[International Conference Papers]
[SR#14]
[Title] MedCAGD: Context-Aware Gated Decoder for Efficient Medical Image Segmentation.
[Publisher] 19th European Conference on Computer Vision (ECCV 2026).
[Authors] Saad Wazir, Patrick Vibild, Phu Tran, Songha Kim, Daeyoung Kim.
[Link] https://arxiv.org/abs/2607.00409
[Code] https://github.com/saadwazir/MedCAGD
[Dataset] https://huggingface.co/datasets/saadwazir/MedCAGD-Dataset-Collection
__________
[SR#13]
[Title] SAT: Selective Aggregation Transformer for Image Super-Resolution.
[Publisher] IEEE / CVF 45th Computer Vision and Pattern Recognition Conference (CVPR Findings 2026).
[Authors] Dinh Phu Tran, Thao Do, Saad Wazir, Seongah Kim, Seon Kwon Kim, Daeyoung Kim.
[Link] https://arxiv.org/abs/2604.07994
[Code] https://github.com/PhuTran1005/SAT
__________
[SR#12]
[Title] Evaluating Video LLMs’ Understanding of Corner Cases in Autonomous Driving.
[Publisher] 37th British Machine Vision Conference (BMVC 2026).
[Authors] Gabriel Manalu, Minh Son Hoang, Hyeontaek Hwang, Jaesung Lee, Hyojin Choi, Tran Tuan Phong, Seon Kwon Kim, Saad Wazir, Daeyoung Kim.
__________
[SR#11]
[Title] Threat Track AI: A Scalable Multi-Agent Framework for Automated Cybersecurity Log Analysis and Threat Detection.
[Publisher] 6th International Conference Digital Futures and Transformative Technologies (ICoDT2 2026).
[Authors] Muhammad Javaid, Saad Wazir.
[Code] https://github.com/javaidgithub/Threat-Track-AI
__________
[SR#10]
[Title] Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention.
[Publisher] IEEE / CVF 44th Computer Vision and Pattern Recognition Conference (CVPR 2025).
[Authors] Saad Wazir, Daeyoung Kim.
[Link] https://arxiv.org/abs/2506.18335
[Code] https://github.com/saadwazir/MCADS-Decoder
__________
[SR#9]
[Title] HistoSeg++: Delving deeper with attention and multiscale feature fusion for biomarker segmentation.
[Publisher] 12th International Conference on Biomedical and Bioinformatics Engineering (ICBBE 2025).
[Authors] Saad Wazir, Rao Faizan, Daeyoung Kim.
[Link] https://dl.acm.org/doi/10.1145/3794209.3794211
[Code] https://github.com/saadwazir/histosegplusplus
__________
[SR#8]
[Title] Rethinking the Nested U-Net Approach: Enhancing Biomarker Segmentation with Attention Mechanisms and Multiscale Feature Fusion.
[Publisher] 5th International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2024) - MICCAI Society Endorsed Event.
[Authors] Saad Wazir, Daeyoung Kim.
[Link] https://arxiv.org/abs/2504.06158
[Code] https://github.com/saadwazir/ReN-UNet
__________
[SR#7]
[Title] Mukhtasir-Khail-Net: An Ultra-Efficient Convolutional Neural Network for Sports Activity Recognition with Wearable Inertial Sensors.
[Publisher] IEEE 4th International Conference on Digital Futures and Transformative Technologies (ICoDT2 2024).
[Authors] Hamza Ali Imran, Shaida Muhammad, Saad Wazir, Ataul Aziz Ikram, Obaidullah Arshad.
[Link] https://doi.org/10.1109/ICoDT262145.2024.10740217
__________
[SR#6]
[Title] Enhanced Human Activity Recognition Using Inertial Sensor Data from Smart Wearables: A Neural Network Approach with Residual Connections.
[Publisher] IEEE International Conference on Engineering & Computing Technologies (ICECT 2024).
[Authors] Shaida Muhammad, Kiran Hamza, Hamza Ali Imran, Saad Wazir.
[Link] https://doi.org/10.1109/ICECT61618.2024.10581358
__________
[SR#5]
[Title] Paying Attention to Human Activities: Recognizing Daily Activities with an Attention-based Neural Network and Inertial Sensors.
[Publisher] IEEE 5th International Conference on Innovative Computing (ICIC 2024).
[Authors] Shaida Muhammad, Hamza Ali Imran, Kiran Hamza, Ataul Aziz Ikram, Saad Wazir.
[Link] https://doi.org/10.1109/ICIC63915.2024.11116432
__________
[SR#4]
[Title] EdgeHARNet: An Edge-Friendly Shallow Convolutional Neural Network for Recognizing Human Activities Using Embedded Inertial Sensors of Smart-Wearables.
[Publisher] IEEE 3rd International Conference on Communication, Computing and Digital Systems (C-CODE 2023).
[Authors] Hamza Ali Imran, Ataul Aziz Ikram, Saad Wazir, Kiran Hamza.
[Link] https://doi.org/10.1109/C-CODE58145.2023.10139860
__________
[SR#3]
[Title] HistoSeg: Quick attention with multi-loss function for multi-structure segmentation in digital histology images.
[Publisher] IEEE 12th International Conference on Pattern Recognition Systems (ICPRS 2022).
[Authors] Saad Wazir, Muhammad Moazam Fraz.
[Link] https://arxiv.org/abs/2209.00729
[Code] https://github.com/saadwazir/HistoSeg
__________
[SR#2]
[Title] Multi-Cloud: A Comprehensive Review.
