence systems that must generalize beyond densely supervised training environments. [1] [2] [3]

Award Suitability

Li’s documented research activity is relevant to recognition in the area of artificial intelligence and machine learning because it combines work in semantic segmentation with adaptive recommendation methodologies. The profile records 52 documents, 261 citations, and an h-index of 7, while the identified publications demonstrate continuing engagement with contemporary learning challenges. [1] [2] [3]

Conclusion

Yunfa Li’s research record demonstrates work across semantic segmentation, few-shot learning, and meta-learning-based recommendation. The identified studies address model efficiency, adaptive representation, cross-domain knowledge transfer, and cold-start learning. Collectively, these areas establish a coherent contribution to contemporary machine learning research and provide a reasonable scholarly basis for consideration for the Best Researcher Award. [1] [2] [3]

References

  1. Li, Y., Huang, Q., Li, Y., Gao, Y., Sheng, X., Yan, C., Wang, Y., & Yan, D. (2026). DPFNet: Towards lightweight few-shot semantic segmentation via dynamic prototype flow and synergistic optimization network. Neurocomputing, 705, 135004.
    https://www.sciencedirect.com/science/article/abs/pii/S0925231226024021
  2. Li, Y. (n.d.). Meta-Learning Based Interest Selection for Cross-Domain Recommendation. ResearchGate.
    https://www.researchgate.net/publication/413589400_Meta-Learning_Based_Interest_Selection_for_Cross-Domain_Recommendation
  3. Li, Y., Zhang, L., & Gao, Y. (2026). KEML: A knowledge enhanced meta-learning model for user cold-start recommendation. IEEE Transactions on Automation Science and Engineering, 23, 14492–14504.
    https://ieeexplore.ieee.org/document/11649485
  4. Elsevier. (n.d.). Scopus author details: Yunfa Li, Author ID 8731557900. Scopus.
    https://www.scopus.com/authid/detail.uri?authorId=8731557900
  5. ORCID. (n.d.). Yunfa Li ORCID record. ORCID.
    https://orcid.org/0000-0002-6889-8481

Xiaoling Zhou | Computer Vision | Best Scholar Award

Published on by Computer Vision Awards

Best Scholar Award

Xiaoling Zhou
Peking University, China

Xiaoling Zhou
Affiliation Peking University
Country China
Scopus ID 57219746593
Documents 22
Citations 85
h-index 6
Subject Area Computer Vision
Event Global Tech Excellence Awards
ORCID 0000-0002-7305-1779

Xiaoling Zhou is a researcher whose documented scholarly work spans machine learning, graph neural networks, interpretable learning, and human–machine dialogue. Her publications demonstrate an interest in developing computational methods that improve model understanding, robustness, and interaction quality. The profile is considered in the context of the Best Scholar Award and the supplied academic record.

Abstract

Xiaoling Zhou’s documented research profile reflects work across machine learning, graph neural networks, interpretable learning, and human–machine dialogue. Her publications address methodological questions involving sample weighting, graph structure, uncertainty, natural-language interaction, and computational learning systems. The research record includes studies published in established scholarly venues and indexed through academic databases. In particular, her work investigates interpretable weighting mechanisms for learning systems, approaches for reducing ineffective graph edges in Bayesian graph neural network approximations, and methods for making human–machine dialogue more natural through user-choice inference and answer generation. These contributions collectively indicate a research trajectory concerned with improving the reliability, interpretability, adaptability, and practical usefulness of intelligent computational methods.[1][2][3]

Keywords

Computer Vision; Machine Learning; Graph Neural Networks; Bayesian Learning; Interpretable Learning; Sample Weighting; Human–Machine Dialogue; Natural Language Processing; Reverse Question Answering; Artificial Intelligence.

