A fast binary pair-based video descriptor for action recognition

Roberto Leyva; Victor Sanchez; Chang-Tsun Li

doi:10.1109/ICIP.2016.7533148

A fast binary pair-based video descriptor for action recognition

Roberto Leyva, Victor Sanchez, Chang-Tsun Li

Research output: Book chapter/Published conference paper › Conference paper › peer-review

6 Citations (Scopus)

4 Downloads (Pure)

Abstract

Inspired by the binary-based descriptors (e.g. LBP, ALOHA, FREAK, BRISK), we propose the 3D Binary Pair Differences (3DBPD) video descriptor for action recognition. By comparing several spatio-temporal sub-regions around interests points, our descriptor is a feature vector with a dimensionality of up to 30% smaller than that of existing state-of-the-art descriptors. We demonstrate the effectiveness of the 3DBPD descriptor for action recognition with a SVM classifier and a simple Bag Of Video Words (BOV) generated using k-means. The proposed descriptor has very competitive recognition rates compared to other state-of-the-art descriptors, with an outstanding performance in terms of speed. Additionally, the 3DBPD descriptor requires a small codebook compared to those required by existing BOV-based descriptors.

Original language	English
Title of host publication	2016 IEEE International Conference on Image Processing, (ICIP)
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	4185-4189
Number of pages	5
ISBN (Print)	9781467399616
DOIs	https://doi.org/10.1109/ICIP.2016.7533148
Publication status	Published - 2016
Event	2016 23rd IEEE International Conference on Image Processing: ICIP 2016 - Phoenix Convention Center, Phoenix, United States Duration: 25 Sep 2016 → 28 Sep 2016 Conference number: 125190 http://2016.ieeeicip.org/default.asp

Conference

Conference	2016 23rd IEEE International Conference on Image Processing
Country/Territory	United States
City	Phoenix
Period	25/09/16 → 28/09/16
Internet address	http://2016.ieeeicip.org/default.asp

Access to Document

10.1109/ICIP.2016.7533148

Cite this

@inproceedings{21df9531817a4e53b2c2ce9cc5cedcec,

title = "A fast binary pair-based video descriptor for action recognition",

abstract = "Inspired by the binary-based descriptors (e.g. LBP, ALOHA, FREAK, BRISK), we propose the 3D Binary Pair Differences (3DBPD) video descriptor for action recognition. By comparing several spatio-temporal sub-regions around interests points, our descriptor is a feature vector with a dimensionality of up to 30% smaller than that of existing state-of-the-art descriptors. We demonstrate the effectiveness of the 3DBPD descriptor for action recognition with a SVM classifier and a simple Bag Of Video Words (BOV) generated using k-means. The proposed descriptor has very competitive recognition rates compared to other state-of-the-art descriptors, with an outstanding performance in terms of speed. Additionally, the 3DBPD descriptor requires a small codebook compared to those required by existing BOV-based descriptors.",

author = "Roberto Leyva and Victor Sanchez and Chang-Tsun Li",

note = "Includes bibliographical references.; 2016 23rd IEEE International Conference on Image Processing : ICIP 2016 ; Conference date: 25-09-2016 Through 28-09-2016",

year = "2016",

doi = "10.1109/ICIP.2016.7533148",

language = "English",

isbn = "9781467399616",

pages = "4185--4189",

booktitle = "2016 IEEE International Conference on Image Processing, (ICIP)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

url = "http://2016.ieeeicip.org/default.asp",

}

Leyva, R, Sanchez, V & Li, C-T 2016, A fast binary pair-based video descriptor for action recognition. in 2016 IEEE International Conference on Image Processing, (ICIP)., 7533148, IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 4185-4189, 2016 23rd IEEE International Conference on Image Processing, Phoenix, Arizona, United States, 25/09/16. https://doi.org/10.1109/ICIP.2016.7533148

A fast binary pair-based video descriptor for action recognition. / Leyva, Roberto; Sanchez, Victor; Li, Chang-Tsun.

2016 IEEE International Conference on Image Processing, (ICIP). United States : IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 4185-4189 7533148.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - A fast binary pair-based video descriptor for action recognition

AU - Leyva, Roberto

AU - Sanchez, Victor

AU - Li, Chang-Tsun

N1 - Conference code: 125190

PY - 2016

Y1 - 2016

N2 - Inspired by the binary-based descriptors (e.g. LBP, ALOHA, FREAK, BRISK), we propose the 3D Binary Pair Differences (3DBPD) video descriptor for action recognition. By comparing several spatio-temporal sub-regions around interests points, our descriptor is a feature vector with a dimensionality of up to 30% smaller than that of existing state-of-the-art descriptors. We demonstrate the effectiveness of the 3DBPD descriptor for action recognition with a SVM classifier and a simple Bag Of Video Words (BOV) generated using k-means. The proposed descriptor has very competitive recognition rates compared to other state-of-the-art descriptors, with an outstanding performance in terms of speed. Additionally, the 3DBPD descriptor requires a small codebook compared to those required by existing BOV-based descriptors.

AB - Inspired by the binary-based descriptors (e.g. LBP, ALOHA, FREAK, BRISK), we propose the 3D Binary Pair Differences (3DBPD) video descriptor for action recognition. By comparing several spatio-temporal sub-regions around interests points, our descriptor is a feature vector with a dimensionality of up to 30% smaller than that of existing state-of-the-art descriptors. We demonstrate the effectiveness of the 3DBPD descriptor for action recognition with a SVM classifier and a simple Bag Of Video Words (BOV) generated using k-means. The proposed descriptor has very competitive recognition rates compared to other state-of-the-art descriptors, with an outstanding performance in terms of speed. Additionally, the 3DBPD descriptor requires a small codebook compared to those required by existing BOV-based descriptors.

U2 - 10.1109/ICIP.2016.7533148

DO - 10.1109/ICIP.2016.7533148

M3 - Conference paper

SN - 9781467399616

SP - 4185

EP - 4189

BT - 2016 IEEE International Conference on Image Processing, (ICIP)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - 2016 23rd IEEE International Conference on Image Processing

Y2 - 25 September 2016 through 28 September 2016

ER -

A fast binary pair-based video descriptor for action recognition

Abstract

Conference

Access to Document

Fingerprint

Cite this