Exquisitor at the Video Browser Showdown 2024: Relevance Feedback Meets Conversational Search

Omar Shahbaz Khan; Hongyi Zhu; Ujjwal Sharma; Evangelos Kanoulas; Stevan Rudinac; Björn Þór Jónsson

doi:10.1007/978-3-031-53302-0_31

Exquisitor at the Video Browser Showdown 2024: Relevance Feedback Meets Conversational Search

Omar Shahbaz Khan
, Hongyi Zhu
, Ujjwal Sharma
, Evangelos Kanoulas
, Stevan Rudinac
, Björn Þór Jónsson

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

Abstract

An important open problem in video retrieval and exploration concerns the generation and refinement of queries for complex tasks that standard methods are unable to solve, especially when the systems are used by novices. In conversational search, the proposed approach is to ask users to interactively refine the information provided to the search process, until results are satisfactory. In user relevance feedback (URF), the proposed approach is to ask users to interactively judge query results, which in turn refines the query used to retrieve the next set of suggestions. The question that we seek to answer in the long term is how to integrate these two approaches: can the query refinements of conversational search directly impact the URF model, and can URF judgments directly impact the conversational search? We extend the existing Exquisitor URF system with conversational search. In this version of Exquisitor, the two modes of interaction are separate, but the user interface has been completely redesigned to (a) prepare for future integration with conversational search and (b) better support novice users.

Original language	English
Title of host publication	MultiMedia Modeling
Editors	Stevan Rudinac, Alan Hanjalic, Cynthia Liem, Marcel Worring, Björn Þór Jónsson, Bei Liu, Yoko Yamakata
Number of pages	9
Place of Publication	Cham
Publisher	Springer Nature Switzerland
Publication date	29 Jan 2024
Pages	347-355
ISBN (Print)	978-3-031-53301-3
ISBN (Electronic)	978-3-031-53302-0
DOIs	https://doi.org/10.1007/978-3-031-53302-0_31
Publication status	Published - 29 Jan 2024
Externally published	Yes
Event	International Conference on Multimedia Modeling - Netherlands, Amsterdam, Netherlands Duration: 29 Jan 2024 → 2 Feb 2024 Conference number: 30 https://mmm2024.org/

Conference

Conference	International Conference on Multimedia Modeling
Number	30
Location	Netherlands
Country/Territory	Netherlands
City	Amsterdam
Period	29/01/2024 → 02/02/2024
Internet address	https://mmm2024.org/

Keywords

video retrieval
conversational search
query refinement
user relevance feedback
exploratory search

Access to Document

10.1007/978-3-031-53302-0_31Licence: Unspecified

Cite this

Khan, O. S., Zhu, H., Sharma, U., Kanoulas, E., Rudinac, S., & Jónsson, B. Þ. (2024). Exquisitor at the Video Browser Showdown 2024: Relevance Feedback Meets Conversational Search. In S. Rudinac, A. Hanjalic, C. Liem, M. Worring, B. Þ. Jónsson, B. Liu, & Y. Yamakata (Eds.), MultiMedia Modeling (pp. 347-355). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-53302-0_31

@inproceedings{4854effc2344498096796338ba5f6500,

title = "Exquisitor at the Video Browser Showdown 2024: Relevance Feedback Meets Conversational Search",

abstract = "An important open problem in video retrieval and exploration concerns the generation and refinement of queries for complex tasks that standard methods are unable to solve, especially when the systems are used by novices. In conversational search, the proposed approach is to ask users to interactively refine the information provided to the search process, until results are satisfactory. In user relevance feedback (URF), the proposed approach is to ask users to interactively judge query results, which in turn refines the query used to retrieve the next set of suggestions. The question that we seek to answer in the long term is how to integrate these two approaches: can the query refinements of conversational search directly impact the URF model, and can URF judgments directly impact the conversational search? We extend the existing Exquisitor URF system with conversational search. In this version of Exquisitor, the two modes of interaction are separate, but the user interface has been completely redesigned to (a) prepare for future integration with conversational search and (b) better support novice users.",

keywords = "video retrieval, conversational search, query refinement, user relevance feedback, exploratory search",