Introduction

Xiaoling Zhou’s research is situated within artificial intelligence and computational learning, with documented studies addressing interpretable learning, graph neural networks, and intelligent dialogue. These areas are connected by a common interest in improving how computational models learn from data, represent information, and respond to users. Her publications provide evidence of this interdisciplinary direction.[1][2][3]

Research Profile

The supplied academic profile records 22 documents, 85 citations, and an h-index of 6, with Computer Vision identified as the principal subject area. Her documented publications also extend into machine learning, graph-based modeling, and dialogue systems. These indicators provide a quantitative and qualitative basis for describing an active computational research profile.[1][2][3]

Research Contributions

Zhou’s documented contributions include an interpretable framework for examining sample weighting, a DropNEdge approach for addressing ineffective graph edges and over-smoothing in graph neural networks, and UCINet and SAGNet methods for user-choice inference and answer generation in dialogue. Together, these studies address learning effectiveness, model structure, uncertainty, and interaction quality.[1][2][3]

Publications

The supplied publication record includes studies appearing in IEEE Transactions on Knowledge and Data Engineering, Lecture Notes in Computer Science, and Knowledge-Based Systems. The works cover interpretable sample weighting, Bayesian graph neural network approximation, and natural human–machine dialogue. Their publication venues and DOI records provide traceable scholarly references for evaluating the research portfolio.[1][2][3]

  • Investigating the Sample Weighting Mechanism Using an Interpretable Weighting Framework — IEEE Transactions on Knowledge and Data Engineering, 36(5), 2041–2055. DOI: 10.1109/TKDE.2023.3316168.[1]
  • Drop “Noise” Edge: An Approximation of the Bayesian GNNs — Pattern Recognition, Lecture Notes in Computer Science, pp. 59–72. DOI: 10.1007/978-3-031-02444-3_5.[2]
  • Increasing naturalness of human–machine dialogue: The users’ choices inference of options in machine-raised questions — Knowledge-Based Systems, 243, 108485. DOI: 10.1016/j.knosys.2022.108485.[3]

Research Impact

The supplied profile reports 85 citations and an h-index of 6 across 22 documents, indicating measurable scholarly visibility. Beyond these metrics, the cited studies address practical and methodological problems in artificial intelligence, including data weighting, graph learning, uncertainty, and dialogue understanding. Their themes support continued relevance to intelligent computational systems and applications.[1][2][3]

Award Suitability

Based on the supplied research record, Xiaoling Zhou demonstrates characteristics relevant to a Best Scholar Award, including a sustained publication record, measurable citation activity, and research spanning several connected areas of artificial intelligence. The documented studies show methodological engagement with learning systems and intelligent interaction, providing a reasonable scholarly basis for recognition.[1][2][3]

Conclusion

Xiaoling Zhou’s documented scholarship presents a coherent contribution to artificial intelligence through studies of interpretable learning, graph neural networks, and human–machine dialogue. The combination of publication activity, citation indicators, and technically focused research provides a substantive basis for academic recognition. The record also suggests continued potential for interdisciplinary development in intelligent systems.[1][2][3]

References

  1. Zhou, X., Wu, O., & Li, M. (2024). Investigating the sample weighting mechanism using an interpretable weighting framework. IEEE Transactions on Knowledge and Data Engineering, 36(5), 2041–2055.
    https://ieeexplore.ieee.org/document/10254261
  2. Zhou, X., & Wu, O. (2022). Drop “Noise” Edge: An approximation of the Bayesian GNNs. In Pattern Recognition: 6th Asian Conference, ACPR 2021, Revised Selected Papers (pp. 59–72). Springer.
    https://link.springer.com/chapter/10.1007/978-3-031-02444-3_5
  3. Zhou, X., Wu, O., & Jiang, C. (2022). Increasing naturalness of human–machine dialogue: The users’ choices inference of options in machine-raised questions. Knowledge-Based Systems, 243, 108485. Elsevier.
    https://www.sciencedirect.com/science/article/abs/pii/S0950705122002064
  4. Elsevier. (n.d.). Scopus author details: Xiaoling Zhou, Author ID 57219746593. Scopus.
    https://www.scopus.com/authid/detail.uri?authorId=57219746593

