Scene Synthesis with Automated Generation of Textual Descriptions.

Julian Müller-Huschke Marcel Ritter Matthias Harders

Published in: Eurographics (Short Papers) (2022)

Keyphrases

textual descriptions
web images
image sequences
video sequences
semantic representation
computer vision
keywords
multi modal
database
metadata
feature extraction
object detection
visual features
semantic information
image regions
semantic concepts