Multimodal video-to-video linking: Turning to the crowd for insight and evaluation

Laurent Amsaleg (Editor), Maria Eskevich, Gylfi Þór Guðmundsson (Editor), Martha Larson, Robin Aly, Cathal Gurrin (Editor), Björn Þór Jónsson (Editor), Serwah Sabetghadam, Gareth J.F. Jones, Shin’ichi Satoh (Editor), Roeland J.F. Ordelman, Benoit Huet

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)
7 Downloads (Pure)

Abstract

Video-to-video linking systems allow users to explore and exploit the content of a large-scale multimedia collection interactively and without the need to formulate specific queries. We present a short introduction to video-to-video linking (also called ‘video hyperlinking’), and describe the latest edition of the Video Hyperlinking (LNK) task at TRECVid 2016. The emphasis of the LNK task in 2016 is on multimodality as used by videomakers to communicate their intended message. Crowdsourcing makes three critical contributions to the LNK task. First, it allows us to verify the multimodal nature of the anchors (queries) used in the task. Second, it enables us to evaluate the performance of video-to-video linking systems at large scale. Third, it gives us insights into how people understand the relevance relationship between two linked video segments. These insights are valuable since the relationship between video segments can manifest itself at different levels of abstraction.
Original languageEnglish
Title of host publicationMultimedia Modeling
Subtitle of host publicationProceedings of the 23rd International Conference on Multimedia Modeling, MMM 2017
Place of PublicationLondon
PublisherSpringer
Pages280-292
Number of pages13
ISBN (Print)978-3-319-51813-8
DOIs
Publication statusPublished - Jan 2017

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume10133
ISSN (Print)0302-9743

Fingerprint

Anchors

Keywords

  • IR-104402
  • EWI-27664

Cite this

Amsaleg, L. (Ed.), Eskevich, M., Guðmundsson, G. Þ. (Ed.), Larson, M., Aly, R., Gurrin, C. (Ed.), ... Huet, B. (2017). Multimodal video-to-video linking: Turning to the crowd for insight and evaluation. In Multimedia Modeling: Proceedings of the 23rd International Conference on Multimedia Modeling, MMM 2017 (pp. 280-292). (Lecture Notes in Computer Science; Vol. 10133). London: Springer. https://doi.org/10.1007/978-3-319-51814-5_24
Amsaleg, Laurent (Editor) ; Eskevich, Maria ; Guðmundsson, Gylfi Þór (Editor) ; Larson, Martha ; Aly, Robin ; Gurrin, Cathal (Editor) ; Jónsson, Björn Þór (Editor) ; Sabetghadam, Serwah ; Jones, Gareth J.F. ; Satoh, Shin’ichi (Editor) ; Ordelman, Roeland J.F. ; Huet, Benoit. / Multimodal video-to-video linking: Turning to the crowd for insight and evaluation. Multimedia Modeling: Proceedings of the 23rd International Conference on Multimedia Modeling, MMM 2017. London : Springer, 2017. pp. 280-292 (Lecture Notes in Computer Science).
@inproceedings{b1881c0008ee411886d88e85542e3d11,
title = "Multimodal video-to-video linking: Turning to the crowd for insight and evaluation",
abstract = "Video-to-video linking systems allow users to explore and exploit the content of a large-scale multimedia collection interactively and without the need to formulate specific queries. We present a short introduction to video-to-video linking (also called ‘video hyperlinking’), and describe the latest edition of the Video Hyperlinking (LNK) task at TRECVid 2016. The emphasis of the LNK task in 2016 is on multimodality as used by videomakers to communicate their intended message. Crowdsourcing makes three critical contributions to the LNK task. First, it allows us to verify the multimodal nature of the anchors (queries) used in the task. Second, it enables us to evaluate the performance of video-to-video linking systems at large scale. Third, it gives us insights into how people understand the relevance relationship between two linked video segments. These insights are valuable since the relationship between video segments can manifest itself at different levels of abstraction.",
keywords = "IR-104402, EWI-27664",
author = "Laurent Amsaleg and Maria Eskevich and Gu{\dh}mundsson, {Gylfi {\TH}{\'o}r} and Martha Larson and Robin Aly and Cathal Gurrin and J{\'o}nsson, {Bj{\"o}rn {\TH}{\'o}r} and Serwah Sabetghadam and Jones, {Gareth J.F.} and Shin’ichi Satoh and Ordelman, {Roeland J.F.} and Benoit Huet",
year = "2017",
month = "1",
doi = "10.1007/978-3-319-51814-5_24",
language = "English",
isbn = "978-3-319-51813-8",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "280--292",
booktitle = "Multimedia Modeling",