Jianjun Zhang | Deep Learning for Computer Vision | Best Innovation Award

Published on by Computer Vision Awards

Prof. Jianjun Zhang | Deep Learning for Computer Vision | Best Innovation Award

Teacher | Guangzhou Huali College | China

Prof. Jianjun Zhang is an academic researcher specializing in business administration education, digital intelligence, and the integration of big data and AI in higher education. He has authored over 30 publications indexed in CNKI, including one SCI paper and two EI-indexed works, reflecting steady scholarly impact. Zhang has led seven national and provincial research projects and collaborates with multidisciplinary teams on digital transformation in education. His work emphasizes virtual simulation and intelligent learning systems to enhance teaching efficiency and practical skill development. Recognized as a “double-qualified” educator, he effectively bridges theory and practice, contributing to workforce readiness and innovation in modern business education.

 

Profiles : ORCID

 

Featured Publications

Zhao Zhao | Computer Vision for Robotics and Autonomous Systems | Research Excellence Award

Published on by Computer Vision Awards

Mr. Zhao Zhao | Computer Vision for Robotics and Autonomous Systems | Research Excellence Award

Tianjin University | Canada

Mr. Zhao Zhao is a researcher at Tianjin University specializing in intelligent transportation systems, autonomous mobile robot (AMR) scheduling, and sustainable urban logistics. His work focuses on optimization models integrating energy consumption, time-dependent electricity pricing, and real-world operational constraints. He has published in leading journals including Transportation Research Part C and International Journal of Production Research. Zhao has collaborated with international institutions such as Tsinghua University, Sichuan University, Tilburg University, and KEDGE Business School, and with industry partners including Toyota Tianjin and Hikvision, contributing to large-scale AMR deployment and innovative last-mile delivery solutions with significant societal and sustainability impact.

Documents Metrics (ORCID)

4

3

2

1

0

Documents
1

🟥 Documents

View ORCID Profile

Featured Publications


In-plant autonomous mobile robot scheduling and routing problem considering battery consumption model.

– Transportation Research Part C: Emerging Technologies  (2025). Cited By : 1

Yanli Shi | Deep Learning for Computer Vision | Best Innovation Award

Published on by Computer Vision Awards

Dr. Yanli Shi | Deep Learning for Computer Vision | Best Innovation Award

Jilin University of Chemical Technology | China

Dr. Yanli Shi is a researcher at the Jilin Institute of Chemical Technology, Jilin, China, with recognized contributions in image processing, computer vision, and intelligent information technologies. As a first author, Dr. Shi has published nearly 20 high-quality SCI and EI-indexed journal articles, including three papers in JCR Zone 1 journals, reflecting strong research impact and international visibility. According to Scopus, Dr. Shi’s work has received 160 citations, with an h-index of 7, demonstrating consistent scholarly influence.Dr. Shi has led and successfully completed several competitive research projects, including one project funded by the Jilin Provincial Natural Science Foundation, one project under the “13th Five-Year Plan” Science and Technology Program of the Jilin Provincial Department of Education, and one vertical project supported by the Jilin Municipal Science and Technology Bureau, which also included the Outstanding Young Talent Cultivation Program. These projects have advanced both fundamental research and applied technological development.With a strong emphasis on technology transfer and practical innovation, Dr. Shi holds one national invention patent and has actively translated research outcomes into industrial solutions. Through extensive collaboration, Dr. Shi has participated in over 100 horizontal projects with Inner Mongolia University and local enterprises, generating more than 1.6 million yuan in research funding. These collaborations have addressed real-world technical challenges and promoted regional industrial and technological development.Dr. Shi’s recent publications in leading journals such as Pattern Recognition and Scientific Reports further highlight expertise in fine-grained visual classification, deep learning, and image super-resolution. Overall, Dr. Shi’s work demonstrates a balanced integration of academic excellence, cross-sector collaboration, and measurable societal and economic impact.

