Exquisitor at the Lifelog Search Challenge 2020

Omar Shahbaz Khan; Mathias Dybkjær Larsen; Liam Alex Sonto Poulsen; Björn Thór Jónsson; Jan Zahálka; Stevan Rudinac; Dennis C. Koelma; Marcel Worring

doi:10.1145/3379172.3391718

Exquisitor at the Lifelog Search Challenge 2020

Omar Shahbaz Khan, Mathias Dybkjær Larsen, Liam Alex Sonto Poulsen, Björn Thór Jónsson, Jan Zahálka, Stevan Rudinac, Dennis C. Koelma, Marcel Worring

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

Abstract

We present an enhanced version of Exquisitor, our interactive and scalable media exploration system. At its core, Exquisitor is an interactive learning system using relevance feedback on media items to build a model of the users' information need. Relying on efficient media representation and indexing, it facilitates real-time user interaction. The new features for the Lifelog Search Challenge 2020 include support for timeline browsing, search functionality for finding positive examples, and significant interface improvements. Participation in the Lifelog Search Challenge allows us to compare our paradigm, relying predominantly on interactive learning, with more traditional search-based multimedia retrieval systems.

Originalsprog	Engelsk
Titel	Proceedings of the ACM Workshop on Lifelog Search Challenge, LSC@ICMR 2020
Redaktører	Cathal Gurrin, Klaus Schöffmann, Björn Þór Jónsson, Duc-Tien Dang-Nguyen, Jakub Lokoč, Minh-Triet Tran, Wolfgang Hürst
Udgivelsessted	Dublin, Ireland
Forlag	Association for Computing Machinery
Publikationsdato	jun. 2020
Sider	19-22
ISBN (Elektronisk)	978-1-4503-7136-0
DOI	https://doi.org/10.1145/3379172.3391718
Status	Udgivet - jun. 2020

Adgang til dokumentet

10.1145/3379172.3391718

Exquisitor__LSC_2020Accepteret manuskript, 2,09 MB

Citationsformater

Khan, O. S., Larsen, M. D., Poulsen, L. A. S., Jónsson, B. T., Zahálka, J., Rudinac, S., Koelma, D. C., & Worring, M. (2020). Exquisitor at the Lifelog Search Challenge 2020. I C. Gurrin, K. Schöffmann, B. Þ. Jónsson, D.-T. Dang-Nguyen, J. Lokoč, M.-T. Tran, & W. Hürst (red.), Proceedings of the ACM Workshop on Lifelog Search Challenge, LSC@ICMR 2020 (s. 19-22). Association for Computing Machinery. https://doi.org/10.1145/3379172.3391718

Khan, Omar Shahbaz ; Larsen, Mathias Dybkjær ; Poulsen, Liam Alex Sonto et al. / Exquisitor at the Lifelog Search Challenge 2020. Proceedings of the ACM Workshop on Lifelog Search Challenge, LSC@ICMR 2020. red. / Cathal Gurrin ; Klaus Schöffmann ; Björn Þór Jónsson ; Duc-Tien Dang-Nguyen ; Jakub Lokoč ; Minh-Triet Tran ; Wolfgang Hürst. Dublin, Ireland : Association for Computing Machinery, 2020. s. 19-22

@inproceedings{66fc16df78c4401cba6e4550d89c57c9,

title = "Exquisitor at the Lifelog Search Challenge 2020",

abstract = "We present an enhanced version of Exquisitor, our interactive and scalable media exploration system. At its core, Exquisitor is an interactive learning system using relevance feedback on media items to build a model of the users' information need. Relying on efficient media representation and indexing, it facilitates real-time user interaction. The new features for the Lifelog Search Challenge 2020 include support for timeline browsing, search functionality for finding positive examples, and significant interface improvements. Participation in the Lifelog Search Challenge allows us to compare our paradigm, relying predominantly on interactive learning, with more traditional search-based multimedia retrieval systems.",

keywords = "Interactive Learning System, Relevance Feedback, Media Exploration, Real-Time User Interaction, Multimedia Retrieval Systems",

author = "Khan, {Omar Shahbaz} and Larsen, {Mathias Dybkj{\ae}r} and Poulsen, {Liam Alex Sonto} and J{\'o}nsson, {Bj{\"o}rn Th{\'o}r} and Jan Zah{\'a}lka and Stevan Rudinac and Koelma, {Dennis C.} and Marcel Worring",