}

Amsaleg, L (ed.), Eskevich, M, Guðmundsson, GÞ (ed.), Larson, M, Aly, R, Gurrin, C (ed.), Jónsson, BÞ (ed.), Sabetghadam, S, Jones, GJF, Satoh, S (ed.), Ordelman, RJF & Huet, B 2017, Multimodal video-to-video linking: Turning to the crowd for insight and evaluation. in Multimedia Modeling: Proceedings of the 23rd International Conference on Multimedia Modeling, MMM 2017. Lecture Notes in Computer Science, vol. 10133, Springer, London, pp. 280-292. https://doi.org/10.1007/978-3-319-51814-5_24

Multimodal video-to-video linking: Turning to the crowd for insight and evaluation. / Amsaleg, Laurent (Editor); Eskevich, Maria; Guðmundsson, Gylfi Þór (Editor); Larson, Martha; Aly, Robin; Gurrin, Cathal (Editor); Jónsson, Björn Þór (Editor); Sabetghadam, Serwah; Jones, Gareth J.F.; Satoh, Shin’ichi (Editor); Ordelman, Roeland J.F.; Huet, Benoit.

Multimedia Modeling: Proceedings of the 23rd International Conference on Multimedia Modeling, MMM 2017. London : Springer, 2017. p. 280-292 (Lecture Notes in Computer Science; Vol. 10133).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Multimodal video-to-video linking: Turning to the crowd for insight and evaluation

AU - Eskevich, Maria

AU - Larson, Martha

AU - Aly, Robin

AU - Sabetghadam, Serwah

AU - Jones, Gareth J.F.

AU - Ordelman, Roeland J.F.

AU - Huet, Benoit

A2 - Amsaleg, Laurent

A2 - Guðmundsson, Gylfi Þór

A2 - Gurrin, Cathal

A2 - Jónsson, Björn Þór

A2 - Satoh, Shin’ichi

PY - 2017/1

Y1 - 2017/1

N2 - Video-to-video linking systems allow users to explore and exploit the content of a large-scale multimedia collection interactively and without the need to formulate specific queries. We present a short introduction to video-to-video linking (also called ‘video hyperlinking’), and describe the latest edition of the Video Hyperlinking (LNK) task at TRECVid 2016. The emphasis of the LNK task in 2016 is on multimodality as used by videomakers to communicate their intended message. Crowdsourcing makes three critical contributions to the LNK task. First, it allows us to verify the multimodal nature of the anchors (queries) used in the task. Second, it enables us to evaluate the performance of video-to-video linking systems at large scale. Third, it gives us insights into how people understand the relevance relationship between two linked video segments. These insights are valuable since the relationship between video segments can manifest itself at different levels of abstraction.

AB - Video-to-video linking systems allow users to explore and exploit the content of a large-scale multimedia collection interactively and without the need to formulate specific queries. We present a short introduction to video-to-video linking (also called ‘video hyperlinking’), and describe the latest edition of the Video Hyperlinking (LNK) task at TRECVid 2016. The emphasis of the LNK task in 2016 is on multimodality as used by videomakers to communicate their intended message. Crowdsourcing makes three critical contributions to the LNK task. First, it allows us to verify the multimodal nature of the anchors (queries) used in the task. Second, it enables us to evaluate the performance of video-to-video linking systems at large scale. Third, it gives us insights into how people understand the relevance relationship between two linked video segments. These insights are valuable since the relationship between video segments can manifest itself at different levels of abstraction.

KW - IR-104402

KW - EWI-27664

U2 - 10.1007/978-3-319-51814-5_24

DO - 10.1007/978-3-319-51814-5_24

M3 - Conference contribution

SN - 978-3-319-51813-8

T3 - Lecture Notes in Computer Science

SP - 280

EP - 292

BT - Multimedia Modeling

PB - Springer

CY - London

ER -

Amsaleg L, (ed.), Eskevich M, Guðmundsson GÞ, (ed.), Larson M, Aly R, Gurrin C, (ed.) et al. Multimodal video-to-video linking: Turning to the crowd for insight and evaluation. In Multimedia Modeling: Proceedings of the 23rd International Conference on Multimedia Modeling, MMM 2017. London: Springer. 2017. p. 280-292. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-51814-5_24