Video Search with Sub-Image Keyword Transfer Using Existing Image Archives
27th International Conference on Multimedia Modeling (MMM 2021)
TL;DR
This paper details our frame-based Ad-hoc video search system for the Video Browser Showdown 2021 (VBS2021), featuring enhanced automatic keywording, fine-tuned visual feature vectors, and improved search result presentation.
Abstract
This paper presents details of our frame-based Ad-hoc Video Search system with manually assisted querying that will be used for the Video Browser Showdown 2021 (VBS2021). The main contributions of our new system consist of an improved automatic keywording component, better visual feature vectors which have been fine-tuned for the task of image retrieval, and an improved visual presentation of the search results. Additionally, we use a more powerful joint textual/visual search engine based on Lucene, which can perform a search according to the temporal sequence of textual or visual properties of the video frames.
BibTeX
If you use our work in your research, please cite our publication:
@InProceedings{10.1007/978-3-030-67835-7_49,
author="Hezel, Nico
and Schall, Konstantin
and Jung, Klaus
and Barthel, Kai Uwe",
editor="Loko{\v{c}}, Jakub
and Skopal, Tom{\'a}{\v{s}}
and Schoeffmann, Klaus
and Mezaris, Vasileios
and Li, Xirong
and Vrochidis, Stefanos
and Patras, Ioannis",
title="Video Search with Sub-Image Keyword Transfer Using Existing Image Archives",
booktitle="MultiMedia Modeling",
year="2021",
publisher="Springer International Publishing",
address="Cham",
pages="484--489",
isbn="978-3-030-67835-7"
}