Profile: Scopus 

Featured Publications

1.Shi, Y., et al. (2025). Multi-scale adversarial diffusion network for image super-resolution. Scientific Reports.  Cited By: 1

2.Shi, Y., et al. (2025). LDH-ViT: Fine-grained visual classification through local concealment and feature selection. Pattern Recognition. Cited By : 1

Dr. Yanli Shi research advances state-of-the-art computer vision and image intelligence technologies, bridging fundamental algorithms with real-world industrial applications. Through high-impact publications, patented innovations, and extensive university–industry collaborations, the work delivers scalable solutions to practical technical challenges. This integration of scientific excellence and technology transfer contributes meaningfully to societal development and global innovation.

Abu Hanzala | Deep Learning for Computer Vision | Research Excellence Award

Published on by Computer Vision Awards

Mr. Abu Hanzala | Deep Learning for Computer Vision | Research Excellence Award

Research Assistant | Daffodil International University | Bangladesh

Mr. Abu Hanzala Daffodil International University, Dhaka, BangladeshHanzala, Abu is an emerging researcher specializing in artificial intelligence–driven medical image analysis, deep learning, and explainable healthcare systems. The researcher’s scholarly work focuses on developing robust hybrid and ensemble learning frameworks that integrate convolutional neural networks (CNNs), vision transformers (ViTs), graph neural networks (GNNs), transfer learning, self-supervised learning, and attention mechanisms for disease detection and classification.A key research achievement includes the publication of a peer-reviewed article in Array (2025) titled “A Hybrid Approach for Cervical Cancer Detection: Combining D-CNN, Transfer Learning, and Ensemble Models”, which demonstrates improved diagnostic accuracy using advanced ensemble strategies. In addition, the researcher has several manuscripts under peer review in high-impact international journals including Scientific Reports Neuroscience, IEEE Transactions on Medical Imaging, ACM Transactions on Computing for Healthcare, Discover Applied Science and Computers & Education: Artificial Intelligence. These studies address a wide range of clinically significant problems such as cervical, lung, and colorectal cancer, Alzheimer’s disease pneumonia neuromuscular disorders peripheral nerve disease and cerebral cortex pathology.The researcher has authored 5 scholarly documents receiving 5 citations, and currently holds an h-index of 2, reflecting a growing academic impact within the medical AI research community. International visibility is further strengthened through a peer-reviewed IEEE conference paper and an invited oral presentation at the 15th International Conference on Computing Communication and Networking Technologies (ICCCNT 2024).Research collaborations span multidisciplinary teams involving computer scientists biomedical engineers and healthcare researchers. The societal impact of this work lies in advancing early disease detection reliable clinical decision support and explainable AI models contributing to scalable trustworthy and globally relevant healthcare technologies.

Profiles: Scopus | ResearchGate

Featured Publication

1. Hanzala, A., Akter, T., & Rahman, M. S. (2025). A hybrid approach for cervical cancer detection: Combining D-CNN, transfer learning, and ensemble models. Cited By : 3

Mr. Abu Hanzala research advances global healthcare innovation by integrating reliable, explainable artificial intelligence with medical imaging to enable early disease detection and data-driven clinical decision support. This work bridges scientific rigor and real-world applicability, contributing to scalable, trustworthy AI solutions with meaningful societal and clinical impact.

