Exquisitor at the Video Browser Showdown 2025: Unifying Conversational Search and User Relevance Feedback

Ujjwal Sharma; Omar Shahbaz Khan; Stevan Rudinac; Björn Þór Jónsson

doi:10.1007/978-981-96-2074-6_31

Exquisitor at the Video Browser Showdown 2025: Unifying Conversational Search and User Relevance Feedback

Ujjwal Sharma
, Omar Shahbaz Khan
, Stevan Rudinac
, Björn Þór Jónsson

Reykjavík University

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

Exquisitor is a multimedia retrieval system designed to combine conversational search and user relevance feedback to enhance interactive video search. In this work, we present recent improvements to Exquisitor, focusing on integrating these two search strategies into a unified, user-friendly interface. In this system edition set to participate at VBS 2025, we propose improvements for fusing results from the conversational search and user relevance feedback subsystems into a single search pane, an ability to launch multiple tabbed search instances and several improvements to the user interface to significantly improve user experience and search efficiency, particularly for novice users.

Original language	English
Title of host publication	MultiMedia Modeling
Editors	Ichiro Ide, Ioannis Kompatsiaris, Changsheng Xu, Keiji Yanai, Wei-Ta Chu, Naoko Nitta, Michael Riegler, Toshihiko Yamasaki
Number of pages	8
Place of Publication	Singapore
Publisher	Springer Nature Singapore
Publication date	Jan 2025
Pages	264-271
ISBN (Print)	9789819620739
ISBN (Electronic)	978-981-96-2074-6
DOIs	https://doi.org/10.1007/978-981-96-2074-6_31
Publication status	Published - Jan 2025
Externally published	Yes
Event	International Conference on Multimedia Modeling - Nara, Japan Duration: 9 Jan 2025 → 11 Jan 2025 Conference number: 31 https://mmm2025.net/

Conference

Conference	International Conference on Multimedia Modeling
Number	31
Country/Territory	Japan
City	Nara
Period	09/01/2025 → 11/01/2025
Internet address	https://mmm2025.net/

Keywords

Interactive learning
Multimedia Retrieval
Multimodal conversational search
Multimodal representation learning
Video browsing

Access to Document

10.1007/978-981-96-2074-6_31

Cite this

Sharma, U., Khan, O. S., Rudinac, S., & Jónsson, B. Þ. (2025). Exquisitor at the Video Browser Showdown 2025: Unifying Conversational Search and User Relevance Feedback. In I. Ide, I. Kompatsiaris, C. Xu, K. Yanai, W.-T. Chu, N. Nitta, M. Riegler, & T. Yamasaki (Eds.), MultiMedia Modeling (pp. 264-271). Springer Nature Singapore. https://doi.org/10.1007/978-981-96-2074-6_31

Sharma, Ujjwal ; Khan, Omar Shahbaz ; Rudinac, Stevan et al. / Exquisitor at the Video Browser Showdown 2025: Unifying Conversational Search and User Relevance Feedback. MultiMedia Modeling. editor / Ichiro Ide ; Ioannis Kompatsiaris ; Changsheng Xu ; Keiji Yanai ; Wei-Ta Chu ; Naoko Nitta ; Michael Riegler ; Toshihiko Yamasaki. Singapore : Springer Nature Singapore, 2025. pp. 264-271

@inproceedings{260176f14ee1439fb1142a1ef68eb6e9,

title = "Exquisitor at the Video Browser Showdown 2025: Unifying Conversational Search and User Relevance Feedback",

abstract = "Exquisitor is a multimedia retrieval system designed to combine conversational search and user relevance feedback to enhance interactive video search. In this work, we present recent improvements to Exquisitor, focusing on integrating these two search strategies into a unified, user-friendly interface. In this system edition set to participate at VBS 2025, we propose improvements for fusing results from the conversational search and user relevance feedback subsystems into a single search pane, an ability to launch multiple tabbed search instances and several improvements to the user interface to significantly improve user experience and search efficiency, particularly for novice users.",

keywords = "Interactive learning, Multimedia Retrieval, Multimodal conversational search, Multimodal representation learning, Video browsing",

