3 papers
cs.LG2026
Learning Unified Representations of Normalcy for Time Series Anomaly Detection
Prithul Sarker, Sushmita Sarker, Nicholas G. Murray +1
The core challenge in unsupervised anomaly detection is identifying abnormal patterns without prior knowledge of their characteristics. While existing methods have addressed aspect…
cs.CV2025
Guided and Unguided Conditional Diffusion Mechanisms for Structured and Semantically-Aware 3D Point Cloud Generation
Gunner Stone, Sushmita Sarker, Alireza Tavakkoli
Generating realistic 3D point clouds is a fundamental problem in computer vision with applications in remote sensing, robotics, and digital object modeling. Existing generative app…
cs.CV2025
Can Score-Based Generative Modeling Effectively Handle Medical Image Classification?
Sushmita Sarker, Prithul Sarker, George Bebis +1
The remarkable success of deep learning in recent years has prompted applications in medical image classification and diagnosis tasks. While classification models have demonstrated…