@misc{paischer2023sitta,
  title={SITTA: A Semantic Image-Text Alignment for Image Captioning},
  author={Fabian Paischer and Thomas Adler and Markus Hofmarcher and Sepp Hochreiter},
  year={2023},
  eprint={2307.05591},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2307.05591}
}