Compressive Sequential Learning for Action Similarity Labeling

Jie Qin, Li Liu, Zhaoxiang Zhang, Yunhong Wang, Ling Shao

Research output: Contribution to journalArticlepeer-review

23 Citations (Scopus)

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.
Original languageEnglish
Pages (from-to)756-769
JournalIEEE Transactions on Image Processing
Volume25
Issue number2
DOIs
Publication statusPublished - 2 Feb 2016

Fingerprint Dive into the research topics of 'Compressive Sequential Learning for Action Similarity Labeling'. Together they form a unique fingerprint.

Cite this