1 code implementation • 6 May 2019 • Philipp Harzig, Dan Zecha, Rainer Lienhart, Carolin Kaiser, René Schallner
Furthermore, we introduce a novel metric that allows us to assess whether the generated captions meet our requirements (i. e., subject, predicate, object, and product name) and describe a series of experiments on caption quality and how to address annotator disagreements for the image ratings with an approach called soft targets.
no code implementations • 6 Feb 2018 • Philipp Harzig, Stephan Brehm, Rainer Lienhart, Carolin Kaiser, René Schallner
Thanks to adding the third output modality, it also considerably improves the quality of generated captions for images depicting branded products.