Skip to main content
Springer Nature Link
Log in

Looking deeper and transferring attention for image captioning

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Image captioning is a challenging task which requires not only to extract semantic information but also to generate descriptions with correct sentences. Most of the previous researches employ one-layer or two-layer Recurrent Neural Network (RNN) as the language model to predict sentence words. The language model may easily deal with the word information for a noun or an object, however, it may not be able to learn a verb or an adjective. To address this issue, a deep attention based language model is proposed to learn more abstract word information and three stacked approaches are designed to process attention. The proposed model makes full use of the Long Short Term Memory (LSTM) network and employs the transferred current attention to enhance extra spatial information. The experimental results on the benchmark MSCOCO and Flickr30K datasets have verified the effectiveness of the proposed model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Banerjee S, Lavie A (2005) METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proc. ACL Workshop IEEMMTS’05, vol 29, pp 65–72

  2. Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915–1929

    Article  Google Scholar 

  3. Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth D (2010) Every picture tells a story: generating sentences from images. In: Proc. ECCV’10, pp 15–29

  4. Gong Y, Wang L, Hodosh M, Hockenmaier J, Lazebnik S (2014) Improving image-sentence embeddings using large weakly annotated photo collections. In: Proc. ECCV’14, pp 529–545

  5. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proc. CVPR’16, pp 770–778

  6. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  7. Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: data, models and evaluation metrics. J Artif Intell Res 47:853–899

    Article  MathSciNet  Google Scholar 

  8. Jia X, Gavves E, Fernando B, Tuytelaars T (2015) Guiding the long-short term memory model for image caption generation. In: Proc. ICCV’15, pp 2407–2415

  9. Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: Proc. CVPR’15, pp 3128–3137

  10. Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Proc. ECCV’14, pp 740–755

  11. Lu J, Xiong C, Parikh D, Socher R (2017) Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Proc. CVPR’17, pp 375–383

  12. Mao J, Xu W, Yang Y, Wang J, Huang Z, Yuille A (2015) Deep captioning with multimodal recurrent neural networks (m-RNN). In: Proc. ICLR’15

  13. Papineni K, Roukos S, Ward T, Zhu W (2002) BLEU: a method for automatic evaluation of machine translation. In: Proc. ACL’02, pp 311–318

  14. Prakash A, Hasan S, Lee K, Datla V, Qadir A, Liu J, Farri O (2016) Neural paraphrase generation with stacked residual LSTM networks. In: Proc. COLING’16, pp 2923–2934

  15. Reddy DR (1997) Speech understanding systems: a summary of results of the five-year research effort. Tech. rep., Carnegie-Mellon University. Computer Science Dept

  16. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proc. ICLR’15

  17. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958

    MathSciNet  MATH  Google Scholar 

  18. Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. In: Proc. NIPS’15, pp 2377–2385

  19. Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Proc. NIPS’14, pp 3104–3112

  20. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proc. CVPR’15, pp 1–9

  21. Vedantam R, Zitnick CL, Parikh D (2015) CIDEr: consensus-based image description evaluation. In: Proc. CVPR’15, pp 4566–4575

  22. Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: Proc. CVPR’15, pp 3156–3164

  23. Wu Q, Shen C, Liu L, Dick A, Hengel AVD (2016) What value do explicit high level concepts have in vision to language problems? In: Proc. CVPR’16, pp 203–212

  24. Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: Proc. ICML’15, pp 2048– 2057

  25. Yao T, Pan Y, Li Y, Qiu Z, Mei T (2017) Boosting image captioning with attributes. In: Proc. ICCV’17, pp 4894–4902

  26. You Q, Jin H, Wang Z, Fang C, Luo J (2015) Long-term recurrent convolutional networks for visual recognition and description. In: Proc. CVPR’15, pp 2625–2634

  27. You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: Proc. CVPR’16, pp 4651–4659

Download references

Acknowledgements

This work was supported in part by National Natural Science Foundation of China under Grants 61622115 and 61472281, Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning (No. GZ2015005), Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing (17DZ2251600), and IBM Shared University Research Awards Program.

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, Tongji University, Shanghai, 201804, China

    Fang Fang, Hanli Wang, Yihao Chen & Pengjie Tang

  2. Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, 200092, China

    Fang Fang, Hanli Wang, Yihao Chen & Pengjie Tang

  3. Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing, Shanghai, 200092, China

    Fang Fang, Hanli Wang, Yihao Chen & Pengjie Tang

Authors
  1. Fang Fang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Hanli Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yihao Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Pengjie Tang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Hanli Wang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fang, F., Wang, H., Chen, Y. et al. Looking deeper and transferring attention for image captioning. Multimed Tools Appl 77, 31159–31175 (2018). https://doi.org/10.1007/s11042-018-6228-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6228-6

Keywords

This website sets only cookies which are necessary for it to function. They are used to enable core functionality such as security, network management and accessibility. These cookies cannot be switched off in our systems. You may disable these by changing your browser settings, but this may affect how the website functions. Please view our privacy policy for further details on how we process your information.