English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/133963
Share/Impact:
Statistics
logo share SHARE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:
Title

Segmentation-aware deformable part models

AuthorsTrulls, Eduard ; Tsogkas, Stavros; Kokkinos, Iasonas; Sanfeliu, Alberto ; Moreno-Noguer, Francesc
Issue Date2014
PublisherInstitute of Electrical and Electronics Engineers
CitationIEEE Computer Society Conference on Computer Vision and Pattern Recognition: 168-175 (2014)
AbstractIn this work we propose a technique to combine bottom-up segmentation, coming in the form of SLIC superpixels, with sliding window detectors, such as Deformable Part Models (DPMs). The merit of our approach lies in >cleaning up> the low-level HOG features by exploiting the spatial support of SLIC superpixels, this can be understood as using segmentation to split the feature variation into object-specific and background changes. Rather than committing to a single segmentation we use a large pool of SLIC superpixels and combine them in a scale-, position- and object-dependent manner to build soft segmentation masks. The segmentation masks can be computed fast enough to repeat this process over every candidate window, during training and detection, for both the root and part filters of DPMs. We use these masks to construct enhanced, background-invariant features to train DPMs. We test our approach on the PASCAL VOC 2007, outperforming the standard DPM in 17 out of 20 classes, yielding an average increase of 1.7% AP. Additionally, we demonstrate the robustness of this approach, extending it to dense SIFT descriptors for large displacement optical flow.
DescriptionTrabajo presentado a la IEEE Conference on Computer Vision and Pattern Recognition (CVPR), celebrada del 23 al 28 de junio de 2014 en Columbus, Ohio (US).
Publisher version (URL)http://dx.doi.org/10.1109/CVPR.2014.29
URIhttp://hdl.handle.net/10261/133963
DOI10.1109/CVPR.2014.29
Identifiersdoi: 10.1109/CVPR.2014.29
issn: 1063-6919
Appears in Collections:(IRII) Artículos
Files in This Item:
File Description SizeFormat 
Segmentation-aware.pdf6,41 MBUnknownView/Open
Show full item record
Review this work
 

Related articles:


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.