CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map based Feature Extraction for Human Action Recognition
Du, Yang1,2,3; Yuan, Chunfeng1; Hu, Weiming1; Yang, Hao1,2,3
2018
会议名称AAAI Conference on Artificial Intelligence (AAAI)
会议录名称2018 AAAI Conference on Artificial Intelligence
会议日期20180202-20180207
会议地点New Orleans, Louisiana, USA
摘要
Feature extraction is a critical step in the task of action recognition. Hand-crafted features are often restricted because of their fixed forms and deep learning features are more effective but need large-scale labeled data for training. In this paper, we propose a new hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map (NOASSOM) to
adaptively and learn effective features from data without supervision. NOASSOM is extended from Adaptive-Subspace Self-Organizing Map (ASSOM) which only deals with linear data and is trained with supervision by the labeled data. Firstly, by adding a nonlinear orthogonal map layer, NOASSOM is able to handle the nonlinear input data and it avoids defining the specific form of the nonlinear orthogonal map by a kernel trick. Secondly, we modify loss function of ASSOM such that every input sample is used to train model individually. In this way, NOASSOM effectively learns the statistic patterns from data without supervision. Thirdly, we propose a hierarchical NOASSOM to extract more representative
features. Finally, we apply the proposed hierarchical NOASSOM
to efficiently describe the appearance and motion information
around trajectories for action recognition. Experimental
results on widely used datasets show that our method has
superior performance than many state-of-the-art hand-crafted
features and deep learning features based methods.
关键词Action Recognition Feature Extraction
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19734
专题模式识别国家重点实验室_视频内容安全
通讯作者Yuan, Chunfeng
作者单位1.CAS Center for Excellence in Brain Science and Intelligence Technology, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.MTdata, Meitu
推荐引用方式
GB/T 7714
Du, Yang,Yuan, Chunfeng,Hu, Weiming,et al. Hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map based Feature Extraction for Human Action Recognition[C],2018.
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
Du_Hierarchical Nonl(4323KB)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
[Du, Yang]的文章
[Yuan, Chunfeng]的文章
[Hu, Weiming]的文章
百度学术
百度学术中相似的文章
[Du, Yang]的文章
[Yuan, Chunfeng]的文章
[Hu, Weiming]的文章
必应学术
必应学术中相似的文章
[Du, Yang]的文章
[Yuan, Chunfeng]的文章
[Hu, Weiming]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Du_Hierarchical Nonlinear Orthogonal Adaptive-Subspace Self-Organizing Map_AAAI_2018.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。