Divya Nimma | Applications of Computer Vision | Women Researcher Award

Published on by Computer Vision Awards

Assist. Prof. Dr. Divya Nimma | Applications of Computer Vision | Women Researcher Award

Assistant Professor | Arkansas Tech University | United States

Dr. Divya Nimma is an accomplished researcher and Assistant Professor at Arkansas Tech University, specializing in Computer Vision, Artificial Intelligence, Image Processing, and Machine Learning. With a strong interdisciplinary footprint, she has contributed extensively to domains spanning environmental monitoring, healthcare analytics, intelligent transportation cybersecurity and immersive technologies. She has published 46 scholarly works and accumulated over 326 citations, with an h-index of 10 and i10-index of 10, underscoring her growing global research influence.Dr. Nimma’s research portfolio reflects a commitment to developing intelligent systems for real-world impact. Her notable contributions include climate-responsive modeling of freshwater ecosystems remote sensing–based marine life assessment for food security transformer-driven object detection , and advanced deep learning frameworks for image forensics and semantic segmentation. She has led and co-authored high-impact studies published in Scientific Reports IEEE Transactions Alexandria Engineering Journal Desalination and Water Treatment Remote Sensing in Earth Systems Sciences and other reputed journals.Her collaborative research spans international teams across the United States  Europe the Middle East  and Asia. Significant works include attention-based models for real-time surveillance explainable AI pipelines for fingerprint recognition IoT-enabled energy management for EV charging predictive maintenance in Industry 4.0 and multisource wearable data analytics for human activity recognition.Dr. Nimma has also made influential contributions to biomedical informatics including cancer detection using optimized deep learning osteoporosis classification and non-invasive brain stimulation–based sleep stage modeling. Additionally her research extends to precision agriculture integrating drone imagery AI and consumer electronics to enhance crop optimization and sustainability.Committed to societal and technological advancement Dr. Nimma’s work demonstrates a unique synthesis of deep learning innovation domain-driven applications and cross-disciplinary collaboration positioning her as a rising scholar and impactful global contributor in modern AI-driven intelligent systems.

Profiles:  Scopus | ORCID | Googlescholar

Featured Publications

1. Nimma, D., Devi, O. R., Laishram, B., Ramesh, J. V. N., Boddupalli, S., Ayyasamy, R., et al. (2025). Implications of climate change on freshwater ecosystems and their biodiversity. Desalination and Water Treatment, 321, 100889. Cited By : 42

2. Srikanth, G., Nimma, D., Lalitha, R. V. S., Jangir, P., Kumari, N. V. S., & Arpita. (2025). Food security-based marine life ecosystem for polar region conditioning: Remote sensing analysis with machine learning model. Remote Sensing in Earth Systems Sciences, 8(1), 65–73. Cited By : 36

3. Nimma, D., Nimma, R., Rajendar, & Uddagiri. (2024). Image processing in augmented reality (AR) and virtual reality (VR). International Journal on Recent and Innovation Trends in Computing and Communication. Cited By : 27

4. Nimma, D., & Zhou, Z. (2024). IntelPVT: Intelligent patch-based pyramid vision transformers for object detection and classification. International Journal of Machine Learning and Cybernetics, 15(5), 1767–1778. Cited By : 25

5. Nimma, D., Nimma, R., & Uddagiri, A. (2024). Advanced image forensics: Detecting and reconstructing manipulated images with deep learning. International Journal of Intelligent Systems and Applications in Engineering.
Cited By : 24

Dr. Divya Nimma’s research advances intelligent vision systems that enhance environmental sustainability, healthcare diagnostics, and smart transportation. Her work integrates AI with real-world applications, driving scientific innovation that strengthens societal resilience and global technological progress.

Mohsen Edalat | Machine Learning for Computer Vision | Editorial Board Member

Published on by Computer Vision Awards

Assoc. Prof. Dr. Mohsen Edalat | Machine Learning for Computer Vision | Editorial Board Member

