TY  - CONF
AU  - Abel Gonzalez-Garcia
AU  - Davide Modolo
AU  - Vittorio Ferrari
A2  - CVPR
PY  - 2018//
TI  - Objects as context for detecting their semantic parts
BT  - 31st IEEE Conference on Computer Vision and Pattern Recognition
SP  - 6907
EP  - 6916
KW  - Proposals
KW  - Semantics
KW  - Wheels
KW  - Automobiles
KW  - Context modeling
KW  - Task analysis
KW  - Object detection
N2  - 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.
L1  - http://158.109.8.37/files/GMF2018.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2018.00722
N1  - LAMP; 600.109; 600.120
ID  - Abel Gonzalez-Garcia2018
ER  -