Header

UZH-Logo

Maintenance Infos

Deep Learning-Based Concept Detection in vitrivr


Rossetto, Luca; Amiri Parian, Mahnaz; Gasser, Ralph; Giangreco, Ivan; Heller, Silvan; Schuldt, Heiko (2019). Deep Learning-Based Concept Detection in vitrivr. In: International Conference on Multimedia Modeling. MultiMedia Modeling. Heidelberg: Springer, 616-621.

Abstract

This paper presents the most recent additions to the vitrivr retrieval stack, which will be put to the test in the context of the 2019 Video Browser Showdown (VBS). The vitrivr stack has been extended by approaches for detecting, localizing, or describing concepts and actions in video scenes using various convolutional neural networks. Leveraging those additions, we have added support for searching the video collection based on semantic sketches. Furthermore, vitrivr offers new types of labels for text-based retrieval. In the same vein, we have also improved upon vitrivr’s pre-existing capabilities for extracting text from video through scene text recognition. Moreover, the user interface has received a major overhaul so as to make it more accessible to novice users, especially for query formulation and result exploration.

Abstract

This paper presents the most recent additions to the vitrivr retrieval stack, which will be put to the test in the context of the 2019 Video Browser Showdown (VBS). The vitrivr stack has been extended by approaches for detecting, localizing, or describing concepts and actions in video scenes using various convolutional neural networks. Leveraging those additions, we have added support for searching the video collection based on semantic sketches. Furthermore, vitrivr offers new types of labels for text-based retrieval. In the same vein, we have also improved upon vitrivr’s pre-existing capabilities for extracting text from video through scene text recognition. Moreover, the user interface has received a major overhaul so as to make it more accessible to novice users, especially for query formulation and result exploration.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Additional indexing

Item Type:Book Section, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Physical Sciences > Theoretical Computer Science
Physical Sciences > General Computer Science
Language:English
Date:11 January 2019
Deposited On:11 Dec 2019 14:58
Last Modified:25 May 2020 19:35
Publisher:Springer
ISBN:978-3-030-05715-2
OA Status:Closed
Publisher DOI:https://doi.org/10.1007/978-3-030-05716-9_55
Other Identification Number:merlin-id:18148

Download

Full text not available from this repository.
View at publisher

Get full-text in a library