Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Text-to-video: Story illustration from online photo collections

: Schwarz, Katharina; Rojtberg, Pavel; Caspar, Joachim; Gurevych, Iryna; Goesele, Michael; Lensch, Hendrik P. A.


Setchi, R.:
Knowledge-based and intelligent information and engineering systems. 14th International Conference, KES 2010. Pt.4 : Cardiff, UK, September 8-10, 2010, Proceedings
Berlin: Springer, 2010 (Lecture Notes in Artificial Intelligence 6279)
ISBN: 3-642-15383-6
ISBN: 978-3-642-15383-9
ISSN: 0302-9743
International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (KES) <14, 2010, Cardiff>
Workshop on 3D Visualisation of Natural Language <2010, Cardiff>
Conference Paper
Fraunhofer IGD ()
community photo collection; natural language processing; Forschungsgruppe Capturing Reality (CARE)

We present a first system to semi-automatically create a visual representation for a given, short text. We first parse the input text, decompose it into suitable units, and construct meaningful search terms. Using these search terms we retrieve a set of candidate images from online photo collections. We then select the final images in a user-assisted process and automatically create a storyboard or photomatic animation. We demonstrate promising initial results on several types of texts.