We propose to model relative attributes1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can captur...
In recent years, many algorithms for the Web have been developed that work with information units distinct from individual web pages. These include segments of web pages or aggreg...
Anomaly detection for network intrusion detection is usually considered an unsupervised task. Prominent techniques, such as one-class support vector machines, learn a hypersphere ...
It has been established that active learning is effective for learning complex, subjective query concepts for image retrieval. However, active learning has been applied in a conc...
This project implements an integrated biological information website that classifies technical documents, learns about users' interests, and offers intuitive interactive visua...
Min Hong, Anis Kairmpour-fard, Steve Russell, Lawr...