Action Recognition Using Weighted Locality-Constrained Linear Coding

Jiangfeng YANG  Zheng MA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E98-D   No.2   pp.462-466
Publication Date: 2015/02/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2014EDL8134
Type of Manuscript: LETTER
Category: Image Processing and Video Processing
Keyword: 
action recognition,  action representation,  weighted locality-constrained linear coding,  

Full Text: PDF(419.8KB)
>>Buy this Article


Summary: 
Recently, locality-constrained linear coding (LLC) as a coding strategy has attracted much attention, due to its better reconstruction than sparse coding and vector quantization. However, LLC ignores the weight information of codewords during the coding stage, and assumes that every selected base has same credibility, even if their weights are different. To further improve the discriminative power of LLC code, we propose a weighted LLC algorithm that considers the codeword weight information. Experiments on the KTH and UCF datasets show that the recognition system based on WLLC achieves better performance than that based on the classical LLC and VQ, and outperforms the recent classical systems.