Convolutional Fisher Kernels for RGB-D Object Recognition

CASIA OpenIR > 模式识别实验室

	Convolutional Fisher Kernels for RGB-D Object Recognition
	Yanhua Cheng; Rui Cai; Xi Zhao; Kaiqi Huang
	2015
会议名称	International Conference on 3D Vision
会议录名称	Proc. International Conference on 3D Vision 2015
页码	135-143
会议日期	2015-10-01
会议地点	France
摘要	This 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.
关键词	Rgb-d recognition fisher Kernel cnn
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12679
专题	模式识别实验室
通讯作者	Kaiqi Huang
作者单位	中国科学院自动化研究所
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yanhua Cheng,Rui Cai,Xi Zhao,et al. Convolutional Fisher Kernels for RGB-D Object Recognition[C],2015:135-143.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
egpaper_final.pdf（1413KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载