Compact Descriptors for Video Analysis: The Emerging MPEG Standard

Ling Yu Duan; Yihang Lou; Yan Bai; Tiejun Huang; Wen Gao; Vijay Chandrasekhar; Jie Lin; Shiqi Wang; Alex Chichung Kot

doi:10.1109/MMUL.2018.2873844

Compact Descriptors for Video Analysis: The Emerging MPEG Standard

Ling Yu Duan
, Yihang Lou
, Yan Bai
, Tiejun Huang
, Wen Gao
, Vijay Chandrasekhar
, Jie Lin
, Shiqi Wang
, Alex Chichung Kot

Research output: Contribution to journal › Article › peer-review

66 Scopus citations

Abstract

This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG). MPEG-CDVA targets at defining a standardized bitstream syntax to enable interoperability in the context of video analysis applications. During the developments of MPEG-CDVA, a series of techniques aiming to reduce the descriptor size and improve the video representation ability have been proposed. This paper describes the new standard that is being developed and reports the performance of these key technical contributions.

Original language	English
Article number	8509139
Pages (from-to)	44-54
Number of pages	11
Journal	IEEE Multimedia
Volume	26
Issue number	2
DOIs	https://doi.org/10.1109/MMUL.2018.2873844
State	Published - 1 Apr 2019
Externally published	Yes

Keywords

Compact Descriptor
Deep Learning
MPEG
Video Analysis

Access to Document

10.1109/MMUL.2018.2873844

Cite this

@article{ef453d1a11f94b8c8b0489056a98884c,

title = "Compact Descriptors for Video Analysis: The Emerging MPEG Standard",

abstract = "This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG). MPEG-CDVA targets at defining a standardized bitstream syntax to enable interoperability in the context of video analysis applications. During the developments of MPEG-CDVA, a series of techniques aiming to reduce the descriptor size and improve the video representation ability have been proposed. This paper describes the new standard that is being developed and reports the performance of these key technical contributions.",

keywords = "Compact Descriptor, Deep Learning, MPEG, Video Analysis",

author = "Duan, \{Ling Yu\} and Yihang Lou and Yan Bai and Tiejun Huang and Wen Gao and Vijay Chandrasekhar and Jie Lin and Shiqi Wang and Kot, \{Alex Chichung\}",

note = "Publisher Copyright: {\textcopyright} 1994-2012 IEEE.",

year = "2019",

month = apr,

day = "1",

doi = "10.1109/MMUL.2018.2873844",

language = "英语",

volume = "26",

pages = "44--54",

journal = "IEEE Multimedia",

issn = "1070-986X",

publisher = "IEEE Computer Society",

number = "2",

}

TY - JOUR

T1 - Compact Descriptors for Video Analysis

T2 - The Emerging MPEG Standard

AU - Duan, Ling Yu

AU - Lou, Yihang

AU - Bai, Yan

AU - Huang, Tiejun

AU - Gao, Wen

AU - Chandrasekhar, Vijay

AU - Lin, Jie

AU - Wang, Shiqi

AU - Kot, Alex Chichung

PY - 2019/4/1

Y1 - 2019/4/1

N2 - This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG). MPEG-CDVA targets at defining a standardized bitstream syntax to enable interoperability in the context of video analysis applications. During the developments of MPEG-CDVA, a series of techniques aiming to reduce the descriptor size and improve the video representation ability have been proposed. This paper describes the new standard that is being developed and reports the performance of these key technical contributions.

AB - This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG). MPEG-CDVA targets at defining a standardized bitstream syntax to enable interoperability in the context of video analysis applications. During the developments of MPEG-CDVA, a series of techniques aiming to reduce the descriptor size and improve the video representation ability have been proposed. This paper describes the new standard that is being developed and reports the performance of these key technical contributions.

KW - Compact Descriptor

KW - Deep Learning

KW - MPEG

KW - Video Analysis

UR - https://www.scopus.com/pages/publications/85055695567

U2 - 10.1109/MMUL.2018.2873844

DO - 10.1109/MMUL.2018.2873844

M3 - 文章

AN - SCOPUS:85055695567

SN - 1070-986X

VL - 26

SP - 44

EP - 54

JO - IEEE Multimedia

JF - IEEE Multimedia

IS - 2

M1 - 8509139

ER -

Compact Descriptors for Video Analysis: The Emerging MPEG Standard

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this