Action recognition: A region based approach

Hakan Bilen, Vinay P. Namboodiri, Luc Van Gool

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

We address the problem of recognizing actions in reallife videos. Space-time interest point-based approaches have been widely prevalent towards solving this problem. In contrast, more spatially extended features such as regions have not been so popular. The reason is, any local region based approach requires the motion flow information for a specific region to be collated temporally. This is challenging as the local regions are deformable and not well delineated from the surroundings. In this paper we address this issue by using robust tracking of regions and we show that it is possible to obtain region descriptors for classification of actions. This paper lays the groundwork for further investigation into region based approaches. Through this paper we make the following contributions a) We advocate identification of salient regions based on motion segmentation b) We adopt a state-of-the art tracker for robust tracking of the identified regions rather than using isolated space-time blocks c) We propose optical flow based region descriptors to encode the extracted trajectories in piece-wise blocks. We demonstrate the performance of our system on real-world data sets.

Original languageEnglish
Title of host publication2011 IEEE Workshop on Applications of Computer Vision, WACV 2011
Pages294-300
Number of pages7
DOIs
Publication statusPublished - 16 Mar 2011
Event2011 IEEE Workshop on Applications of Computer Vision, WACV 2011 - Kona, HI, USA United States
Duration: 5 Jan 20117 Jan 2011

Publication series

Name2011 IEEE Workshop on Applications of Computer Vision, WACV 2011

Conference

Conference2011 IEEE Workshop on Applications of Computer Vision, WACV 2011
CountryUSA United States
CityKona, HI
Period5/01/117/01/11

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Bilen, H., Namboodiri, V. P., & Van Gool, L. (2011). Action recognition: A region based approach. In 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011 (pp. 294-300). [5711517] (2011 IEEE Workshop on Applications of Computer Vision, WACV 2011). https://doi.org/10.1109/WACV.2011.5711517

Action recognition : A region based approach. / Bilen, Hakan; Namboodiri, Vinay P.; Van Gool, Luc.

2011 IEEE Workshop on Applications of Computer Vision, WACV 2011. 2011. p. 294-300 5711517 (2011 IEEE Workshop on Applications of Computer Vision, WACV 2011).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bilen, H, Namboodiri, VP & Van Gool, L 2011, Action recognition: A region based approach. in 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011., 5711517, 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011, pp. 294-300, 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011, Kona, HI, USA United States, 5/01/11. https://doi.org/10.1109/WACV.2011.5711517
Bilen H, Namboodiri VP, Van Gool L. Action recognition: A region based approach. In 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011. 2011. p. 294-300. 5711517. (2011 IEEE Workshop on Applications of Computer Vision, WACV 2011). https://doi.org/10.1109/WACV.2011.5711517
Bilen, Hakan ; Namboodiri, Vinay P. ; Van Gool, Luc. / Action recognition : A region based approach. 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011. 2011. pp. 294-300 (2011 IEEE Workshop on Applications of Computer Vision, WACV 2011).
@inproceedings{33e28161abca44a7ab6d18ba1eb37286,
title = "Action recognition: A region based approach",
abstract = "We address the problem of recognizing actions in reallife videos. Space-time interest point-based approaches have been widely prevalent towards solving this problem. In contrast, more spatially extended features such as regions have not been so popular. The reason is, any local region based approach requires the motion flow information for a specific region to be collated temporally. This is challenging as the local regions are deformable and not well delineated from the surroundings. In this paper we address this issue by using robust tracking of regions and we show that it is possible to obtain region descriptors for classification of actions. This paper lays the groundwork for further investigation into region based approaches. Through this paper we make the following contributions a) We advocate identification of salient regions based on motion segmentation b) We adopt a state-of-the art tracker for robust tracking of the identified regions rather than using isolated space-time blocks c) We propose optical flow based region descriptors to encode the extracted trajectories in piece-wise blocks. We demonstrate the performance of our system on real-world data sets.",
author = "Hakan Bilen and Namboodiri, {Vinay P.} and {Van Gool}, Luc",
year = "2011",
month = "3",
day = "16",
doi = "10.1109/WACV.2011.5711517",
language = "English",
isbn = "9781424494965",
series = "2011 IEEE Workshop on Applications of Computer Vision, WACV 2011",
pages = "294--300",
booktitle = "2011 IEEE Workshop on Applications of Computer Vision, WACV 2011",

}

TY - GEN

T1 - Action recognition

T2 - A region based approach

AU - Bilen, Hakan

AU - Namboodiri, Vinay P.

AU - Van Gool, Luc

PY - 2011/3/16

Y1 - 2011/3/16

N2 - We address the problem of recognizing actions in reallife videos. Space-time interest point-based approaches have been widely prevalent towards solving this problem. In contrast, more spatially extended features such as regions have not been so popular. The reason is, any local region based approach requires the motion flow information for a specific region to be collated temporally. This is challenging as the local regions are deformable and not well delineated from the surroundings. In this paper we address this issue by using robust tracking of regions and we show that it is possible to obtain region descriptors for classification of actions. This paper lays the groundwork for further investigation into region based approaches. Through this paper we make the following contributions a) We advocate identification of salient regions based on motion segmentation b) We adopt a state-of-the art tracker for robust tracking of the identified regions rather than using isolated space-time blocks c) We propose optical flow based region descriptors to encode the extracted trajectories in piece-wise blocks. We demonstrate the performance of our system on real-world data sets.

AB - We address the problem of recognizing actions in reallife videos. Space-time interest point-based approaches have been widely prevalent towards solving this problem. In contrast, more spatially extended features such as regions have not been so popular. The reason is, any local region based approach requires the motion flow information for a specific region to be collated temporally. This is challenging as the local regions are deformable and not well delineated from the surroundings. In this paper we address this issue by using robust tracking of regions and we show that it is possible to obtain region descriptors for classification of actions. This paper lays the groundwork for further investigation into region based approaches. Through this paper we make the following contributions a) We advocate identification of salient regions based on motion segmentation b) We adopt a state-of-the art tracker for robust tracking of the identified regions rather than using isolated space-time blocks c) We propose optical flow based region descriptors to encode the extracted trajectories in piece-wise blocks. We demonstrate the performance of our system on real-world data sets.

UR - http://www.scopus.com/inward/record.url?scp=79952507257&partnerID=8YFLogxK

U2 - 10.1109/WACV.2011.5711517

DO - 10.1109/WACV.2011.5711517

M3 - Conference contribution

AN - SCOPUS:79952507257

SN - 9781424494965

T3 - 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011

SP - 294

EP - 300

BT - 2011 IEEE Workshop on Applications of Computer Vision, WACV 2011

ER -