Master data

Title: diveXB: An Interactive Video Retrieval System for Beginners
Subtitle:
Abstract:

We present an interactive video retrieval system called diveXB (diveXplore for Beginners), which is an enhancement of our diveXplore system used for the recent Video Browser Showdown competitions. In addition to a common free-text search with text-image embeddings, diveXB integrates a new exploration component that allows browsing the video collection without any query. For this purpose, we employ k-means clustering of image embeddings that are extracted from video summaries with state-of-the-art vision transformers and select the most coherent clusters for query-free browsing in our user interface. First qualitative experiments have shown that this feature allows users to easily get an overview of the content structure in the video collection and to find desired content without the need for any textual input.

Keywords: image retrieval, similarity search, novice users
Publication type: Article in Proceedings (Authorship)
Publication date: 20.09.2023 (Print)
Published by: CBMI '23 Proceedings of the 20th International Conference on Content-based Multimedia Indexing
CBMI '23 Proceedings of the 20th International Conference on Content-based Multimedia Indexing
to publication
 ( ACM Digital Library; )
Title of the series: -
Volume number: -
First publication: Yes
Version: -
Page: pp. 153 - 157

Versionen

Keine Version vorhanden
Publication date: 20.09.2023
ISBN:
  • 979-8-4007-0912-8
ISSN: -
Homepage: https://dl.acm.org/doi/abs/10.1145/3617233.3617258
Publication date: 30.12.2023
ISBN (e-book): -
eISSN: -
DOI: http://dx.doi.org/10.1145/3617233.3617258
Homepage: https://dl.acm.org/doi/abs/10.1145/3617233.3617258
Open access
  • Available online (open access)

Assignment

Organisation Address
Fakultät für Technische Wissenschaften
 
Institut für Informationstechnologie
Universitaetsstr. 65-67
9020 Klagenfurt am Wörthersee
Austria
   martina.steinbacher@aau.at
http://itec.aau.at/
To organisation
Universitaetsstr. 65-67
AT - 9020  Klagenfurt am Wörthersee

Categorisation

Subject areas
  • 1020 - Computer Sciences
Research Cluster No research Research Cluster selected
Peer reviewed
  • Yes
Publication focus
  • Science to Science (Quality indicator: II)
Classification raster of the assigned organisational units:
working groups
  • Verteilte Systeme

Cooperations

No partner organisations selected

Articles of the publication

No related publications