• DOI:10.1109/MIPR.2019.00085
Corpus ID: 133608221

Image Captioning with Clause-Focused Metrics in a Multi-modal Setting for Marketing

@article{Harzig2019ImageCW,
  title={Image Captioning with Clause-Focused Metrics in a Multi-modal Setting for Marketing},
  author={Philipp Harzig and D. Zecha and R. Lienhart and C. Kaiser and Ren{\'e} Schallner},
  journal={2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)},
  year={2019},
  pages={419-424}
}

Philipp Harzig, D. Zecha, +2 authors René Schallner

Published 2019

Computer Science

2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)

Automatically generating descriptive captions for images is a well-researched area in computer vision. However, existing evaluation approaches focus on measuring the similarity between two sentences disregarding fine-grained semantics of the captions. In our setting of images depicting persons interacting with branded products, the subject, predicate, object and the name of the branded product are important evaluation criteria of the generated captions. Generating image captions with these… CONTINUE READING

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed