Human attribute recognition by deep hierarchical contexts
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractWe present an approach for recognizing human attributes in unconstrained settings.We train a Convolutional Neural Network (CNN) to select the most attribute-descriptive human parts from all poselet detections, and combine them with the whole body as a pose-normalized deep representation. We further improve by using deep hierarchical contexts ranging from human-centric level to scene level. Human-centric context captures human relations, which we compute from the nearest neighbor parts of other people on a pyramid of CNN feature maps. The matched parts are then average pooled and they act as a similarity regularization. To utilize the scene context, we re-score human-centric predictions by the global scene classification score jointly learned in our CNN, yielding final scene-aware predictions. To facilitate our study, a largescale WIDER Attribute dataset(Dataset URL: is introduced with human attribute and image event annotations, and our method surpasses competitive baselines on this dataset and other popular ones.
All Author(s) ListLi Y., Huang C., Loy C.C., Tang X.
Name of ConferenceEuropean Conference on Computer Vision
Start Date of Conference08/10/2016
End Date of Conference16/10/2016
Place of ConferenceAmsterdam
Country/Region of ConferenceNetherlands
Proceedings TitleECCV 2016: Computer Vision – ECCV 2016
Volume Number9910 LNCS
PublisherSpringer Verlag
Place of PublicationGermany
Pages684 - 700
LanguagesEnglish-United Kingdom

Last updated on 2020-30-06 at 04:22