Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Enhancing human action recognition via structural average curves analysis

Enhancing human action recognition via structural average curves analysis Human action recognition typically requires a large amount of training samples, which is often expensive and time-consuming to create. In this paper, we present a novel approach for enhancing human actions with a limited number of samples via structural average curves analysis. Our approach first learns average sequences from each pair of video samples for every action class and then gather them with original video samples together to form a new training set. Action modeling and recognition are proposed to be performed with the resulting new set. Our technique was evaluated on four benchmarking datasets. Our classification results are superior to those obtained with the original training sets, which suggests that the proposed method can potentially be integrated with other approaches to further improve their recognition performances. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png "Signal, Image and Video Processing" Springer Journals

Enhancing human action recognition via structural average curves analysis

Download PDF
8 pages

Loading next page...
 
/lp/springer_journal/enhancing-human-action-recognition-via-structural-average-curves-Wu1HqMsb2j
Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer-Verlag London Ltd., part of Springer Nature
Subject
Computer Science; Image Processing and Computer Vision; Signal,Image and Speech Processing; Computer Imaging, Vision, Pattern Recognition and Graphics; Multimedia Information Systems
ISSN
1863-1703
eISSN
1863-1711
DOI
10.1007/s11760-018-1311-z
Publisher site
See Article on Publisher Site

Abstract

Human action recognition typically requires a large amount of training samples, which is often expensive and time-consuming to create. In this paper, we present a novel approach for enhancing human actions with a limited number of samples via structural average curves analysis. Our approach first learns average sequences from each pair of video samples for every action class and then gather them with original video samples together to form a new training set. Action modeling and recognition are proposed to be performed with the resulting new set. Our technique was evaluated on four benchmarking datasets. Our classification results are superior to those obtained with the original training sets, which suggests that the proposed method can potentially be integrated with other approaches to further improve their recognition performances.

Journal

"Signal, Image and Video Processing" – Springer Journals

Published: May 29, 2018

References

  • Action recognition based on statistical analysis from clustered flow vectors
    Mahbub, U; Imtiaz, H; Ahad, MAR
  • Spatio-temporal laplacian pyramid coding for action recognition
    Shao, L; Zhen, X; Tao, D; Li, X
  • Learning spatio-temporal features for action recognition from the side of the video
    Pei, L; Ye, M; Zhao, X; Xiang, T; Li, T
  • Combining 2d and 3d deep models for action recognition with depth information
    Keçeli, AS; Kaya, A; Can, AB
  • Evolutionary joint selection to improve human action recognition with rgb-d devices
    Chaaraoui, AA; Padilla-Lpez, JR; Climent-Prez, P; Flrez-Revuelta, F
  • Visual event recognition in videos by learning from web data
    Duan, L; Xu, D; Tsang, IH; Luo, J
  • Learning sparse representations for human action recognition
    Guha, T; Ward, RK
  • Pose-based human action recognition via sparse representation in dissimilarity space
    Theodorakopoulos, I; Kastaniotis, D; Economou, G; Fotopoulos, S
  • Action recognition from one example
    Seo, HJ; Milanfar, P
  • Methods for aligning and for averaging 3d volumes with missing data
    Schmid, MF; Booth, CR
  • Statistical comparisons of classifiers over multiple data sets
    Demsar, J
  • Core shape modelling of a set of curves
    Boudaoud, S; Rix, H; Meste, O
  • Data Analysis, Classification and the Forward Search
    Morlini, I; Zani, S
  • Enriching speech recognition with automatic detection of sentence boundaries and disfluencies
    Liu, Y; Shriberg, E; Stolcke, A; Hillard, D; Ostendorf, M; Harper, M
  • Learning action patterns in difference images for efficient action recognition
    Lu, G; Kudo, M