CASIA OpenIR  > 智能感知与计算研究中心
Convolutional fisher kernels for RGB-D object recognition
Cheng, Yanhua1; Cai, Rui2; Zhao, Xin1; Huang, Kaiqi1; Kaiqi Huang
Conference NameInternational Conference on 3D Vision
Source PublicationProc. International Conference on 3D Vision 2015
Conference Date2015-10-01
Conference PlaceFrance
AbstractThis paper studies the problem of improving object recognition using the novel RGB-D data. To address the problem, a new convolutional Fisher Kernels (CFK) method is proposed to represent RGB-D objects powerfully yet efficiently. The core idea of our approach is to integrate the both advantages of the convolutional neural networks (CNN) and Fisher Kernel encoding (FK): CNN model is flexible to adapt to new data sources, but requires for large amounts of training data with significant computational resources for good generalization, In comparison, FK encoding is able to represent objects powerfully and efficiently with small training data, however, its success highly depends on the well-designed SIFT features in literature, which may not be suitable for the new depth data. CFK can be interpreted as a two-layer feature learning structure to bridge the two models. The first layer employs a single-layer CNN to learn low-level translation ally invariant features for both RGB and depth data efficiently. The second layer aggregates the convolutional responses by FK encoding. Here 2D and 3D spatial pyramids are applied to further improve the Fisher vector representation of each modality. Experiments on RGB-D object recognition benchmarks demonstrate that our approach can achieve the state-of-the-art results.
KeywordRgb-d Recognition Fisher Kernel Cnn
Document Type会议论文
Corresponding AuthorKaiqi Huang
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Cheng, Yanhua,Cai, Rui,Zhao, Xin,et al. Convolutional fisher kernels for RGB-D object recognition[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
egpaper_final.pdf(1413KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cheng, Yanhua]'s Articles
[Cai, Rui]'s Articles
[Zhao, Xin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cheng, Yanhua]'s Articles
[Cai, Rui]'s Articles
[Zhao, Xin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cheng, Yanhua]'s Articles
[Cai, Rui]'s Articles
[Zhao, Xin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: egpaper_final.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.