A Survey on Video Moment Localization

Meng Liu; Liqiang Nie; Yunxiao Wang; Meng Wang; Yong Rui

doi:10.1145/3556537

A Survey on Video Moment Localization

Meng Liu
, Liqiang Nie^*
, Yunxiao Wang
, Meng Wang
, Yong Rui

^*Corresponding author for this work

Shandong Jianzhu University
Harbin Institute of Technology Shenzhen
Shandong University
Hefei University of Technology
Lenovo Research

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

46 Scopus citations

Abstract

Video moment localization, also known as video moment retrieval, aims to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models.

Original language	English
Article number	3556537
Journal	ACM Computing Surveys
Volume	55
Issue number	9
DOIs	https://doi.org/10.1145/3556537
State	Published - 30 Sep 2023
Externally published	Yes

Keywords

Video moment localization
cross-modal retrieval
survey
video moment retrieval
vision and language

Access to Document

10.1145/3556537

Cite this

@article{7bf59c47f8a4457587266032ac12af87,

title = "A Survey on Video Moment Localization",

abstract = "Video moment localization, also known as video moment retrieval, aims to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models.",

keywords = "Video moment localization, cross-modal retrieval, survey, video moment retrieval, vision and language",

author = "Meng Liu and Liqiang Nie and Yunxiao Wang and Meng Wang and Yong Rui",

note = "Publisher Copyright: {\textcopyright} 2023 Association for Computing Machinery.",

year = "2023",

month = sep,

day = "30",

doi = "10.1145/3556537",

language = "英语",

volume = "55",

journal = "ACM Computing Surveys",

issn = "0360-0300",

publisher = "Association for Computing Machinery ",

number = "9",

}

TY - JOUR

T1 - A Survey on Video Moment Localization

AU - Liu, Meng

AU - Nie, Liqiang

AU - Wang, Yunxiao

AU - Wang, Meng

AU - Rui, Yong

PY - 2023/9/30

Y1 - 2023/9/30

N2 - Video moment localization, also known as video moment retrieval, aims to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models.

AB - Video moment localization, also known as video moment retrieval, aims to search a target segment within a video described by a given natural language query. Beyond the task of temporal action localization whereby the target actions are pre-defined, video moment retrieval can query arbitrary complex activities. In this survey paper, we aim to present a comprehensive review of existing video moment localization techniques, including supervised, weakly supervised, and unsupervised ones. We also review the datasets available for video moment localization and group results of related work. In addition, we discuss promising future directions for this field, in particular large-scale datasets and interpretable video moment localization models.

KW - Video moment localization

KW - cross-modal retrieval

KW - survey

KW - video moment retrieval

KW - vision and language

UR - https://www.scopus.com/pages/publications/85147855781

U2 - 10.1145/3556537

DO - 10.1145/3556537

M3 - 文章

AN - SCOPUS:85147855781

SN - 0360-0300

VL - 55

JO - ACM Computing Surveys

JF - ACM Computing Surveys

IS - 9

M1 - 3556537

ER -

A Survey on Video Moment Localization

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this