Associate Professor | Shiraz University | Iran

Dr. Mohsen Edalat an accomplished researcher from Shiraz University, Iran, has made notable contributions to the fields of machine learning geospatial modeling and smart agriculture. With an impressive research record comprising 39 scientific publications and over 614 citations Dr. Edalat has demonstrated sustained academic productivity and influence in computational and environmental sciences. His research emphasizes the integration of advanced data-driven algorithms with ecological and agricultural systems to enhance sustainability and decision-making processes.Among his recent works Dr. Edalat has explored diverse applications of machine learning for ecological and agricultural optimization. His 2025 publications include studies on predicting nepetalactone accumulation in Nepeta persica through machine learning and geospatial analysis modeling ecological preferences of Kentucky bluegrass under varying water conditions (Water Switzerland)  and mapping early-season dominant weeds using UAV-based imagery to support precision farming. These investigations reflect his innovative approach to merging remote sensing artificial intelligence and environmental modeling to address complex agroecological challenges.With an h-index of 11 and collaborations with more than 60 co-authors  Dr. Edalat’s work highlights strong interdisciplinary engagement and a commitment to advancing data-driven sustainability. His studies contribute not only to the scientific community but also to practical agricultural applications that promote resource efficiency and ecological resilience. Through his ongoing research Dr. Edalat continues to shape the evolving landscape of smart agriculture and environmental informatics demonstrating the global relevance and societal value of computational intelligence in natural systems.

Profiles:  Scopus | ORCID

Featured Publications

1. Edalat, M., et al. (2025). Predicting nepetalactone accumulation in Nepeta persica using machine learning algorithms and geospatial analysis. Scientific Reports.

2. Edalat, M., et al. (2025). Modeling the ecological preferences and adaptive capacities of Kentucky bluegrass based on water availability using various machine learning algorithms. Water (Switzerland).

3. Edalat, M., et al. (2025). Early season dominant weed mapping in maize field using unmanned aerial vehicle (UAV) imagery: Towards developing prescription map. Smart Agricultural Technology.

Dr. Mohsen Edalat’s research integrates machine learning, geospatial analytics, and agricultural science to enhance crop management and environmental sustainability. His innovative work advances precision agriculture, supporting data-driven decisions that improve resource efficiency, boost food security, and promote sustainable development at a global scale.

Benito Farina | Spatio-Temporal CV | Best Researcher Award

Published on by Computer Vision Awards

Mr. Benito Farina | Spatio-Temporal CV | Best Researcher Award

Researcher | Universidad Politecnica de Madrid | Spain

Benito Farina is a dedicated researcher in artificial intelligence, machine learning, and biomedical engineering with a strong focus on medical imaging, cancer screening, and predictive modeling. He completed his bachelor’s and master’s degrees in Biomedical Engineering with highest honors at Università degli Studi di Napoli Federico II, where his theses explored machine learning for breast cancer histopathology and deep learning models for lung nodule malignancy detection. He pursued his doctoral studies in Electrical Engineering at Universidad Politécnica de Madrid, graduating with distinction for his research on spatio-temporal image analysis methods to enhance lung cancer screening and therapy response prediction. Professionally, he gained extensive experience as a Junior Research Scientist at Universidad Politécnica de Madrid, where he developed AI-based medical imaging datasets, implemented advanced models including CNNs, RNNs, and transformers, and explored generative models and explainable AI for clinical applications. He later joined the Centro de Investigación Biomédica en Red as a Research Scientist, leading projects in medical image segmentation, classification, and interpretability, managing GPU-based deployments, and contributing to international collaborations and grant proposals. His international exposure includes visiting scientist positions at Harvard University’s Brigham and Women’s Hospital, where he worked on image harmonization techniques to improve consistency in multi-center datasets. His research interests lie in artificial intelligence for healthcare, medical image processing, radiomics, generative models, self-supervised learning, and explainable AI with a vision of translating computational tools into clinical practice. Throughout his career, he has guided undergraduate and master’s students, actively contributed to competitive AI challenges, and engaged in cultural leadership as Vice-President of a community association promoting cultural heritage and development. He has presented his research at reputed conferences, published in indexed journals, and continues to expand his academic contributions through collaborative projects. His research skills include proficiency in Python, R, MATLAB, TensorFlow, PyTorch, and Keras, expertise in GPU cluster computing, dataset development, model deployment with Docker, and technical documentation with LaTeX. Fluent in Italian, Spanish, and English, he thrives in multicultural academic environments and has demonstrated both technical excellence and leadership capabilities. Benito has earned academic distinctions for his outstanding performance in higher education and doctoral research, reflecting his commitment to excellence. With strong foundations in artificial intelligence and biomedical engineering, he aspires to drive advancements in precision medicine, foster global collaborations, and translate AI innovations into impactful healthcare solutions.

