Support vector machines (SVMs) have been widely used in multimedia retrieval to learn a concept in order to find the best matches. In such a SVM active learning environment, the ...
We introduce GaZIR, a gaze-based interface for browsing and searching for images. The system computes on-line predictions of relevance of images based on implicit feedback, and wh...
We study how to best use crowdsourced relevance judgments learning to rank [1, 7]. We integrate two lines of prior work: unreliable crowd-based binary annotation for binary classi...
I report briefly on some of my own work in each of these areas and elucidate some of the questions that this research has raised. Then I propose as a research agenda the developme...
This paper proposes a D-algebra to compose decisions from multiple access control policies. Compared to other algebrabased approaches aimed at policy composition, D-algebra is the...