This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the model follows an “analysis by synthesis” scheme and can be interpreted as a mode seeking and mode shifting process. The model can synthesize 3D shape patterns by sampling from the probability distribution via MCMC suc...

BACKGROUND The extent to which co-evolutionary processes shape morphological traits is one of the most fascinating topics in evolutionary biology. Both passive and active pollination modes coexist in the fig tree (Ficus, Moraceae) and fig wasp (Agaonidae, Hymenoptera) mutualism. This classic obligate relationship that is about 75 million years old provides an ideal system to consider the role o...

PURPOSE There is a continuing need to improve the prediction of hip fractures to identify those at highest risk, enabling cost-effective use of preventative therapies. METHODS The aim of this work was to validate an innovative imaging biomarker for hip fracture by modelling the shape and texture of the proximal femur assessed from dual energy X-ray absorptiometry (DXA) scans. Scans used were ...

This paper proposes a method to generate realistic character images from on-line patterns. From the pen trajectory of an on-line pattern, the proposed method generates images of various stroke shapes using four painting modes: constant line mode, proportional mode and two calligraphic modes. Particularly, the calligraphic modes combine the pen trajectory with real stroke-shape images so that th...