Profile: Google Scholar | Scopus Profile | ORCID Profile

Featured Publications

Farina, B., Guerra, A. D. R., Bermejo-Peláez, D., Miras, C. P., Peral, A. A., & others. (2023). Integration of longitudinal deep-radiomics and clinical data improves the prediction of durable benefits to anti-PD-1/PD-L1 immunotherapy in advanced NSCLC patients. Journal of Translational Medicine, 21(1), 174.

Farina, B., Guerra, A. D. R., Miras, C. P., Madueño, G. G., Muñoz-Barrutia, A., & others. (2021). Delta-radiomics signature for prediction of survival in advanced NSCLC patients treated with immunotherapy. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) (pp. 886–890). IEEE.

Farina, B., Benito, R. C., Montalvo-García, D., Bermejo-Peláez, D., Maceiras, L. S., & others. (2025). Spatio-temporal deep learning with temporal attention for indeterminate lung nodule classification. Computers in Biology and Medicine, 196, 110813.

Ramos-Guerra, A. D., Farina, B., Rubio Pérez, J., Vilalta-Lacarra, A., & others. (2025). Monitoring peripheral blood data supports the prediction of immunotherapy response in advanced non-small cell lung cancer based on real-world data. Cancer Immunology, Immunotherapy, 74(4), 120.

Seijo, L., Bermejo-Peláez, D., Gil-Bazo, I., Farina, B., Domine, M., & others. (2023). Integration of longitudinal deep-radiomics and clinical data improves the prediction of durable benefits to anti-PD-1/PD-L1 immunotherapy in advanced NSCLC patients. Journal of Translational Medicine, 21(1), 174.

Bolaños, M. C., Farina, B., Guerra, A. D. R., Miras, C. P., Madueño, G. G., & others. (2020). Design and implementation of predictive models based on radiomics to assess response to immunotherapy in non-small-cell lung cancer. In XXXVIII Congreso Anual de la Sociedad Española de Ingeniería Biomédica.

Assoc Prof Dr. Qi Jia | Object Detection and Recognition | Best Researcher Award

Published on by Computer Vision Awards

Assoc Prof Dr. Qi Jia | Object Detection and Recognition | Best Researcher Award

Qi Jia at Dalian University of Technology, China

👨‍🎓 Profiles

Scopus

Google Scholar

Publications

Temporal refinement and multi-grained matching for moment retrieval and highlight detection

  • Authors: Zhu, C., Zhang, Y., Jia, Q., Wang, W., Liu, Y.
  • Journal: Multimedia Systems
  • Year: 2025

Bilevel progressive homography estimation via correlative region-focused transformer

  • Authors: Jia, Q., Feng, X., Zhang, W., Pu, N., Sebe, N.
  • Journal: Computer Vision and Image Understanding
  • Year: 2025

PMGNet: Disentanglement and entanglement benefit mutually for compositional zero-shot learning

  • Authors: Liu, Y., Li, J., Zhang, Y., Pu, N., Sebe, N.
  • Journal: Computer Vision and Image Understanding
  • Year: 2024

WBNet: Weakly-supervised salient object detection via scribble and pseudo-background priors

  • Authors: Wang, Y., Wang, R., He, X., Jia, Q., Fan, X.
  • Journal: Pattern Recognition
  • Year: 2024

A rotation robust shape transformer for cartoon character recognition

  • Authors: Jia, Q., Chen, X., Wang, Y., Ling, H., Latecki, L.J.
  • Journal: Visual Computer
  • Year: 2024