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

year = "2024",

month = jan,

day = "29",

doi = "10.1007/978-3-031-53302-0\_31",

language = "English",

isbn = "978-3-031-53301-3",

pages = "347--355",

editor = "Stevan Rudinac and Alan Hanjalic and Cynthia Liem and Marcel Worring and J{\'o}nsson, \{Bj{\"o}rn {\TH}{\'o}r\} and Bei Liu and Yoko Yamakata",

booktitle = "MultiMedia Modeling",

publisher = "Springer Nature Switzerland",

note = "International Conference on Multimedia Modeling, MMM ; Conference date: 29-01-2024 Through 02-02-2024",

url = "https://mmm2024.org/",

}

Khan, OS, Zhu, H, Sharma, U, Kanoulas, E, Rudinac, S & Jónsson, BÞ 2024, Exquisitor at the Video Browser Showdown 2024: Relevance Feedback Meets Conversational Search. in S Rudinac, A Hanjalic, C Liem, M Worring, BÞ Jónsson, B Liu & Y Yamakata (eds), MultiMedia Modeling. Springer Nature Switzerland, Cham, pp. 347-355, International Conference on Multimedia Modeling, Amsterdam, Netherlands, 29/01/2024. https://doi.org/10.1007/978-3-031-53302-0_31

Exquisitor at the Video Browser Showdown 2024: Relevance Feedback Meets Conversational Search. / Khan, Omar Shahbaz; Zhu, Hongyi; Sharma, Ujjwal et al.
MultiMedia Modeling. ed. / Stevan Rudinac; Alan Hanjalic; Cynthia Liem; Marcel Worring; Björn Þór Jónsson; Bei Liu; Yoko Yamakata. Cham: Springer Nature Switzerland, 2024. p. 347-355.

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 2024: Relevance Feedback Meets Conversational Search

AU - Khan, Omar Shahbaz

AU - Zhu, Hongyi

AU - Sharma, Ujjwal

AU - Kanoulas, Evangelos

AU - Rudinac, Stevan

AU - Jónsson, Björn Þór

N1 - Conference code: 30

PY - 2024/1/29

Y1 - 2024/1/29

N2 - An important open problem in video retrieval and exploration concerns the generation and refinement of queries for complex tasks that standard methods are unable to solve, especially when the systems are used by novices. In conversational search, the proposed approach is to ask users to interactively refine the information provided to the search process, until results are satisfactory. In user relevance feedback (URF), the proposed approach is to ask users to interactively judge query results, which in turn refines the query used to retrieve the next set of suggestions. The question that we seek to answer in the long term is how to integrate these two approaches: can the query refinements of conversational search directly impact the URF model, and can URF judgments directly impact the conversational search? We extend the existing Exquisitor URF system with conversational search. In this version of Exquisitor, the two modes of interaction are separate, but the user interface has been completely redesigned to (a) prepare for future integration with conversational search and (b) better support novice users.

AB - An important open problem in video retrieval and exploration concerns the generation and refinement of queries for complex tasks that standard methods are unable to solve, especially when the systems are used by novices. In conversational search, the proposed approach is to ask users to interactively refine the information provided to the search process, until results are satisfactory. In user relevance feedback (URF), the proposed approach is to ask users to interactively judge query results, which in turn refines the query used to retrieve the next set of suggestions. The question that we seek to answer in the long term is how to integrate these two approaches: can the query refinements of conversational search directly impact the URF model, and can URF judgments directly impact the conversational search? We extend the existing Exquisitor URF system with conversational search. In this version of Exquisitor, the two modes of interaction are separate, but the user interface has been completely redesigned to (a) prepare for future integration with conversational search and (b) better support novice users.

KW - video retrieval

KW - conversational search

KW - query refinement

KW - user relevance feedback

KW - exploratory search

U2 - 10.1007/978-3-031-53302-0_31

DO - 10.1007/978-3-031-53302-0_31

M3 - Article in proceedings

SN - 978-3-031-53301-3

SP - 347

EP - 355

BT - MultiMedia Modeling

A2 - Rudinac, Stevan

A2 - Hanjalic, Alan

A2 - Liem, Cynthia

A2 - Worring, Marcel

A2 - Jónsson, Björn Þór

A2 - Liu, Bei

A2 - Yamakata, Yoko

PB - Springer Nature Switzerland

CY - Cham

T2 - International Conference on Multimedia Modeling

Y2 - 29 January 2024 through 2 February 2024