| Convolutional fisher kernels for RGB-D object recognition | |
Cheng, Yanhua1 ; Cai, Rui2; Zhao, Xin1; Huang, Kaiqi1; Kaiqi Huang
| |
| 2015 | |
| 会议名称 | International Conference on 3D Vision |
| 会议录名称 | Proc. International Conference on 3D Vision 2015 |
| 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 |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.ia.ac.cn/handle/173211/12730 |
| 专题 | 模式识别实验室 |
| 通讯作者 | Kaiqi Huang |
| 作者单位 | 1.中国科学院自动化研究所 2.微软亚洲研究院 |
| 第一作者单位 | 中国科学院自动化研究所 |
| 推荐引用方式 GB/T 7714 | Cheng, Yanhua,Cai, Rui,Zhao, Xin,et al. Convolutional fisher kernels for RGB-D object recognition[C],2015. |
| 条目包含的文件 | ||||||
| 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 | ||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
修改评论