Theses/Dissertations from 2024
Enhancing 3D Indoor Instance Segmentation through Spatial and Semantic Supervision with Infused Subjectivity in Evaluation, Salwa AlKhatib
Limb Prescribe: Text-to-Pose Generative Model for Therapeutic Exercise Prescription, Shamma Alsaedi
Multimodal Object Detection in Remote Sensing Imagery, Nouf Alshamsi
Federated Learning of Plug-and-Play Adapter for Segment Anything Model, Mothilal Asokan
Byzantine Tolerant Gradient Aggregation for Cross-Silo Federated Learning, Joseph Benjamin
Open-World 3D instance segmentation, Mohamed Boudjoghra
A Virtual Try-On System for Any Clothing and Body Model, Cong Cao
Large Language Vision Assistant for Summarization of Temporal Changes in Chest Radiograph, Hosam Elgendy
From EHRs to Forecasts: A Pathway to Enhanced Prediction of Medication Demand, Ibraheem Hamdi
Test-Time Adaptation of Vision-Language Models using Prompt Learning, Jameel Hassan
A Comprehensive Virtual Assistant for Remote Health Monitoring and Medical Support, Thanh Ho
The Heterogeneity and Privacy in Cross-Silo Federated Learning, Xiangjian Hou
A Practical Multi-View System for Building Neural Head Avatars, Kane Lindsay
Gaussian Splat-Based Human Performance Reconstruction from Sparse Cameras, Zhenhui Lin
On Enabling Video Networks for Reliable 2D Time Echocardiography Analysis, Fadillah Adamsyah Maani
Domain Generalization methods in Medical Imaging data analysis, Aleksandr Matsun
Efficient and Accurate Phase Recognition in Videos of Cataract Surgeries, Dana Mohamed
Towards Efficient Models for Continual Learning in Medical Imaging, Mohammad Qazi
PEMMA: Parameter Efficient Multi Modal Adaptation in Head and Neck Cancer Segmentation, Nada Saadi
Leveraging Model Merging and Multi-Modal Medical Imaging Data for Diagnosis & Generation Tasks, Santosh Sanjeev
Towards Generaliable Predictions, Baliah Sanoojan
Towards End-to-End Trustworthy Large Language Models, Chong Tian
Open-Vocabulary Object Detection and its Application in Robotic Navigation, Hanlue Zhang
Face Tracking Using Diffusion Model Generated Data, Yufei Zhang
Submissions from 2023
Improving Generalization Performance of Deep Learning Models for Whole Slide Image Segmentation, Kudaibergen Abutalip
Part-based Signal Modulation and Adaptive Skip Merger for Person Search, Reem Abdalla Sharif Mohamed Alameeri
Pseudo-Label Generation and Refinement for Minimally Supervised Video Anomaly Detection, Anas Emad Addeen Diab Al-lahham
Toward Adaptive Person Search/ReID systems, Mohammed Khaled Mohamed Ahmed Almansoori
Towards Efficient Neural Radiance Field For Real-world Applications, Aliyu Bagudu
XMem++: Towards production level interactive video object segmentation, Maksym Bekuzarov
Towards a Computer Vision-based Approach for Digital Twin Implementation, Miriam Cristofoletti
Object Detection and Semantic Segmentation on Radar Frequency Signals, Yahia Ibrahim R Dalbah
FusedVision: Advancing Anomaly Detection in Surveillance Videos with Branched Networks, Khaled W. H. Dawoud
Open World Object Detection in Satellite Images, Abhishek Singh Gehlot
Efficient Test-Time Adaptation for Vision-Language Models, Adilbek Karmanov
Semi-Supervised Domain Generalization in Visual Recognition, Adnan Khan
Transferability of Vision-Language models with Prompt Learning, Muhammad Uzair Khattak
Towards Learning Efficient Multilingual and Multimodal Representation, Gokul Karthik Kumar
Zero-shot out-of-distribution cancer tissue classification via the Contextualized Classifier, Juwayni Macadato Lucman
Semi-supervised Open-World Object Detection, Sahal Shaji Mullappilly
Learning a Latent Space of Cell Shapes via Signed Distance Functions, Sara Pieri
Efficient Deep Learning Architectures for Computer Vision Deployment on Industrial Scenarios, Jose Renato Restom Viera
Exploring the Potential of Deep Learning for Biomedical Image Segmentation, Muhammad Hamza Sharif
A Filling-Based Masking Strategy for Siamese ConvNets, Kirill Vishniakov
Sequence Pre-training-based Graph Neural Network for Predicting LncRNA-miRNA Associations, Zixiao Wang
Submissions from 2022
A 16×16 Patch Attack on Vision Transformers with Differential Evolution, Abass Bamidele Abdulsalam
3D Object Detection in Context, Sultan Mobeen Jawdat Abu Ghazal
Robustness in Point-based 3D Object Detection, Fatima Abdulla Omar Albreiki
Improving Vision Transformers for Remote Sensing, Abdulaziz Amer Mohammed Aleissaee
Visual Object Tracking in Adverse Weather conditions, Wafa Hamad Mohamed Alghallabi
Hippocampal Segmentation and Pseudolabel generation for Alzheimer’s Classification, Roba Al Majzoub
On Improving Model Generalizability via Optimization and Representation Learning Techniques, Omar Ali Ahmed Hajras Alsuwaidi
Nuclei Segmentation and Classification, Hussam Osama Fares Azzuni
Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection, Hanoona Bangalath
Improving Vision Transformers for Fine-Grained Recognition, Dmitry Demidov
CGPS-3DV: Cycled Generative Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Vehicles, Ahmed Adel Gomaa Sayed Elhagry
Class Incremental Continual Learning for Computer Vision, Rushali Grandhe
Class-agnostic Object Detection with Multi-modal Transformer, Muhammad Maaz
Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations, Hashmat Shadab Malik
Negating Bias in Hybrid Transformers for Class Incremental Learning, Abdelrahman Mohamed Helmy Mohamed
Data-efficient transformer-based 3D object detection, Aidana Nurakhmetova
Ventricular Segmentation and Coronary Artery Disease Classification in Echocardiography with Limited Data, Mohamed Eltag Salih Saeed
YoloS3DN: Towards Low-Latency ViT-Powered Stereo 3D Object Detection, Zakaria Sebaitre
Diagnosis and Prognosis of Head and Neck Cancer Patients using Artificial Intelligence, Ikboljon Sobirov
Semi-Supervised Cross-Modal Salient Object Detection with U-Structure Networks, Bao Yunqing