Advertisement

Towards Cycle-Consistent Models for Text and Image Retrieval

  • Marcella CorniaEmail author
  • Lorenzo Baraldi
  • Hamed R. Tavakoli
  • Rita Cucchiara
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11132)

Abstract

Cross-modal retrieval has been recently becoming an hot-spot research, thanks to the development of deeply-learnable architectures. Such architectures generally learn a joint multi-modal embedding space in which text and images could be projected and compared. Here we investigate a different approach, and reformulate the problem of cross-modal retrieval as that of learning a translation between the textual and visual domain. In particular, we propose an end-to-end trainable model which can translate text into image features and vice versa, and regularizes this mapping with a cycle-consistency criterion. Preliminary experimental evaluations show promising results with respect to ordinary visual-semantic models.

Keywords

Cross-modal retrieval Cycle consistency Visual-semantic models 

Notes

Acknowledgments

We gratefully acknowledge the support of Facebook AI Research and NVIDIA Corporation with the donation of the GPUs used for this research.

References

  1. 1.
    Baraldi, L., Cornia, M., Grana, C., Cucchiara, R.: Aligning text and document illustrations: towards visually explainable digital humanities. In: International Conference on Pattern Recognition (2018)Google Scholar
  2. 2.
    Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. arXiv preprint arXiv:1607.04606 (2016)
  3. 3.
    Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: Paying more attention to saliency: image captioning with saliency and context attention. ACM Trans. Multimedia Comput. Commun. Appl. 14(2), 48:1–48:21 (2018)CrossRefGoogle Scholar
  4. 4.
    Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: British Machine Vision Conference (2018)Google Scholar
  5. 5.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE International Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  6. 6.
    Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853–899 (2013)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: IEEE International Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  8. 8.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  9. 9.
    Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)
  10. 10.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems (2013)Google Scholar
  11. 11.
    Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing (2014)Google Scholar
  12. 12.
    Shetty, R., Tavakoli, H.R., Laaksonen, J.: Image and video captioning with augmented neural architectures. IEEE MultiMedia 25, 34–46 (2018)CrossRefGoogle Scholar
  13. 13.
    Tavakoli, H.R., Shetty, R., Borji, A., Laaksonen, J.: Paying attention to descriptions generated by image captioning models. In: IEEE International Conference on Computer Vision (2017)Google Scholar
  14. 14.
    Wang, L., Li, Y., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell. (2018)Google Scholar
  15. 15.
    Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67–78 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Marcella Cornia
    • 1
    Email author
  • Lorenzo Baraldi
    • 1
  • Hamed R. Tavakoli
    • 2
  • Rita Cucchiara
    • 1
  1. 1.University of Modena and Reggio EmiliaModenaItaly
  2. 2.Aalto UniversityEspooFinland

Personalised recommendations