Interactive multimodal video search: an extended post-evaluation for the VBS 2022 competition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10488719" target="_blank" >RIV/00216208:11320/24:10488719 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=C0PSFYKptQ" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=C0PSFYKptQ</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s13735-024-00325-9" target="_blank" >10.1007/s13735-024-00325-9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Interactive multimodal video search: an extended post-evaluation for the VBS 2022 competition

Popis výsledku v původním jazyce

CLIP-based text-to-image retrieval has proven to be very effective at the interactive video retrieval competition Video Browser Showdown 2022, where all three top-scoring teams had implemented a variant of a CLIP model in their system. Since the performance of these three systems was quite close, this post-evaluation was designed to get better insights on the differences of the systems and compare the CLIP-based text-query retrieval engines by introducing slight modifications to the original competition settings. An extended analysis of the overall results and the retrieval performance of all systems&apos; functionalities shows that a strong text retrieval model certainly helps, but has to be coupled with extensive browsing capabilities and other query-modalities to consistently solve known-item-search tasks in a large-scale video database.

Název v anglickém jazyce

Interactive multimodal video search: an extended post-evaluation for the VBS 2022 competition

Popis výsledku anglicky

CLIP-based text-to-image retrieval has proven to be very effective at the interactive video retrieval competition Video Browser Showdown 2022, where all three top-scoring teams had implemented a variant of a CLIP model in their system. Since the performance of these three systems was quite close, this post-evaluation was designed to get better insights on the differences of the systems and compare the CLIP-based text-query retrieval engines by introducing slight modifications to the original competition settings. An extended analysis of the overall results and the retrieval performance of all systems&apos; functionalities shows that a strong text retrieval model certainly helps, but has to be coupled with extensive browsing capabilities and other query-modalities to consistently solve known-item-search tasks in a large-scale video database.

Druh

J_imp - Článek v periodiku v databázi Web of Science

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 periodika

International Journal of Multimedia Information Retrieval

ISSN

2192-6611

e-ISSN

2192-662X

Svazek periodika

13

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

13

Strana od-do

15

Kód UT WoS článku

001191286600001

EID výsledku v databázi Scopus

2-s2.0-85189147310