Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approac...
Graham Taylor, Ian Spiro, Rob Fergus, Christoph Br...
We introduce an algorithm that, given n objects, learns a similarity matrix over all n2 pairs, from crowdsourced data alone. The algorithm samples responses to adaptively chosen t...
Omer Tamuz, Ce Liu, Serge Belongie, Ohad Shamir, A...
How is work created, assigned, and completed on large-scale, crowd-powered systems like Wikipedia? And what design principles might enable these federated online systems to be mor...
Michel Krieger, Emily Margarete Stark, Scott R. Kl...
This paper introduces a doctoral research on open innovation solver's behavior and group factors inducing it. The research is now finishing its first year and exploratory str...
The ongoing rise of human computation as a means of solving computational problems has created an environment where human workers are often regarded as nameless, faceless computat...