Ghent University Academic Bibliography

Advanced

Spatio-temporal object recognition

Roeland De Geest, Francis Deboeverie, Wilfried Philips UGent and Tinne Tuytelaars (2015) Lecture Notes in Computer Science. 9386. p.681-692
abstract
Object recognition in video is in most cases solved by extracting keyframes from the video and then applying still image recognition methods on these keyframes only. This procedure largely ignores the temporal dimension. Nevertheless, the way an object moves may hold valuable information on its class. Therefore, in this work, we analyze the effectiveness of different motion descriptors, originally developed for action recognition, in the context of action-invariant object recognition. We conclude that a higher classification accuracy can be obtained when motion descriptors (specifically, HOG and MBH around trajectories) are used in combination with standard static descriptors extracted from keyframes. Since currently no suitable dataset for this problem exists, we introduce two new datasets and make them publicly available.
Please use this url to cite or link to this publication:
author
organization
year
type
conference (proceedingsPaper)
publication status
published
subject
in
Lecture Notes in Computer Science
LNCS
editor
Sebastiano Battiato, Jacques Blanc-Talon, Giovanni Gallo, Wilfried Philips UGent, Dan Popescu and Paul Scheunders
volume
9386
issue title
ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, ACIVS 2015
pages
681 - 692
publisher
Springer
conference name
16th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS)
conference location
Catania, Italy
conference start
2015-10-26
conference end
2015-10-29
Web of Science type
Proceedings Paper
Web of Science id
000374794500059
ISSN
0302-9743
ISBN
978-3-319-25902-4
DOI
10.1007/978-3-319-25903-1_59
language
English
UGent publication?
yes
classification
P1
copyright statement
I have transferred the copyright for this publication to the publisher
id
6986785
handle
http://hdl.handle.net/1854/LU-6986785
date created
2015-11-19 14:04:15
date last changed
2016-12-19 15:36:44
@inproceedings{6986785,
  abstract     = {Object recognition in video is in most cases solved by extracting keyframes from the video and then applying still image recognition methods on these keyframes only. This procedure largely ignores the temporal dimension. Nevertheless, the way an object moves may hold valuable information on its class. Therefore, in this work, we analyze the effectiveness of different motion descriptors, originally developed for action recognition, in the context of action-invariant object recognition. We conclude that a higher classification accuracy can be obtained when motion descriptors (specifically, HOG and MBH around trajectories) are used in combination with standard static descriptors extracted from keyframes. Since currently no suitable dataset for this problem exists, we introduce two new datasets and make them publicly available.},
  author       = {De Geest, Roeland and Deboeverie, Francis and Philips, Wilfried and Tuytelaars, Tinne},
  booktitle    = {Lecture Notes in Computer Science},
  editor       = {Battiato, Sebastiano and Blanc-Talon, Jacques and Gallo, Giovanni and Philips, Wilfried and Popescu, Dan and Scheunders, Paul},
  isbn         = {978-3-319-25902-4},
  issn         = {0302-9743},
  language     = {eng},
  location     = {Catania, Italy},
  pages        = {681--692},
  publisher    = {Springer},
  title        = {Spatio-temporal object recognition},
  url          = {http://dx.doi.org/10.1007/978-3-319-25903-1\_59},
  volume       = {9386},
  year         = {2015},
}

Chicago
De Geest, Roeland, Francis Deboeverie, Wilfried Philips, and Tinne Tuytelaars. 2015. “Spatio-temporal Object Recognition.” In Lecture Notes in Computer Science, ed. Sebastiano Battiato, Jacques Blanc-Talon, Giovanni Gallo, Wilfried Philips, Dan Popescu, and Paul Scheunders, 9386:681–692. Springer.
APA
De Geest, R., Deboeverie, F., Philips, W., & Tuytelaars, T. (2015). Spatio-temporal object recognition. In S. Battiato, J. Blanc-Talon, G. Gallo, W. Philips, D. Popescu, & P. Scheunders (Eds.), Lecture Notes in Computer Science (Vol. 9386, pp. 681–692). Presented at the 16th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS), Springer.
Vancouver
1.
De Geest R, Deboeverie F, Philips W, Tuytelaars T. Spatio-temporal object recognition. In: Battiato S, Blanc-Talon J, Gallo G, Philips W, Popescu D, Scheunders P, editors. Lecture Notes in Computer Science. Springer; 2015. p. 681–92.
MLA
De Geest, Roeland, Francis Deboeverie, Wilfried Philips, et al. “Spatio-temporal Object Recognition.” Lecture Notes in Computer Science. Ed. Sebastiano Battiato et al. Vol. 9386. Springer, 2015. 681–692. Print.