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...
Graphs capture the essential elements of many problems broadly defined as searching or categorizing. With the rapid increase of data volumes from sensors, many application discipl...
In this paper we investigate the quality of 3D-2D pose estimates using hand labeled line and point correspondences. We select point correspondences from junctions in the image, all...
Florian Pilz, Yan Shi, Daniel Grest, Nicolas Pugea...
Conventional image categorization techniques primarily rely on low-level visual cues. In this paper, we describe a multimodal fusion scheme which improves the image classification...
We propose a multi-camera system that can detect omni-directional pointing gestures and estimate the direction of pointing. In general, when a human points at something, their tar...