Accession Number : AD1024300


Title :   Semi-Supervised Multiple Feature Analysis for Action Recognition


Descriptive Note : Journal Article - Open Access


Corporate Author : Carnegie Mellon University Pittsburgh United States


Personal Author(s) : Ma,Zhigang ; Yang,Yi ; Li,Xue ; Pang,Chaoyi ; Hauptmann,Alexander G ; Wang,Sen


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1024300.pdf


Report Date : 26 Nov 2013


Pagination or Media Count : 13


Abstract : This paper presents a semi-supervised method for categorizing human actions using multiple visual features. The proposed algorithm simultaneously learns multiple features from a small number of labeled videos, and automatically utilizes data distributions between labeled and unlabeled data to boost the recognition performance. Shared structural analysis is applied in our approach to discover a common subspace shared by each type of feature. In the subspace, the proposed algorithm is able to characterize more discriminative information of each feature type. Additionally, data distribution information of each type of feature has been preserved. The aforementioned attributes make our algorithm robust for action recognition, especially when only limited labeled training samples are provided. Extensive experiments have been conducted on both the choreographed and the realistic video datasets, including KTH, Youtube action and UCF50. Experimental results show that our method outperforms several state-of-the-art algorithms. Most notably, much better performances have been achieved when there are only a few labeled training samples.


Descriptors :   feature extraction , machine learning , signal processing , VIDEO IMAGES


Subject Categories : Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE