CASIA OpenIR  > 智能感知与计算研究中心
Semi-supervised Learning for RGB-D Object Recognition
Yanhua Cheng; Xin Zhao; Kaiqi Huang; Tieniu Tan
2014
会议名称International Conference on Pattern Recognition
会议录名称Proc. International Conference on Pattern Recognition 2014
页码2377-2382
会议日期2014-08-01
会议地点Stockholm, Sweden
摘要Conventional supervised object recognition methods have been investigated for many years. Despite their successes, there are still two suffering limitations: (1) various information of an object is represented by artificial features only derived from RGB images, (2) lots of manually labeled data is required by supervised learning. To address those limitations, we propose a new semi-supervised learning framework based on RGB and depth (RGB-D) images to improve object recognition. In particular, our framework has two modules: (1) RGB and depth images are represented by convolutional-recursive neural networks to construct high level features, respectively, (2) co-training is exploited to make full use of unlabeled RGB-D instances due to the existing two independent views. Experiments on the standard RGB-D object dataset demonstrate that our method can compete against with other state-of-the-art methods with only 20% labeled data.
关键词Accuracy   cameras   feature Extraction   object Recognition
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12684
专题智能感知与计算研究中心
通讯作者Kaiqi Huang
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,Xin Zhao,Kaiqi Huang,et al. Semi-supervised Learning for RGB-D Object Recognition[C],2014:2377-2382.
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
Semi-supervised Lear(645KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yanhua Cheng]的文章
[Xin Zhao]的文章
[Kaiqi Huang]的文章
百度学术
百度学术中相似的文章
[Yanhua Cheng]的文章
[Xin Zhao]的文章
[Kaiqi Huang]的文章
必应学术
必应学术中相似的文章
[Yanhua Cheng]的文章
[Xin Zhao]的文章
[Kaiqi Huang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Semi-supervised Learning for RGB-D Object Recognition.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。