Overview of the MPEG-CDVS Standard

被引：101

作者：

Duan, Ling-Yu ^{[1
]}

Chandrasekhar, Vijay ^{[2
]}

Chen, Jie ^{[1
]}

Lin, Jie ^{[2
]}

Wang, Zhe ^{[1
]}

Huang, Tiejun ^{[1
]}

Girod, Bernd ^{[3
]}

Gao, Wen ^{[1
]}

机构：

[1] Peking Univ, Inst Digital Media, Sch Elect Engn & Comp Sci, Beijing 100871, Peoples R China

[2] Inst Infocomm Res, Singapore 138632, Singapore

[3] Stanford Univ, Dept Elect Engn, Informat Syst Lab, Stanford, CA 94305 USA

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 2016年 / 25卷 / 01期

关键词：

Compact descriptors; feature compression; MPEG-CDVS; visual search; BINARY AGGREGATED DESCRIPTORS; FISHER CODES; QUANTIZATION;

D O I：

10.1109/TIP.2015.2500034

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Compact descriptors for visual search (CDVS) is a recently completed standard from the ISO/IEC moving pictures experts group (MPEG). The primary goal of this standard is to provide a standardized bitstream syntax to enable interoperability in the context of image retrieval applications. Over the course of the standardization process, remarkable improvements were achieved in reducing the size of image feature data and in reducing the computation and memory footprint in the feature extraction process. This paper provides an overview of the technical features of the MPEG-CDVS standard and summarizes its evolution.

引用

页码：179 / 194

页数：16

共 63 条

[1] [Anonymous], 2010, PROC ACM SIGMM INT C
[2] [Anonymous], 2006, 2006 IEEE COMP SOC C
[3] [Anonymous], 2012, INT J COMPUT VISION, DOI DOI 10.1007/s11263-011-0472-9
[4] [Anonymous], 2011, P IEEE INT C MULT EX
[5] [Anonymous], 2007, P IEEE CVPR
[6] [Anonymous], JTC1SC29WG11M31369 I
[7] [Anonymous], P INT C MOB MULT COM
[8] [Anonymous], JTC1SC29WG11M23578 I
[9] [Anonymous], 15938132015 ISOIEC
[10] [Anonymous], 2011, JTC1SC29WG11N12367 I

← 1 2 3 4 5 6 7 →