year = "2020",

month = jun,

doi = "10.1145/3379172.3391718",

language = "English",

pages = "19--22",

editor = "Cathal Gurrin and Klaus Sch{\"o}ffmann and J{\'o}nsson, {Bj{\"o}rn {\TH}{\'o}r} and Duc-Tien Dang-Nguyen and Jakub Loko{\v c} and Minh-Triet Tran and Wolfgang H{\"u}rst",

booktitle = "Proceedings of the ACM Workshop on Lifelog Search Challenge, LSC@ICMR 2020",

publisher = "Association for Computing Machinery",

address = "United States",

}

Khan, OS, Larsen, MD, Poulsen, LAS, Jónsson, BT, Zahálka, J, Rudinac, S, Koelma, DC & Worring, M 2020, Exquisitor at the Lifelog Search Challenge 2020. i C Gurrin, K Schöffmann, BÞ Jónsson, D-T Dang-Nguyen, J Lokoč, M-T Tran & W Hürst (red), Proceedings of the ACM Workshop on Lifelog Search Challenge, LSC@ICMR 2020. Association for Computing Machinery, Dublin, Ireland, s. 19-22. https://doi.org/10.1145/3379172.3391718

Exquisitor at the Lifelog Search Challenge 2020. / Khan, Omar Shahbaz; Larsen, Mathias Dybkjær; Poulsen, Liam Alex Sonto et al.
Proceedings of the ACM Workshop on Lifelog Search Challenge, LSC@ICMR 2020. red. / Cathal Gurrin; Klaus Schöffmann; Björn Þór Jónsson; Duc-Tien Dang-Nguyen; Jakub Lokoč; Minh-Triet Tran; Wolfgang Hürst. Dublin, Ireland: Association for Computing Machinery, 2020. s. 19-22.

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Exquisitor at the Lifelog Search Challenge 2020

AU - Khan, Omar Shahbaz

AU - Larsen, Mathias Dybkjær

AU - Poulsen, Liam Alex Sonto

AU - Jónsson, Björn Thór

AU - Zahálka, Jan

AU - Rudinac, Stevan

AU - Koelma, Dennis C.

AU - Worring, Marcel

PY - 2020/6

Y1 - 2020/6

N2 - We present an enhanced version of Exquisitor, our interactive and scalable media exploration system. At its core, Exquisitor is an interactive learning system using relevance feedback on media items to build a model of the users' information need. Relying on efficient media representation and indexing, it facilitates real-time user interaction. The new features for the Lifelog Search Challenge 2020 include support for timeline browsing, search functionality for finding positive examples, and significant interface improvements. Participation in the Lifelog Search Challenge allows us to compare our paradigm, relying predominantly on interactive learning, with more traditional search-based multimedia retrieval systems.

AB - We present an enhanced version of Exquisitor, our interactive and scalable media exploration system. At its core, Exquisitor is an interactive learning system using relevance feedback on media items to build a model of the users' information need. Relying on efficient media representation and indexing, it facilitates real-time user interaction. The new features for the Lifelog Search Challenge 2020 include support for timeline browsing, search functionality for finding positive examples, and significant interface improvements. Participation in the Lifelog Search Challenge allows us to compare our paradigm, relying predominantly on interactive learning, with more traditional search-based multimedia retrieval systems.

KW - Interactive Learning System

KW - Relevance Feedback

KW - Media Exploration

KW - Real-Time User Interaction

KW - Multimedia Retrieval Systems

U2 - 10.1145/3379172.3391718

DO - 10.1145/3379172.3391718

M3 - Article in proceedings

SP - 19

EP - 22

BT - Proceedings of the ACM Workshop on Lifelog Search Challenge, LSC@ICMR 2020

A2 - Gurrin, Cathal

A2 - Schöffmann, Klaus

A2 - Jónsson, Björn Þór

A2 - Dang-Nguyen, Duc-Tien

A2 - Lokoč, Jakub

A2 - Tran, Minh-Triet

A2 - Hürst, Wolfgang

PB - Association for Computing Machinery

CY - Dublin, Ireland

ER -

Khan OS, Larsen MD, Poulsen LAS, Jónsson BT, Zahálka J, Rudinac S et al. Exquisitor at the Lifelog Search Challenge 2020. I Gurrin C, Schöffmann K, Jónsson BÞ, Dang-Nguyen DT, Lokoč J, Tran MT, Hürst W, red., Proceedings of the ACM Workshop on Lifelog Search Challenge, LSC@ICMR 2020. Dublin, Ireland: Association for Computing Machinery. 2020. s. 19-22 doi: 10.1145/3379172.3391718

Exquisitor at the Lifelog Search Challenge 2020

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater