• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. VisionKG: Towards a unified vision knowledge graph
 
  • Details
  • Full
Options
2021
Conference Paper
Title

VisionKG: Towards a unified vision knowledge graph

Abstract
Computer Vision (CV) has recently achieved signi_cant im-provements, thanks to the evolution of deep learning. Along with ad-vanced architectures and optimisations of deep neural networks, CV data for (cross-datasets) training, validating, and testing contributes greatly to the performance of CV models. Many CV datasets have been created for different tasks, but they are available in heterogeneous data formats and semantic representations. Therefore, it is challenging when one needs to combine different datasets either for training or testing purposes. This paper proposes a unified framework using the Semantic Web technology that provides a novel way to interlink and integrate labelled data across different data sources. We demonstrate its advantages via various sce-narios with the system framework accessible both online and via APIs.4.
Author(s)
Le-Tuan, Anh
Technische Universität Berlin  
Tran, Trung-Kien
Bosch center for artificial intelligence
Nguyen-Duc, Manh
Technische Universität Berlin  
Yuan, Jicheng
Technische Universität Berlin  
Hauswirth, Manfred  
Technische Universität Berlin  
Phuoc, Danh Le
Technische Universität Berlin  
Mainwork
ISWC 2021 Posters, Demos and Industry Tracks. Proceedings  
Conference
International Semantic Web Conference (ISWC) 2021  
Link
Link
Language
English
Fraunhofer-Institut für Offene Kommunikationssysteme FOKUS  
  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024