DISCount: counting in large image collections with detector-based importance sampling
Many applications use computer vision to detect and count objects in massive image
collections. However, automated methods may fail to deliver accurate counts, especially …
collections. However, automated methods may fail to deliver accurate counts, especially …
[PDF][PDF] Overview: From data to science with AI and human-in-the-loop
G Perez - gperezs.com
My research in computer vision and machine learning focuses on finding effective ways to
combine human and computational effort, and statistical estimation to reduce the cost of …
combine human and computational effort, and statistical estimation to reduce the cost of …