[Publisher] IEEE 23rd International Multitopic Conference (INMIC 2020).
[Authors] Hamza Ali Imran, Usama Latif, Ataul Aziz Ikram, Maryam Ehsan, Ahmed Jamal Ikram, Waleed Ahmad Khan, Saad Wazir.
[Link] https://doi.org/10.1109/INMIC50486.2020.9318176
__________
[SR#1]
[Title] HPC as a Service A naive model.
[Publisher] IEEE 8th International Conference on Information and Communication Technologies (ICICT 2019).
[Authors] Hamza Ali Imran, Saad Wazir, Ahmed Jamal Ikram, Ataul Aziz Ikram, Hanif Ullah, Maryam Ehsan.
[International Journal Papers]
[SR#2]
[Title] Artificial Intelligence of Things–Enabled Sleep Monitoring Using Wearable Inertial Sensors and a Transformer–CNN Model.
[Publisher] IEEE Embedded Systems Letters. 2026/5/19.
[Authors] Hamza Ali Imran, Ataul Aziz Ikram, Saad Wazir.
[Link] https://doi.org/10.1109/LES.2026.3694991
__________
[SR#1]
[Title] Performance Comparison of Mpich and Mpi4py on Raspberry Pi-3B Beowulf Cluster.
[Publisher] Journal of Advanced Research in Dynamic and Control Systems. Volume: 11 | Special Issue 03 | 2019.
[Authors] Saad Wazir, Ataul Aziz Ikram, Hamza Ali Imran, Hanif Ullah, Ahmed Jamal Ikram, Maryam Ehsan.
[Upcoming/Under Review]
[SR#9]
[Title] Learning to Abstain: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Dinh Phu Tran, Jihoon Jeong, Saad Wazir, Seongah Kim, Thao Do, Cem Subakan, Daeyoung Kim.
__________
[SR#8]
[Title] FusedVTON: Early Image Fusion for Efficient Virtual Try-On. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Cuong Tran Van, Dam Hoang Phuong, Quyen Nguyen Duc, Saad Wazir, Trung X. Pham, Daeyoung Kim.
__________
[SR#7]
[Title] Beyond Passive Watching: A Comprehensive Survey of Agentic Systems for Long-Form Video Understanding. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Dinh Phu Tran, Minh Son Hoang, Dam Hoang Phuong, Quyen Nguyen Duc, Jaesuk Lim, Thao Do, Hyeontaek Hwang, Tolcha Yalew Kidane, Nguyen Dinh Son, Seongah Kim, Jaesung Lee, Vy Tuong Dang, Cuong Tran Van, Jihoon Jeong, Seon Kwon Kim, Saad Wazir, Tran Tuan Phong, Gabriel Manalu, Duc Dm, Seungmin Yang, Daeyoung Kim.
__________
[SR#6]
[Title] FalOTS: Orthogonal Target-Aware SAM for Federated Active Learning Under Global Class Imbalance. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Dinh Phu Tran, Seon Kwon Kim, Thao Do, Dam Hoang Phuong, Minh Son Hoang, Saad Wazir, Seungmin Yang, Daeyoung Kim.
__________
[SR#5]
[Title] GRACE: Grounding and Confidence Calibration for Audio-Visual Hallucination. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Seongah Kim, Saad Wazir, Duc Dm, Hyeontaek Hwang, Dinh Phu Tran, Gabriel Manalu, Daeyoung Kim.
__________
[SR#4]
[Title] Measuring the Reasoning-Action Coupling in Driving Vision-Language-Action Models through Counterfactuals. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Gabriel Manalu, Saad Wazir, Thao Do, Seongah Kim, Hyeontaek Hwang, Tolcha Yalew Kidane, Daeyoung Kim.
__________
[SR#3]
[Title] TB-AVA: Text-Bridged Audio-Visual Adapter for Parameter-Efficient Alignment. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Seongah Kim, Dinh Phu Tran, Hyojin Choi, Hyeontaek Hwang, Saad Wazir, Daeyoung Kim.
[Link] https://arxiv.org/abs/2605.11572
__________
[SR#2]
[Title] Post-hoc Vocabulary Expansion for Embedding Models via Definition-Learning. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Seungmin Yang, Dinh Phu Tran, Saad Wazir, Hyeontaek Hwang, Daeyoung Kim.
__________
[SR#1]
[Title] Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering. (Under Review 2026).
[Publisher] Under Review (2026).
[Authors] Dinh Phu Tran, Jihoon Jeong, Saad Wazir, Seongah Kim, Thao Do, Cem Subakan, Daeyoung Kim.
[Scientific Manuscripts / Preprints]
__________
[SR#3]
[Title] Classifying Human Activities with Inertial Sensors: A Machine Learning Approach.
[Authors] Hamza Ali Imran, Saad Wazir, Usman Iftikhar, Usama Latif.
[Link] https://arxiv.org/abs/2111.05333
__________
[SR#2]
[Title] Embedded development boards for edge-AI: A comprehensive report
[Authors] Hamza Ali Imran, Usama Mujahid, Saad Wazir, Usama Latif, Kiran Mehmood.
[Link] https://arxiv.org/abs/2009.00803
__________
[SR#1]
[Title] Single Board Computers (SBC): The Future of Next Generation Pedagogies in Pakistan
[Authors] Saad Wazir, Hamza Ali Imran , Usama Latif , Usama Mujahid , Muhammad Bilal.