Known-Item Search in Video: An Eye Tracking-Based Study

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10490637" target="_blank" >RIV/00216208:11320/24:10490637 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1145/3652583.3658119" target="_blank" >https://doi.org/10.1145/3652583.3658119</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3652583.3658119" target="_blank" >10.1145/3652583.3658119</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Known-Item Search in Video: An Eye Tracking-Based Study

Popis výsledku v původním jazyce

Deep learning has revolutionized multimedia retrieval, yet effectively searching within large video collections remains a complex challenge. This paper focuses on the design and evaluation of known-item search systems, leveraging the strengths of CLIP-based deep neural networks for ranking. At events like the Video Browser Showdown, these models have shown promise in effectively ranking the video frames. While ranking models can be pre-selected automatically based on a benchmark collection, the selection of an optimal browsing interface, crucial for refining top-ranked items, is complex and heavily influenced by user behavior. Our study addresses this by presenting an eye tracking-based analysis of user interaction with different image grid layouts. This approach offers novel insights into search patterns and user preferences, particularly examining the trade-off between displaying fewer but larger images versus more but smaller images. Our findings reveal a preference for grids with fewer images and detail how image similarity and grid position affect user search behavior. These results not only enhance our understanding of effective video retrieval interface design but also set the stage for future advancements in the field.

Název v anglickém jazyce

Known-Item Search in Video: An Eye Tracking-Based Study

Popis výsledku anglicky

Deep learning has revolutionized multimedia retrieval, yet effectively searching within large video collections remains a complex challenge. This paper focuses on the design and evaluation of known-item search systems, leveraging the strengths of CLIP-based deep neural networks for ranking. At events like the Video Browser Showdown, these models have shown promise in effectively ranking the video frames. While ranking models can be pre-selected automatically based on a benchmark collection, the selection of an optimal browsing interface, crucial for refining top-ranked items, is complex and heavily influenced by user behavior. Our study addresses this by presenting an eye tracking-based analysis of user interaction with different image grid layouts. This approach offers novel insights into search patterns and user preferences, particularly examining the trade-off between displaying fewer but larger images versus more but smaller images. Our findings reveal a preference for grids with fewer images and detail how image similarity and grid position affect user search behavior. These results not only enhance our understanding of effective video retrieval interface design but also set the stage for future advancements in the field.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA22-21696S" target="_blank" >GA22-21696S: Hluboké vizuální reprezentace nestrukturovaných dat</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

PROCEEDINGS OF THE 14TH ANNUAL ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2024

ISBN

979-8-4007-0619-6

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

311-319

Název nakladatele

ASSOC COMPUTING MACHINERY

Místo vydání

NEW YORK

Místo konání akce

Phuket

Datum konání akce

10. 6. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001282078400035