[go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Semantic association enhancement transformer with relative position for image captioning

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

Abstract

Transformer-based architectures have shown encouraging results in image captioning. They usually utilize self-attention based methods to establish the semantic association between objects in an image for predicting caption. However, when appearance features between the candidate object and query object show weak dependence, the self-attention based methods are hard to capture the semantic association between them. In this paper, a Semantic Association Enhancement Transformer model is proposed to address the above challenge. First, an Appearance-Geometry Multi-Head Attention is introduced to model a visual relationship by integrating the geometry features and appearance features of the objects. The visual relationship characterizes the semantic association and relative position among the objects. Secondly, a Visual Relationship Improving module is presented to weigh the importance of appearance feature and geometry feature of query object to the modeled visual relationship. Then, the visual relationship among different objects is adaptively improved according to the constructed importance, especially the objects with weak dependence on appearance features, thereby enhancing their semantic association. Extensive experiments on MS COCO dataset demonstrate that the proposed method outperforms the state-of-the-art methods.

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
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Anderson P, Fernando B, Johnson M, Gould S (2016) Spice: semantic propositional image caption evaluation. In: European conference on computer vision (ECCV), pp 382–398

  2. Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 6077–6086

  3. Ashish N, Vaswani S, Niki P, Jakob U, Llion J, Aidan NG, Lukasz K, Illia P (2017) Attention is all you need. In: Conference and workshop on neural information processing systems (NeurlPS), pp 5998–6008

  4. Banerjee S, Lavie A (2005) Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Annual meeting of the association for computational linguistics (ACL), pp 65–72

  5. Bansal M, Kumar M, Kumar M (2021) 2d object recognition techniques: state-of-the-art work. Arch Comput Methods Eng 28(3):1147–1161

    Article  MathSciNet  Google Scholar 

  6. Chhabra P, Garg NK, Kumar M (2020) Content-based image retrieval system using orb and sift features. Neural Comput Applic 32(7):2725–2733

    Article  Google Scholar 

  7. Cornia M, Stefanini M, Baraldi L, Cucchiara R (2020) Meshed-memory transformer for image captioning. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 10575–10584

  8. Deng J, Dong W, Socher R, Li L, Li K, Feifei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 248–255

  9. Devlin J, Chang MW, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the conference of the North American chapter of the association for computational linguistics: human language technologies (NAACL-HLT), pp 4171–4186

  10. Gao L, Li X, Song J, Shen HT (2020) Hierarchical lstms with adaptive attention for visual captioning. IEEE Trans Pattern Anal Mach Intell 42 (5):1112–1131

    Google Scholar 

  11. Guo L, Liu J, Lu S, Lu H (2020) Show, tell, and polish: ruminant decoding for image captioning. IEEE Trans Multimodal (TMM) 22(8):2149–2162

    Article  Google Scholar 

  12. Guo L, Liu J, Zhu X, Yao P, Lu S, Lu H (2020) Normalized and geometry-aware self-attention network for image captioning. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 10324–10333

  13. Herdade S, Kappeler A, Boakye K, Soares J (2019) Image captioning: transforming objects into words. In: Conference and workshop on neural information processing systems (NeurlPS), pp 11135–11145

  14. Hu H, Gu J, Zhang Z, Dai J, Wei Y (2018) Relation networks for object detection. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 3588–3597

  15. Huang L, Wang W, Xia Y, Chen J (2019) Adaptively aligned image captioning via adaptive attention time. In: Conference and workshop on neural information processing systems (NeurlPS), pp 8942–8951

  16. Huang Y, Chen J, Ouyang W, Wan W, Xue Y (2020) Image captioning with end-to-end attribute detection and subsequent attributes prediction. IEEE Trans Image Process (TIP) 29:4013–4026

    Article  Google Scholar 

  17. Ji J, Xu C, Zhang X, Wang B, Song X (2020) Spatio-temporal memory attention for image captioning. IEEE Trans Image Process (TIP) 29:7615–7628

    Article  Google Scholar 

  18. Jiang W, Ma L, Jiang Y, Liu W, Zhang T (2018) Recurrent fusion network for image captioning. In: European conference on computer vision (ECCV), pp 510–526

  19. Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li L, Shamma DA, Bernstein MS, Li F (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis (IJCV) 123(1):32–73

    Article  MathSciNet  Google Scholar 

  20. Kumar M, Chhabra P, Garg NK (2018) An efficient content based image retrieval system using bayesnet and k-nn. Multimed Tools Appl 77(16):21557–21570

    Article  Google Scholar 

  21. Kumar M, Kumar M, et al. (2021) Xgboost: 2d-object recognition using shape descriptors and extreme gradient boosting classifier. In: International conference on computational methods and data engineering (ICCMDE), pp 207–222

  22. Li G, Zhu L, Liu P, Yang Y (2019) Entangled transformer for image captioning. In: IEEE International conference on computer vision (ICCV), pp 8928–8937

  23. Li J, Yao P, Guo L, Zhang W (2019) Boosted transformer for image captioning. Appl Sci 9(16):3260

    Article  Google Scholar 

  24. Lin C (2004) Rouge: a package for automatic evaluation of summaries. In: Annual meeting of the association for computational linguistics (ACL), pp 74–81

