RECOGNIZING HUMAN ACTIONS BASED ON SPARSE CODING WITH NON-NEGATIVE AND LOCALITY CONSTRAINTS

被引：0

作者：

Chen, Yuanbo ^{[1
]}

Zhao, Yanyun ^{[1
]}

Cai, Anni ^{[1
]}

机构：

[1] Beijing Univ Posts & Telecommun, Sch Informat & Commun Engn, Beijing 100088, Peoples R China

来源：

2013 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP 2013) | 2013年

关键词：

Human action recognition; SCNL model; datum-adaptive; locality; sparse;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, Sparse Coding with Non-negative and Locality constraints (SCNL) is proposed to generate discriminative feature descriptions for human action recognition. The non-negative constraint ensures that every data sample is in the convex hull of its neighbors. The locality constraint makes a data sample only represented by its related neighbor atoms. The sparsity constraint confines the dictionary atoms involved in the sample representation as fewer as possible. The SCNL model can better capture the global subspace structures of data than classical sparse coding, and are more robust to noise compared to locality-constrained linear coding. Extensive experiments testify the significant advantages of the proposed SCNL model through evaluations on three remarkable human action datasets.

引用

页数：6