%0 Conference Proceedings
%T Objects as context for detecting their semantic parts
%A Abel Gonzalez-Garcia
%A Davide Modolo
%A Vittorio Ferrari
%B 31st IEEE Conference on Computer Vision and Pattern Recognition
%D 2018
%F Abel Gonzalez-Garcia2018
%O LAMP; 600.109; 600.120
%O exported from refbase (http://158.109.8.37/show.php?record=3229), last updated on Tue, 25 Feb 2020 13:01:51 +0100
%X We present a semantic part detection approach that effectively leverages object information. We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues todetect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone (+5 mAP on the PASCAL-Part dataset). We also compareto other part detection methods on both PASCAL-Part and CUB200-2011 datasets.
%K Proposals
%K Semantics
%K Wheels
%K Automobiles
%K Context modeling
%K Task analysis
%K Object detection
%U http://158.109.8.37/files/GMF2018.pdf
%U http://dx.doi.org/10.1109/CVPR.2018.00722
%P 6907-6916