Frame-level matching of near duplicate videos based on ternary frame descriptor and iterative refinement

Kyung Rae Kim; Won Dong Jang; Chang-Su Kim

doi:10.1109/ICIP.2015.7350753

Frame-level matching of near duplicate videos based on ternary frame descriptor and iterative refinement

Kyung Rae Kim, Won Dong Jang, Chang-Su Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

A frame-level video matching algorithm, which achieves dense frame matching between near-duplicate videos, is proposed in this work. First, we propose a ternary frame descriptor for the near-duplicate video matching. The ternary descriptor partitions a frame into patches and uses ternary digits to represent relations between pairs of patches. Second, we formulate the frame-level matching problem as the minimization of a cost function, which consists of matching costs and adaptive unmatching costs. We develop an iterative refinement scheme that converges to a local minimum of the cost function. The iterative scheme performs competitively with the global optimization techniques while demands a significantly lower computational complexity. Experimental results show that the proposed algorithm achieves effective frame description and efficient frame matching of near duplicate videos.

Original language	English
Title of host publication	Proceedings - International Conference on Image Processing, ICIP
Publisher	IEEE Computer Society
Pages	31-35
Number of pages	5
Volume	2015-December
ISBN (Print)	9781479983391
DOIs	https://doi.org/10.1109/ICIP.2015.7350753
Publication status	Published - 2015 Dec 9
Event	IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, Canada Duration: 2015 Sept 27 → 2015 Sept 30

Other

Other	IEEE International Conference on Image Processing, ICIP 2015
Country/Territory	Canada
City	Quebec City
Period	15/9/27 → 15/9/30

Keywords

frame-level video matching
iterative refinement
Near-duplicate video detection
ternary frame descriptor

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2015.7350753

Cite this

Frame-level matching of near duplicate videos based on ternary frame descriptor and iterative refinement. / Kim, Kyung Rae; Jang, Won Dong; Kim, Chang-Su.
Proceedings - International Conference on Image Processing, ICIP. Vol. 2015-December IEEE Computer Society, 2015. p. 31-35 7350753.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kim, KR, Jang, WD & Kim, C-S 2015, Frame-level matching of near duplicate videos based on ternary frame descriptor and iterative refinement. in Proceedings - International Conference on Image Processing, ICIP. vol. 2015-December, 7350753, IEEE Computer Society, pp. 31-35, IEEE International Conference on Image Processing, ICIP 2015, Quebec City, Canada, 15/9/27. https://doi.org/10.1109/ICIP.2015.7350753

@inproceedings{56b193a1a0fc436c857bff4fc9b52302,

title = "Frame-level matching of near duplicate videos based on ternary frame descriptor and iterative refinement",

abstract = "A frame-level video matching algorithm, which achieves dense frame matching between near-duplicate videos, is proposed in this work. First, we propose a ternary frame descriptor for the near-duplicate video matching. The ternary descriptor partitions a frame into patches and uses ternary digits to represent relations between pairs of patches. Second, we formulate the frame-level matching problem as the minimization of a cost function, which consists of matching costs and adaptive unmatching costs. We develop an iterative refinement scheme that converges to a local minimum of the cost function. The iterative scheme performs competitively with the global optimization techniques while demands a significantly lower computational complexity. Experimental results show that the proposed algorithm achieves effective frame description and efficient frame matching of near duplicate videos.",

keywords = "frame-level video matching, iterative refinement, Near-duplicate video detection, ternary frame descriptor",

author = "Kim, {Kyung Rae} and Jang, {Won Dong} and Chang-Su Kim",

year = "2015",

month = dec,

day = "9",

doi = "10.1109/ICIP.2015.7350753",

language = "English",

isbn = "9781479983391",

volume = "2015-December",

pages = "31--35",

booktitle = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

note = "IEEE International Conference on Image Processing, ICIP 2015 ; Conference date: 27-09-2015 Through 30-09-2015",

}

TY - GEN

T1 - Frame-level matching of near duplicate videos based on ternary frame descriptor and iterative refinement

AU - Kim, Kyung Rae

AU - Jang, Won Dong

AU - Kim, Chang-Su

PY - 2015/12/9

Y1 - 2015/12/9

N2 - A frame-level video matching algorithm, which achieves dense frame matching between near-duplicate videos, is proposed in this work. First, we propose a ternary frame descriptor for the near-duplicate video matching. The ternary descriptor partitions a frame into patches and uses ternary digits to represent relations between pairs of patches. Second, we formulate the frame-level matching problem as the minimization of a cost function, which consists of matching costs and adaptive unmatching costs. We develop an iterative refinement scheme that converges to a local minimum of the cost function. The iterative scheme performs competitively with the global optimization techniques while demands a significantly lower computational complexity. Experimental results show that the proposed algorithm achieves effective frame description and efficient frame matching of near duplicate videos.

AB - A frame-level video matching algorithm, which achieves dense frame matching between near-duplicate videos, is proposed in this work. First, we propose a ternary frame descriptor for the near-duplicate video matching. The ternary descriptor partitions a frame into patches and uses ternary digits to represent relations between pairs of patches. Second, we formulate the frame-level matching problem as the minimization of a cost function, which consists of matching costs and adaptive unmatching costs. We develop an iterative refinement scheme that converges to a local minimum of the cost function. The iterative scheme performs competitively with the global optimization techniques while demands a significantly lower computational complexity. Experimental results show that the proposed algorithm achieves effective frame description and efficient frame matching of near duplicate videos.

KW - frame-level video matching

KW - iterative refinement

KW - Near-duplicate video detection

KW - ternary frame descriptor

UR - http://www.scopus.com/inward/record.url?scp=84956625613&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956625613&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7350753

DO - 10.1109/ICIP.2015.7350753

M3 - Conference contribution

AN - SCOPUS:84956625613

SN - 9781479983391

VL - 2015-December

SP - 31

EP - 35

BT - Proceedings - International Conference on Image Processing, ICIP

PB - IEEE Computer Society

T2 - IEEE International Conference on Image Processing, ICIP 2015

Y2 - 27 September 2015 through 30 September 2015

ER -

Frame-level matching of near duplicate videos based on ternary frame descriptor and iterative refinement

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this