English

End-to-End Attention-based Image Captioning

Computer Vision and Pattern Recognition 2021-05-03 v1 Artificial Intelligence

Abstract

In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow rule-based or CNN+RNN based methodology. However, they seem to underperform on noisy images and images with small number of distinguishable features. To overcome this, we propose an end-to-end transformer model. When compared to attention-based techniques, our proposed model outperforms on molecular datasets.

Keywords

Cite

@article{arxiv.2104.14721,
  title  = {End-to-End Attention-based Image Captioning},
  author = {Carola Sundaramoorthy and Lin Ziwen Kelvin and Mahak Sarin and Shubham Gupta},
  journal= {arXiv preprint arXiv:2104.14721},
  year   = {2021}
}
R2 v1 2026-06-24T01:39:21.338Z