Best Researcher Award
Dinh-Thai Kim
Vietnam National University, Vietnam
Dinh-Thai Kim is a researcher affiliated with Vietnam National University whose documented research profile is situated within computer science and artificial intelligence. The available bibliometric record lists 49 documents, 194 citations, and an h-index of 8. [1] Recent publications demonstrate work spanning computer vision, deep learning, federated learning, speech emotion recognition, agricultural imaging, and Vietnamese sign-language classification.
Abstract
Dinh-Thai Kim’s research profile reflects applied artificial intelligence research addressing visual recognition, natural-language and speech-related intelligence, and machine-learning applications. Recent work includes lightweight object detection for cashew kernel assessment, growth-stage detection in lychee orchards, privacy-preserving speech emotion recognition, and graph-based Vietnamese sign-language classification. [2]–[5]
Keywords
Artificial intelligence; computer vision; deep learning; object detection; federated learning; speech emotion recognition; sign-language classification; agricultural AI.
Introduction
The research record associated with Kim illustrates the application of contemporary machine-learning methods to practical recognition problems. The publications supplied for this profile indicate an emphasis on deployable computer-vision systems and specialized intelligent models, including applications involving agricultural products, orchard monitoring, human speech, and gesture-based language recognition.
Research Profile
Kim’s documented research spans several complementary areas of artificial intelligence. The work on YOLOv8s-based lychee detection applies object-detection techniques under natural orchard conditions, while CSTAR-Det addresses lightweight vision-based assessment of cashew kernels. [2] [3] Other research extends machine learning toward Vietnamese speech emotion recognition and sign-language classification. [4] [5]
Research Contributions
- Development of lightweight vision-based approaches for agricultural quality assessment.
- Application of object detection to crop growth-stage recognition under natural conditions.
- Investigation of prototype-based federated learning for privacy-preserving speech emotion recognition.
- Use of graph convolutional networks and skeletal points for Vietnamese sign-language classification.
Publications
CSTAR-Det: A lightweight vision-based framework for conveyor-based cashew kernel quality assessment. Array, listed publication date December 2026. [2]
YOLO-Lychee: A YOLOv8s-Based Detector for Lychee Growth-Stage Detection under Natural Orchard Conditions. EAI Endorsed Transactions on AI and Robotics, 27 July 2026. [3]
EmoFedProto: Privacy-Preserving Vietnamese Speech Emotion Recognition via Prototype-Based Federated Learning. EAI Endorsed Transactions on AI and Robotics, 23 April 2026. [4]
Deep Learning Based Graph Convolutional Network Using Hand Skeletal Points For Vietnamese Sign Language Classification. Iranian Journal of Electrical and Electronic Engineering, March 2026. [5]
Research Impact
The supplied Scopus metrics record 194 citations across 49 documents, with an h-index of 8. [1] These indicators provide a quantitative view of scholarly visibility, while the publication record shows application-oriented research across multiple AI domains. Citation indicators should be interpreted in relation to publication age, field practices, and database coverage.
Award Suitability
The documented record provides evidence relevant to recognition in a research category focused on computer science and artificial intelligence. The combination of bibliometric activity and recent research involving computer vision, federated learning, and deep-learning classification offers a factual basis for consideration under the Best Researcher Award category. [1]–[5]
Conclusion
Dinh-Thai Kim’s documented research profile combines measurable scholarly activity with recent applications of artificial intelligence to agricultural vision, speech processing, privacy-preserving learning, and sign-language recognition. The available record supports a multidisciplinary description within computer science and artificial intelligence and provides the principal bibliographic and impact indicators presented on this page.
External Links
References
- Elsevier. (n.d.). Scopus author details: Dinh-Thai Kim, Author ID 57265279400. Scopus.
https://www.scopus.com/authid/detail.uri?authorId=57265279400
- Kim, Dinh-Thai. (2026). CSTAR-Det: A lightweight vision-based framework for conveyor-based cashew kernel quality assessment. Array.
https://doi.org/10.1016/j.array.2026.101282
- Kim, Dinh-Thai. (2026). YOLO-Lychee: A YOLOv8s-Based Detector for Lychee Growth-Stage Detection under Natural Orchard Conditions. EAI Endorsed Transactions on AI and Robotics.
https://doi.org/10.4108/airo.12140
- Kim, Dinh-Thai. (2026). EmoFedProto: Privacy-Preserving Vietnamese Speech Emotion Recognition via Prototype-Based Federated Learning. EAI Endorsed Transactions on AI and Robotics.
https://doi.org/10.4108/airo.11595
- Kim, Dinh-Thai. (2026). Deep Learning Based Graph Convolutional Network Using Hand Skeletal Points For Vietnamese Sign Language Classification. Iranian Journal of Electrical and Electronic Engineering.
https://doi.org/10.22068/IJEEE.22.1.3717
- ORCID. (n.d.). Dinh-Thai Kim, ORCID record.
https://orcid.org/0000-0002-9060-4769
- International Forensic Scientist Awards. (n.d.). Official award website.
forensicscientist.org
