Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Towards more robust fashion recognition by combining of deep-learning-based detection with semantic reasoning

: Reiz, Achim; Albadawi, Mohamad; Sandkuhl, Kurt; Vahl, Matthias; Sidin, Dennis

Fulltext ()

Martin, A. ; Association for the Advancement of Artificial Intelligence -AAAI-:
AAAI Spring Symposium on Combining Machine Learning and Knowledge Engineering, AAAI-MAKE 2021. Online resource : Proceedings of the AAAI 2021 Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE 2021), Stanford University, Palo Alto, California, USA, March 22-24, 2021
La Clusaz: CEUR, 2021 (CEUR Workshop Proceedings 2846)
ISSN: 1613-0073
URN: urn:nbn:de:0074-2846-4
12 pp.
Spring Symposium on Combining Machine Learning and Knowledge Engineering (AAAI-MAKE) <2021, Online>
European Commission EC
Kl-based object recognition and semanticsupported content analysis
Conference Paper, Electronic Publication
Fraunhofer IGD, Institutsteil Rostock ()
image classification; deep learning; convolutional neural network (CNN); Lead Topic: Visual Computing as a Service; Research Line: Computer vision (CV); object detection; semantic analysis; targeted advertisement

The company FutureTV produces and distributes self-produced videos in the fashion domain. It creates revenue through the placement of relevant advertising. The placement of apposite ads, though, requires an understanding of the contents of the videos. Until now, this tagging is created manually in a labor-intensive process. We believe that image recognition technologies can significantly decrease the need for manual involvement in the tagging process. However, the tagging of videos comes with additional challenges: Preliminary, new deep-learning models need to be trained on vast amounts of data obtained in a labor-intensive data-collection process. We suggest a new approach for the combining of deep-learning-based recognition with a semantic reasoning engine. Through the explicit declaration of knowledge fitting to the fashion categories present in the training data of the recognition system, we argue that it is possible to refine the recognition results and win extra k nowledge beyond what is found in the neural net.