W2VV BERT Model at VBS 2021
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10422767" target="_blank" >RIV/00216208:11320/21:10422767 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1007/978-3-030-67835-7_46" target="_blank" >https://doi.org/10.1007/978-3-030-67835-7_46</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-67835-7_46" target="_blank" >10.1007/978-3-030-67835-7_46</a>
Alternative languages
Result language
angličtina
Original language name
W2VV BERT Model at VBS 2021
Original language description
The W2VV++ model BoW variant integrated to VIRET and SOMHunter systems has proven its effectiveness in the previous Video Browser Showdown competition in 2020. As a next experimental interactive search prototype to benchmark, we consider a simple system relying on the more complex BERT variant of the W2VV++ model, accepting a rich text input. The input can be provided by keyboard or by speech processed by a third-party cloud service. The motivation for the more complex BERT variant is its good performance for rich text descriptions that can be provided for known-item search tasks. At the same time, users will be instructed to specify as rich text description about the searched scene as possible.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GJ19-22071Y" target="_blank" >GJ19-22071Y: Flexible models for known-item search in large video collections</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
MultiMedia Modeling
ISBN
978-3-030-67835-7
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
467-472
Publisher name
Springer International Publishing
Place of publication
Cham
Event location
Prague, Czech Republic
Event date
Jun 22, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—