Stony Brook University

About: Stony Brook University is a education organization based out in Stony Brook, New York, United States. It is known for research contribution in the topics: Population & Poison control. The organization has 32534 authors who have published 68218 publications receiving 3035131 citations. The organization is also known as: State University of New York at Stony Brook & SUNY Stony Brook.

Positive scalar curvature and the Dirac operator on complete riemannian manifolds

Abstract: Operateurs de Dirac generalises sur une variete complete. Theoremes d'annulation. Estimations pour la dimension du noyau et du conoyau. Le theoreme d'indice relatif. Varietes hyperspheriques et agrandissables. Varietes qui admettent des metriques non completes de courbure scalaire positive. Varietes qui admettent des metriques non completes de courbure scalaire uniformement positive. Resultats pour des varietes a 3 et 4 dimensions. Theoremes fondamentaux pour des 3 varietes incompletes. Applications a la topologie des hypersurfaces minimales. Theoremes pour des varietes incompletes de dimension ≤7. Generalisations aux varietes qui representent des classes d'homologie non triviales dans des espaces de courbure non positive

BabyTalk: Understanding and Generating Simple Image Descriptions

Abstract: We present a system to automatically generate natural language descriptions from images. This system consists of two parts. The first part, content planning, smooths the output of computer vision-based detection and recognition algorithms with statistics mined from large pools of visually descriptive text to determine the best content words to use to describe an image. The second step, surface realization, chooses words to construct natural language sentences based on the predicted content and general statistics from natural language. We present multiple approaches for the surface realization step and evaluate each using automatic measures of similarity to human generated reference descriptions. We also collect forced choice human evaluations between descriptions from the proposed generation system and descriptions from competing approaches. The proposed system is very effective at producing relevant sentences for images. It also generates descriptions that are notably more true to the specific image content than previous work.