Compressive sequential learning for action similarity labeling

Qin, Jie, Liu, Li, Zhang, Zhaoxiang, Wang, Yunhong and Shao, Ling (2016) Compressive sequential learning for action similarity labeling. IEEE Transactions on Image Processing, 25 (2). pp. 756-769. ISSN 1057-7149

Preview

PDF (Accepted manuscript) - Accepted Version Download (1MB) | Preview

Abstract

Human action recognition in videos has been extensively studied in recent years due to its wide range of applications. Instead of classifying video sequences into a number of action categories, in this paper, we focus on a particular problem of action similarity labeling (ASLAN), which aims at verifying whether a pair of videos contain the same type of action or not. To address this challenge, a novel approach called compressive sequential learning (CSL) is proposed by leveraging the compressive sensing theory and sequential learning. We first project data points to a low-dimensional space by effectively exploring an important property in compressive sensing: the restricted isometry property. In particular, a very sparse measurement matrix is adopted to reduce the dimensionality efficiently. We then learn an ensemble classifier for measuring similarities between pairwise videos by iteratively minimizing its empirical risk with the AdaBoost strategy on the training set. Unlike conventional AdaBoost, the weak learner for each iteration is not explicitly defined and its parameters are learned through greedy optimization. Furthermore, an alternative of CSL named compressive sequential encoding is developed as an encoding technique and followed by a linear classifier to address the similarity-labeling problem. Our method has been systematically evaluated on four action data sets: ASLAN, KTH, HMDB51, and Hollywood2, and the results show the effectiveness and superiority of our method for ASLAN.

Item Type:	Article
Additional Information:	(c) 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Faculty \ School:	Faculty of Science > School of Computing Sciences
Depositing User:	Pure Connector
Date Deposited:	16 Feb 2017 02:20
Last Modified:	03 Jul 2023 10:30
URI:	https://ueaeprints.uea.ac.uk/id/eprint/62615
DOI:	10.1109/TIP.2015.2508600

Downloads

Actions (login required)

View Item