%0 Conference Proceedings
%T Contextual rescoring for Human Pose Estimation
%A Antonio Hernandez
%A Stan Sclaroff
%A Sergio Escalera
%B 25th British Machine Vision Conference
%D 2014
%F Antonio Hernandez2014
%O HuPBA;MILAB
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2525), last updated on Thu, 10 Nov 2016 12:15:54 +0100
%X A contextual rescoring method is proposed for improving the detection of body joints of a pictorial structure model for human pose estimation. A set of mid-level parts is incorporated in the model, and their detections are used to extract spatial and score-related features relative to other body joint hypotheses. A technique is proposed for the automatic discovery of a compact subset of poselets that covers a set of validation imageswhile maximizing precision. A rescoring mechanism is defined as a set-based boosting classifier that computes a new score for body joint detections, given its relationship to detections of other body joints and mid-level parts in the image. This new score complements the unary potential of a discriminatively trained pictorial structure model. Experiments on two benchmarks show performance improvements when considering the proposed mid-level image representation and rescoring approach in comparison with other pictorial structure-based approaches.
%U http://refbase.cvc.uab.es/files/HSE2014.pdf
%U http://dx.doi.org/10.5244/C.28.121