A Fast Sub-Volume Search Method for Human Action Detection

Ping GUO; Zhenjiang MIAO; Xiao-Ping ZHANG; Zhe WANG

doi:10.1587/transinf.E95.D.285

A Fast Sub-Volume Search Method for Human Action Detection

Ping GUO, Zhenjiang MIAO, Xiao-Ping ZHANG, Zhe WANG

Full Text Views

0

Share
Cite this

Summary :

This paper discusses the task of human action detection. It requires not only classifying what type the action of interest is, but also finding actions' spatial-temporal locations in a video. The novelty of this paper lies on two significant aspects. One is to introduce a new graph based representation for the search space in a video. The other is to propose a novel sub-volume search method by Minimum Cycle detection. The proposed method has a low computation complexity while maintaining a high action detection accuracy. It is evaluated on two challenging datasets which are captured in cluttered backgrounds. The proposed approach outperforms other state-of-the-art methods in most situations in terms of both Precision-Recall values and running speeds.

Publication: IEICE TRANSACTIONS on Information Vol.E95-D No.1 pp.285-288

Publication Date: 2012/01/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E95.D.285

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Cite this

Copy

Ping GUO, Zhenjiang MIAO, Xiao-Ping ZHANG, Zhe WANG, "A Fast Sub-Volume Search Method for Human Action Detection" in IEICE TRANSACTIONS on Information, vol. E95-D, no. 1, pp. 285-288, January 2012, doi: 10.1587/transinf.E95.D.285.
Abstract: This paper discusses the task of human action detection. It requires not only classifying what type the action of interest is, but also finding actions' spatial-temporal locations in a video. The novelty of this paper lies on two significant aspects. One is to introduce a new graph based representation for the search space in a video. The other is to propose a novel sub-volume search method by Minimum Cycle detection. The proposed method has a low computation complexity while maintaining a high action detection accuracy. It is evaluated on two challenging datasets which are captured in cluttered backgrounds. The proposed approach outperforms other state-of-the-art methods in most situations in terms of both Precision-Recall values and running speeds.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E95.D.285/_p

Copy

@ARTICLE{e95-d_1_285,
author={Ping GUO, Zhenjiang MIAO, Xiao-Ping ZHANG, Zhe WANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Fast Sub-Volume Search Method for Human Action Detection},
year={2012},
volume={E95-D},
number={1},
pages={285-288},
abstract={This paper discusses the task of human action detection. It requires not only classifying what type the action of interest is, but also finding actions' spatial-temporal locations in a video. The novelty of this paper lies on two significant aspects. One is to introduce a new graph based representation for the search space in a video. The other is to propose a novel sub-volume search method by Minimum Cycle detection. The proposed method has a low computation complexity while maintaining a high action detection accuracy. It is evaluated on two challenging datasets which are captured in cluttered backgrounds. The proposed approach outperforms other state-of-the-art methods in most situations in terms of both Precision-Recall values and running speeds.},
keywords={},
doi={10.1587/transinf.E95.D.285},
ISSN={1745-1361},
month={January},}

Copy

TY - JOUR
TI - A Fast Sub-Volume Search Method for Human Action Detection
T2 - IEICE TRANSACTIONS on Information
SP - 285
EP - 288
AU - Ping GUO
AU - Zhenjiang MIAO
AU - Xiao-Ping ZHANG
AU - Zhe WANG
PY - 2012
DO - 10.1587/transinf.E95.D.285
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2012
AB - This paper discusses the task of human action detection. It requires not only classifying what type the action of interest is, but also finding actions' spatial-temporal locations in a video. The novelty of this paper lies on two significant aspects. One is to introduce a new graph based representation for the search space in a video. The other is to propose a novel sub-volume search method by Minimum Cycle detection. The proposed method has a low computation complexity while maintaining a high action detection accuracy. It is evaluated on two challenging datasets which are captured in cluttered backgrounds. The proposed approach outperforms other state-of-the-art methods in most situations in terms of both Precision-Recall values and running speeds.
ER -