We examine how to leverage the efforts of crowds and algorithms to find the boundaries of objects in biomedical images (segmentation). We propose a modular framework, SAVE, which generates candidate segmentations and then employs voting to choose among the candidates. This framework supports integration of both computer vision and crowdsourcing modules. We evaluated four implementations of SAVE...

It is well established that in certain domains, noisy inputs can be reliably combined to obtain a better answer than any individual. It is now possible to consider the crowdsourcing of physical actions, commonly used for creative expressions such as drawing, shading, and singing. We provide algorithms for converting low-quality input obtained from the physical actions of a crowd into high-quali...

Real time rendering of animated crowds has many practical multimedia applications. The Graphics Processor Unit (GPU) is being increasingly employed to accelerate associated rendering and deformation calculations. This paper explores skeletal deformation calculations on the GPU for crowds of articulated figures. It compares a few strategies for efficient reuse of such calculations on clones. We ...

Recently crowdsourcing services are often used to collect a large amount of labeled data for machine learning, since they provide us an easy way get labels at very low cost and in short period. The use has introduced new challenge that is, coping with the variable quality crowd-generated data. Although there have been many recent attempts address problem multiple workers, only few existing meth...

We describe a series of experiments investigated the perception of urban crowds and the implementation of these results in a real-time crowd system. Our first series of perceptual experiments examined the role of context in locations containing pedestrian crowds, where properties of the location affect the formation of the individuals making up the crowd, i.e. their position and orientation. Ou...