Multimodal Learning
Machine learning methods that jointly model information across text, audio, image, and video.
Mustafa Sert
Professor of CSE, AI Engineering
Chair, Department of Artificial Intelligence Engineering
Vice Dean, Faculty of Engineering
Baskent University, Ankara, Turkiye
My research interests span the areas of machine learning, semantic multimedia, multimodal learning, audio signal processing, and vision-language understanding, along with their applications in health, social systems, and IoT systems.
Research
Research Interests
Audio, Vision and Language
Representation learning and semantic understanding for audio, visual and language-based AI tasks.
Semantic Multimedia
Machine learning methods for extracting semantic meaning from multimedia content.
Applied Intelligent Systems
AI systems for multimedia recognition, semantic retrieval, multimodal fusion, and human-centered intelligent applications.
News
Recent Updates
May 2026 - Our Guest Editorial, co-authored by Mustafa Sert, Bryan Chou, and Julienne A. Greer, has been published in the International Journal of Semantic Computing (IJSC). DOI NEW
May 2026 - I serve as PC Co-Chair for AIxB 2026. NEW
March 2026 - I serve as Area Chair for ACM Multimedia 2026. NEW
February 2026 - I serve as Program Co-Chair for IEEE ISM 2026. NEW
January 2026 - I serve as Demo Papers Co-Chair for IEEE MIPR 2026. NEW
October 2025 - We received the Best Paper Award at the IEEE Conference on Artificial Intelligence x Software Engineering (AIxSE 2025).
September 2025 - Our edited book Semantic Computing and AI: Transforming Knowledge into Intelligence has been published by World Scientific.
November 2024 - I received the Outstanding Area Chair Award at ACM Multimedia 2024, Melbourne, Australia.
October 28 - November 1, 2024 - I served as Area Chair for the 32nd ACM Multimedia Conference 2024, Melbourne, Australia.
October 1, 2024 - I joined the Department of Electrical Engineering and Computer Science at the University of California, Irvine, CA, USA. [msert [at] uci [dot] edu]
February 3-5, 2025 - I served as Program Co-Chair of IEEE AIxMM 2025, Laguna Hills, California, USA.
Selected Work
Selected Publications
Visual and Auditory Data Fusion for Energy-Efficient and Improved Object Recognition in Wireless Multimedia Sensor Networks
IEEE Sensors Journal, 2019
Multimodal Vehicle Type Classification Using Convolutional Neural Network and Statistical Representations of MFCC
IEEE AVSS, 2017
Sketch Recognition Using Transfer Learning
Multimedia Tools and Applications, 2019
Early and Late Level Fusion of Deep Convolutional Neural Networks for Visual Concept Recognition
International Journal of Semantic Computing, 2016
Audio Captioning Based on Combined Audio and Semantic Embeddings
IEEE ISM, 2020
An Intelligent Multimedia Information System for Multimodal Content Extraction and Querying
Multimedia Tools and Applications, 2018
Automated Audio Captioning With Topic Modeling
IEEE Access, 2023
Detection of Basic Human Physical Activities With Indoor-Outdoor Information Using Sigma-Based Features and Deep Learning
IEEE Sensors Journal, 2019
Teaching
Teaching Highlights
Teaching Interests and Experience
Dr. Sert's teaching interests span both theory and applications of database management systems, object-oriented analysis and design, multimedia systems, and machine learning. His teaching combines fundamental concepts with applied perspectives in intelligent systems, software-oriented computing, and data-driven methods.