Overview of Visual Signal Compression towards Machine Vision

Shurun Wang; Shiqi Wang; Yan Ye

doi:10.1145/3638036.3640291

Overview of Visual Signal Compression towards Machine Vision

Shurun Wang, Shiqi Wang, Yan Ye

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

Machine analysis of visual signals has been providing fundamental infrastructure support for artificial intelligence (AI) applications. As such, the compact representation of visual signal towards machine analysis is critical in current AI systems. A straightforward and general pipeline of visual signal compression for machines is to compress the visual signal, then perform the machine analysis on the reconstructed visual signal for ultimate results. This pipeline naturally supports multiple machine vision tasks and human perception, and is denoted as visual signal compression towards machines (VSCM). This paper provides an overview to summarize the VSCM related technologies in terms of various modules, and envision the future development of VSCM. © 2024 ACM.

Original language	English
Title of host publication	MHV '24
Subtitle of host publication	Proceedings of the 3rd Mile-High Video Conference
Publisher	Association for Computing Machinery
Pages	126-127
ISBN (Print)	979-8-4007-0493-2
DOIs	https://doi.org/10.1145/3638036.3640291
Publication status	Published - 2024
Event	3rd Mile-High Video Conference, MHV 2024 - Denver, United States Duration: 11 Feb 2024 → 14 Feb 2024

Publication series

Name	MHV - Proceedings of the 3rd Mile-High Video Conference

Conference

Conference	3rd Mile-High Video Conference, MHV 2024
Place	United States
City	Denver
Period	11/02/24 → 14/02/24

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 62022002, in part by the Hong Kong Research Grants Council General Research Fund 11203220, and in part by the Alibaba Innovative Research.

Research Keywords

compression towards machine vision
Visual signal compression

Access Output

10.1145/3638036.3640291

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{4fa3f71641a64bf9a596f8b9bd7aa31f,

title = "Overview of Visual Signal Compression towards Machine Vision",

abstract = "Machine analysis of visual signals has been providing fundamental infrastructure support for artificial intelligence (AI) applications. As such, the compact representation of visual signal towards machine analysis is critical in current AI systems. A straightforward and general pipeline of visual signal compression for machines is to compress the visual signal, then perform the machine analysis on the reconstructed visual signal for ultimate results. This pipeline naturally supports multiple machine vision tasks and human perception, and is denoted as visual signal compression towards machines (VSCM). This paper provides an overview to summarize the VSCM related technologies in terms of various modules, and envision the future development of VSCM. {\textcopyright} 2024 ACM.",

keywords = "compression towards machine vision, Visual signal compression",

author = "Shurun Wang and Shiqi Wang and Yan Ye",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).; 3rd Mile-High Video Conference, MHV 2024 ; Conference date: 11-02-2024 Through 14-02-2024",

year = "2024",

doi = "10.1145/3638036.3640291",

language = "English",

isbn = "979-8-4007-0493-2",

series = "MHV - Proceedings of the 3rd Mile-High Video Conference",

publisher = "Association for Computing Machinery",

pages = "126--127",

booktitle = "MHV '24",

address = "United States",

}

Wang, S, Wang, S & Ye, Y 2024, Overview of Visual Signal Compression towards Machine Vision. in MHV '24: Proceedings of the 3rd Mile-High Video Conference. MHV - Proceedings of the 3rd Mile-High Video Conference, Association for Computing Machinery, pp. 126-127, 3rd Mile-High Video Conference, MHV 2024, Denver, United States, 11/02/24. https://doi.org/10.1145/3638036.3640291

Overview of Visual Signal Compression towards Machine Vision. / Wang, Shurun; Wang, Shiqi; Ye, Yan.
MHV '24: Proceedings of the 3rd Mile-High Video Conference. Association for Computing Machinery, 2024. p. 126-127 (MHV - Proceedings of the 3rd Mile-High Video Conference).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Overview of Visual Signal Compression towards Machine Vision

AU - Wang, Shurun

AU - Wang, Shiqi

AU - Ye, Yan

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

PY - 2024

Y1 - 2024

N2 - Machine analysis of visual signals has been providing fundamental infrastructure support for artificial intelligence (AI) applications. As such, the compact representation of visual signal towards machine analysis is critical in current AI systems. A straightforward and general pipeline of visual signal compression for machines is to compress the visual signal, then perform the machine analysis on the reconstructed visual signal for ultimate results. This pipeline naturally supports multiple machine vision tasks and human perception, and is denoted as visual signal compression towards machines (VSCM). This paper provides an overview to summarize the VSCM related technologies in terms of various modules, and envision the future development of VSCM. © 2024 ACM.

AB - Machine analysis of visual signals has been providing fundamental infrastructure support for artificial intelligence (AI) applications. As such, the compact representation of visual signal towards machine analysis is critical in current AI systems. A straightforward and general pipeline of visual signal compression for machines is to compress the visual signal, then perform the machine analysis on the reconstructed visual signal for ultimate results. This pipeline naturally supports multiple machine vision tasks and human perception, and is denoted as visual signal compression towards machines (VSCM). This paper provides an overview to summarize the VSCM related technologies in terms of various modules, and envision the future development of VSCM. © 2024 ACM.

KW - compression towards machine vision

KW - Visual signal compression

UR - http://www.scopus.com/inward/record.url?scp=85188711337&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85188711337&origin=recordpage

U2 - 10.1145/3638036.3640291

DO - 10.1145/3638036.3640291

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-4007-0493-2

T3 - MHV - Proceedings of the 3rd Mile-High Video Conference

SP - 126

EP - 127

BT - MHV '24

PB - Association for Computing Machinery

T2 - 3rd Mile-High Video Conference, MHV 2024

Y2 - 11 February 2024 through 14 February 2024

ER -

Overview of Visual Signal Compression towards Machine Vision

Abstract

Publication series

Conference

Bibliographical note

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Towards Smart Visual Sensor Data Representation with Intelligent Sensing in the Internet of Video Things

Cite this

Overview of Visual Signal Compression towards Machine Vision

Abstract

Publication series

Conference

Bibliographical note

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Towards Smart Visual Sensor Data Representation with Intelligent Sensing in the Internet of Video Things

Cite this