  25. Lin T, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision (ECCV), pp 740–755

  26. Naqvi N, Ye Z (2021) Image captions: global-local and joint signals attention model (gl-jsam). Multimed Tools Appl 79(33):24429–24448

    Google Scholar 

  27. Papineni K, Roukos S, Ward T, Zhu W (2002) Bleu: a method for automatic evaluation of machine translation. In: Annual meeting of the association for computational linguistics (ACL), pp 311–318

  28. Qin Y, Du J, Zhang Y, Lu H (2019) Look back and predict forward in image captioning. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 8367–8375

  29. Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Conference and workshop on neural information processing systems (NeurlPS), pp 91–99

  30. Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2017) Self-critical sequence training for image captioning. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 1179–1195

  31. Ryan K, Ruslan S, Richard SZ (2014) Unifying visual-semantic embeddings with multimodal neural language models. In: arXiv:1411.253

  32. Shen X, Liu B, Zhou Y, Zhao J (2020) Remote sensing image caption generation via transformer and reinforcement learning. Multimed Tools Appl 79(35):26661–26682

    Article  Google Scholar 

  33. Shi Z, Zhou X, Qiu X, Zhu X (2020) Improving image captioning with better use of captions. In: Annual meeting of the association for computational linguistics (ACL), pp 7454–7464

  34. Tran A, Mathews A, Xie L (2020) Transform and tell: entity-aware news image captioning. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 13032–13042

  35. Vedantam R, Zitnick CL, Parikh D (2015) Cider: consensus-based image description evaluation. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 4566–4575

  36. Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: a neural image caption generator. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 3156–3164

  37. Wang L, Bai Z, Zhang Y, Lu H (2020) Show, recall, and tell: image captioning with recall mechanism. In: AAAI Conference on artificial intelligence (AAAI), pp 12176–12183

  38. Wang S, Lan L, Zhang X, Luo Z (2020) Gatecap: gated spatial and semantic attention model for image captioning. Multimed Tools Appl 79 (17):11531–11549

    Article  Google Scholar 

  39. Wen Z, Peng Y (2020) Multi-level knowledge injecting for visual commonsense reasoning. IEEE Trans Circ Syst Vid Technol (TCSVT) 31(3):1042–1054

    Article  Google Scholar 

  40. Wu J, Chen T, Wu H, Yang Z, Luo G, Lin L (2020) Fine-grained image captioning with global-local discriminative objective. IEEE Transactions on Multimedia (TMM). https://doi.org/10.1109/TMM.2020.3011317

  41. Wu L, Xu M, Sang L, Yao T, Mei T (2020) Noise augmented double-stream graph convolutional networks for image captioning. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). https://doi.org/10.1109/TCSVT.2020.3036860

  42. Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhutdinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning (ICML), pp 2048–2057

  43. Yan C, Hao Y, Li L, Yin J, Liu A, Mao Z, Chen Z, Gao X (2021) Task-adaptive attention for image captioning. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). https://doi.org/10.1109/TCSVT.2021.3067449

  44. Yang L, Wang H, Tang P, Li Q (2021) Captionnet: a tailor-made recurrent neural network for generating image descriptions. IEEE Trans Multimed (TMM) 23:835–845

    Article  Google Scholar 

  45. Yang X, Tang K, Zhang H, Cai J (2019) Auto-encoding scene graphs for image captioning. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 10685–10694

  46. Yao T, Pan Y, Li Y, Mei T (2018) Exploring visual relationship for image captioning. In: European conference on computer vision (ECCV), pp 711–727

  47. Yao T, Pan Y, Li Y, Mei T (2019) Hierarchy parsing for image captioning. In: IEEE International conference on computer vision (ICCV), pp 2621–2629

  48. Yu J, Li J, Yu Z, Huang Q (2020) Multimodal transformer with multi-view visual representation for image captioning. IEEE Trans Circ Syst Video Technol (TCSVT) 30(12):4467–4480

    Article  Google Scholar 

  49. Zhang Y, Shi X, Mi S, Yang X (2021) Image captioning with transformer and knowledge graph. Pattern Recogn Lett (PRL) 143:43–49

    Article  Google Scholar 

  50. Zhu X, Li L, Liu J, Peng H, Niu X (2018) Captioning transformer with stacked attention modules. Appl Sci 8:5

    Google Scholar 

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China under Grants (61925201, 62132001, U21B2025, 62020106004, and 92048301) and the National Key R&D Program of China (2018YFB1305200).

Author information

Authors and Affiliations

  1. The Engineering Research Center of Learning-Based Intelligent System and The Key Laboratory of Computer Vision and System, Ministry of Education, Tianjin University of Technology, Tianjin, 300384, China

    Xin Jia & Shengyong Chen

  2. The Wangxuan Institute of Computer Technology, Peking University, Beijing, 100871, China

    Yunbo Wang & Yuxin Peng

Authors
  1. Xin Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yunbo Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuxin Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shengyong Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shengyong Chen.

Ethics declarations

Conflict of Interests

The authors declare that they have no conflict of interest.

Additional information

Human participants or animals

This article does not contain any studies with human participants or animals performed by any of the authors.

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jia, X., Wang, Y., Peng, Y. et al. Semantic association enhancement transformer with relative position for image captioning. Multimed Tools Appl 81, 21349–21367 (2022). https://doi.org/10.1007/s11042-022-12776-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12776-5

Keywords