author = "Ujjwal Sharma and Khan, \{Omar Shahbaz\} and Stevan Rudinac and J{\'o}nsson, \{Bj{\"o}rn {\TH}{\'o}r\}",

year = "2025",

month = jan,

doi = "10.1007/978-981-96-2074-6\_31",

language = "English",

isbn = "9789819620739",

pages = "264--271",

editor = "Ichiro Ide and Ioannis Kompatsiaris and Changsheng Xu and Keiji Yanai and Wei-Ta Chu and Naoko Nitta and Michael Riegler and Toshihiko Yamasaki",

booktitle = "MultiMedia Modeling",

publisher = "Springer Nature Singapore",

note = "International Conference on Multimedia Modeling, MMM ; Conference date: 09-01-2025 Through 11-01-2025",

url = "https://mmm2025.net/",

}

Sharma, U, Khan, OS, Rudinac, S & Jónsson, BÞ 2025, Exquisitor at the Video Browser Showdown 2025: Unifying Conversational Search and User Relevance Feedback. in I Ide, I Kompatsiaris, C Xu, K Yanai, W-T Chu, N Nitta, M Riegler & T Yamasaki (eds), MultiMedia Modeling. Springer Nature Singapore, Singapore, pp. 264-271, International Conference on Multimedia Modeling, Nara, Japan, 09/01/2025. https://doi.org/10.1007/978-981-96-2074-6_31

Exquisitor at the Video Browser Showdown 2025: Unifying Conversational Search and User Relevance Feedback. / Sharma, Ujjwal; Khan, Omar Shahbaz; Rudinac, Stevan et al.
MultiMedia Modeling. ed. / Ichiro Ide; Ioannis Kompatsiaris; Changsheng Xu; Keiji Yanai; Wei-Ta Chu; Naoko Nitta; Michael Riegler; Toshihiko Yamasaki. Singapore: Springer Nature Singapore, 2025. p. 264-271.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Exquisitor at the Video Browser Showdown 2025: Unifying Conversational Search and User Relevance Feedback

AU - Sharma, Ujjwal

AU - Khan, Omar Shahbaz

AU - Rudinac, Stevan

AU - Jónsson, Björn Þór

N1 - Conference code: 31

PY - 2025/1

Y1 - 2025/1

N2 - Exquisitor is a multimedia retrieval system designed to combine conversational search and user relevance feedback to enhance interactive video search. In this work, we present recent improvements to Exquisitor, focusing on integrating these two search strategies into a unified, user-friendly interface. In this system edition set to participate at VBS 2025, we propose improvements for fusing results from the conversational search and user relevance feedback subsystems into a single search pane, an ability to launch multiple tabbed search instances and several improvements to the user interface to significantly improve user experience and search efficiency, particularly for novice users.

AB - Exquisitor is a multimedia retrieval system designed to combine conversational search and user relevance feedback to enhance interactive video search. In this work, we present recent improvements to Exquisitor, focusing on integrating these two search strategies into a unified, user-friendly interface. In this system edition set to participate at VBS 2025, we propose improvements for fusing results from the conversational search and user relevance feedback subsystems into a single search pane, an ability to launch multiple tabbed search instances and several improvements to the user interface to significantly improve user experience and search efficiency, particularly for novice users.

KW - Interactive learning

KW - Multimedia Retrieval

KW - Multimodal conversational search

KW - Multimodal representation learning

KW - Video browsing

U2 - 10.1007/978-981-96-2074-6_31

DO - 10.1007/978-981-96-2074-6_31

M3 - Article in proceedings

SN - 9789819620739

SP - 264

EP - 271

BT - MultiMedia Modeling

A2 - Ide, Ichiro

A2 - Kompatsiaris, Ioannis

A2 - Xu, Changsheng

A2 - Yanai, Keiji

A2 - Chu, Wei-Ta

A2 - Nitta, Naoko

A2 - Riegler, Michael

A2 - Yamasaki, Toshihiko

PB - Springer Nature Singapore

CY - Singapore

T2 - International Conference on Multimedia Modeling

Y2 - 9 January 2025 through 11 January 2025