Vision, Language and Sound (VLS)

Current advancements in digital technologies have caused an explosion in the volume and diversity of document collections, which include text, image, audio and video. This has spurred widespread interest in media-specific information retrieval and its related computational research. The VLS research group focuses on investigating techniques in managing large document collections, transforming data into computational representations and devising strategies for storage, processing, organisation, retrieval and interaction with these digital document collections. The main research fields that members are actively involved in include computer vision, natural language processing, information retrieval, image and video processing and sense-making, speech and audio processing, multimedia analytics, image security and multimodal intelligent systems.

For more information: LinkedIn, Brochure and Research Direction.

Our people:

	Name	Expertise
	Assoc. Prof. Dr. Azreen Azman (Leader) azreenazman@upm.edu.my Website: https://profile.upm.edu.my/azreenazman LinkedIn: https://www.linkedin.com/in/azreen-azman-a8844a86/	Information Retrieval, Natural Language Processing, Intelligent Systems
	Assoc. Prof. Dr. Fatimah Khalid fatimahk@upm.edu.my Website: https://profile.upm.edu.my/fatimahk LinkedIn: https://www.linkedin.com/in/fatimah-khalid-42a90542/	Computer Vision, Image Processing
	Assoc. Prof. Dr. Mas Rina Mustaffa masrina@upm.edu.my Website:  https://profile.upm.edu.my/masrina LinkedIn: www.linkedin.com/in/mas-rina-mustaffa-b9a72282	Computer Vision, Multimedia Analytics, Intelligent Systems
	Assoc. Prof. Dr. Hizmawati Madzin hizmawati@upm.edu.my Website: https://profile.upm.edu.my/hizmawati LinkedIn: https://www.linkedin.com/in/hizmawati-madzin-8237728b/	Computer Vision, Information Retrieval, Medical Imaging
	Dr. Alfian Abdul Halin alfian@upm.edu.my Website: https://profile.upm.edu.my/alfian LinkedIn: https://www.linkedin.com/in/alfian-abdul-halin-44819610/	Image and Video Processing, Computer Vision
	Dr. Nurul Amelina Nasharuddin nurulamelina@upm.edu.my Website: https://profile.upm.edu.my/nurulamelina LinkedIn: https://www.linkedin.com/in/nurulamelinanasharuddin/	Natural Language Processing, Multimedia Analytics, Intelligent Systems

Current Research Projects/Grants:

Students at Risk Prediction (SaRP) Web Plugin (Geran Pembangunan Produk Penyelidikan, UPM) — RM85,400.00
Duration: 2024 – 2026
Project Leader: Ts. Dr. Nurul Amelina Nasharuddin

AICoFE: Artificial Intelligence (AI) Competency Framework for Educators (Geran Inovasi Pengajaran dan Pembelajaran) — RM14,500.00
Duration: 2023 – 2026
Project leader: Ts. Dr. Nurul Amelina Nasharuddin

Extraction of Consolidation and Cavity in Lung CT Scan Images using Cross-Model Deep Learning Approach for Active Pulmonary Tuberculosis (PUTRA IPS) — RM20,000.00
Duration: 2023
Project Leader: Assoc. Prof. Dr Hizmawati Madzin 

Extraction of Pulmonary Cavity in Lung CT Scan using Gray Level and Level Set Segmentation Methods for Tuberculosis Severity Score (FRGS)  — RM77,700.00
Duration: 2022
Project Leader: Assoc. Prof. Dr Hizmawati Madzin

Recent Publications:

Abokadr, S., Azman, A., Hamdan, H. & Nasharuddin, N. A. (2026). Kernel-based dynamic ensemble approach for classifying imbalanced data with overlapping classes. Scientific Reports, 16, 13789. https://doi.org/10.1038/s41598-026-42940-y (WoS)

Ding, Z., Tan, Z., Madzin, H., Li, Z., & Liu, J. (2026). Refining weak supervision for robust lung cavity segmentation: A graph-affinity method with boundary constraints. PLoS ONE, 21(2), e0341717. https://doi.org/10.1371/journal.pone.0341717 (WoS)

Khalid, F. B., Singh, R. R., Shafferi, N. A., Ahlawat, T. R., Sankanur, M., Agrawal, A., ... & Mustaffa, M. R. (2025). Efficient deep learning with compressed muzzle prints for scalable buffalo identification. Journal of Theoretical and Applied Information Technology, 103(24). (Scopus)

Liu, Y., Ding, Y., Khalid, F. B., Wang, C., & Wang, L. (2026). Few-shot font generation via denoising diffusion and component-level fine-grained style. Expert Systems With Applications, 296, 128987. https://doi.org/10.1016/j.eswa.2025.128987. (WoS)

Tan, Z., Madzin, H., Sun, W., Ding, Z., Cai, F., Nie, T. & Mustaffa, M. R. Weakly Supervised Semantic Segmentation for Tuberculosis Lung Cavity Diagnosis (2026). Asia-Pacific Journal of Information Technology and Multimedia, 15(1), 140-150. https://doi.org/10.17576/apjitm-2026-1501-08 (Scopus)

Zhang, J., Mustaffa, M. R., Khalid, F. & Kahar, Z. A. (2026). SWL-YOLO: A synergistic feature fusion strategy for small object detection in remote sensing images based on YOLOv11. IEEE Access, 14, 1508–1521. https://doi.org/10.1109/ACCESS.2025.3646852 (WoS)

Zheng, S. & Nasharuddin, N. A. (2026). Structural modelling for smart healthcare: quantitative phenotype gaining network (QPGnet) for taxonomic identification of complementary medicines. PeerJ Computer Science, 12, e3917. https://doi.org/10.7717/peerj-cs.3917 (WoS).

Khalaf, A. D., Hamdan, H., Abdul Halin, A. & Manshor, N. Segmentation and Classification of Skin Cancer Diseases Based on Deep Learning: Challenges and Future Directions (2025). IEEE Access, 13, 90163-90184.  https://doi.org/10.1109/ACCESS.2025.3569170  

Mustaffa, M. R., Osman, N. S., Doraisamy, S., & Madzin, H. (2025). Fish image analysis: fusion of moment-based and directional features in colour space. Malaysian Journal of Computer Science, 38 (Special). https://doi.org/10.22452/mjcs.vol38spc.7 (WoS)

Jiang, C., Abdul Halin, A., Yang, B., Abdullah, L. N., Manshor, N. & Perumal, T. (2024). Res-Unet Ensemble learning for semantic segmentation of mineral optical microscopy images. Minerals, 14, 12, 1281. https://doi.org/10.3390/min14121281 (WoS)

Tan, Z., Madzin, H., Norafida, B., Rahmat, R. W. O., Khalid, F. & Sulaiman, P. S. (2024). SwinUNeLCsT: global–local spatial representation learning with hybrid cnn–transformer for efficient tuberculosis lung cavity weakly supervised semantic segmentation. Journal of King Saud University-Computer and Information Sciences, 36(4), 102012. https://doi.org/10.1016/j.jksuci.2024.102012 (WoS)

Tan, Z., Madzin, H., Bahari, N., Yang, C., Wei, S., Tianyu, N. & Fengzhou, C. (2024) DeepPulmoTB: A benchmark dataset for multi-task learning of tuberculosis lesions in lung computerized tomography (CT). Heliyon, 10(4), e25490. https://doi.org/10.1016/j.heliyon.2024.e25490 (WoS)

Updated:: 07/07/2026 [gundala80]