PhD in Computer Science, University of Missouri-Kansas City, USA
BSc in Computer Science & Engineering, BUET, Bangladesh
- Sunday & Tuesday : 02:40 PM – 04:10 PM
- Saturday & Thursday : 11:20 AM – 12:50 PM
- Saturday & Thursday : 02:40 PM – 04:10 PM
Biography
Md Adnan Arefeen is an Assistant Professor in the Department of Electrical & Computer Engineering at North South University (NSU), Dhaka, Bangladesh. He earned his Ph.D. in Computer Science from the University of Missouri-Kansas City (UMKC). He completed his undergraduate studies in Computer Science and Engineering from Bangladesh University of Engineering and Technology (BUET).
Dr. Arefeen’s research focuses on edge computing, efficient AI inference, video analytics, and cost-efficient large language model (LLM) API utilization. He has interned at NEC Labs America, where he contributed to projects on retrieval-augmented generation and domain-specific cost-efficient QA systems. His work has been published in top-tier conferences, including CVPR, CIKM, ITSC, IoTDI, and ECML.
Prior to his Ph.D., he served as a lecturer at United International University.
Research Areas
Research Interests
- Generative AI
- Computer Vision
- Natural Language Processing
- Cost-efficient Video Analytics
Teaching
Selected Publications
Journals
- Md Adnan Arefeen, Biplob Debnath, Srimat Chakradhar, “LeanContext: Cost-efficient domain-specific question answering using LLMs,” Natural Language Processing Journal, 2024
- Md Adnan Arefeen, Sumaiya Tabassum Nimi, M Sohel Rahman, “Neural Network-based Undersampling Techniques,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020
Conference Papers
- Md Adnan Arefeen, Biplob Debnath, Md Yusuf Sarwar Uddin, Srimat Chakradhar, “iRAG: Advancing RAG for Videos with an Incremental Approach,” 33rd ACM International Conference on Information and Knowledge Management (CIKM), 2024
- Md Adnan Arefeen, Biplob Debnath, Md Yusuf Sarwar Uddin, Srimat Chakradhar, “Vita: An efficient video-to-text algorithm using vlm for rag-based video analysis system,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR MAR), 2024
- Md Adnan Arefeen, Sumaiya Tabassum Nimi, Md Yusuf Sarwar Uddin, “Framehopper: Selective processing of video frames in detection-driven real-time video analytics,” 18th International Conference on Distributed Computing in Sensor Systems (DCOSS), 2022
- Sumaiya Tabassum Nimi, Adnan Arefeen, Yusuf Sarwar Uddin, Yugyung Lee, “Earlin: Early out-of-distribution detection for resource-efficient collaborative inference,” European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 2021
- Md Adnan Arefeen, Zhouyu Li, Md Yusuf Sarwar Uddin, Anupam Das, “MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning,” ACM/IEEE Conference on Internet of Things Design and Implementation, 2023
- Sumaiya Tabassum Nimi, Md Adnan Arefeen, Md Yusuf Sarwar Uddin, Biplob Debnath, Srimat Chakradhar, “Factionformer: Context-driven collaborative vision transformer models for edge intelligence,” IEEE International Conference on Smart Computing (SMARTCOMP), 2023
- Sumaiya Tabassum Nimi, Md Adnan Arefeen, Md Yusuf Sarwar Uddin, Biplob Debnath, Srimat Chakradhar, “Chimera: Context-aware splittable deep multitasking models for edge intelligence,” IEEE International Conference on Smart Computing (SMARTCOMP), 2022
- Md Adnan Arefeen, Sumaiya Tabassum Nimi, Md Yusuf Sarwar Uddin, Yugyung Lee, “TransJury: Towards explainable transfer learning through selection of layers from deep neural networks,” IEEE International Conference on Big Data (Big Data), 2021
- Md Adnan Arefeen, Sumaiya Tabassum Nimi, Md Yusuf Sarwar Uddin, Zhu Li, “A lightweight relu-based feature fusion for aerial scene classification,” IEEE International Conference on Image Processing (ICIP), 2021