Cross-modal multi-relationship aware reasoning for image-text matching | Multimedia Tools and Applications Skip to main content
Springer Nature Link
Log in

Cross-modal multi-relationship aware reasoning for image-text matching

  • 1177: Advances in Deep Learning for Multimodal Fusion and Alignment
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Cross-modal image-text matching has attracted considerable interest in both computer vision and natural language processing communities. The main issue of image-text matching is to learn the compact cross-modal representations and the correlation between image and text representations. However, the image-text matching task has two major challenges. First, the current image representation methods focus on the semantic information and disregard the spatial position relations between image regions. Second, most existing methods pay little attention to improving textual representation which plays a significant role in image-text matching. To address these issues, we designed a decipherable cross-modal multi-relationship aware reasoning network (CMRN) for image-text matching. In particular, a new method is proposed to extract multi-relationship and to learn the correlations between image regions, including two kinds of visual relations: the geometric position relation and semantic interaction. In addition, images are processed as graphs, and a novel spatial relation encoder is introduced to perform reasoning on the graphs by employing a graph convolutional network (GCN) with attention mechanism. Thereafter, a contextual text encoder based on Bidirectional Encoder Representations from Transformers is adopted to learn distinctive textual representations. To verify the effectiveness of the proposed model, extensive experiments were conducted on two public datasets, namely MSCOCO and Flickr30K. The experimental results show that CMRN achieved superior performance when compared with state-of-the-art methods. On Flickr30K, the proposed method outperforms state-of-the-art methods more than 7.4% in text retrieval from image query, and 5.0% relatively in image retrieval with text query (based on Recall@1). On MSCOCO, the performance reaches 73.9% for text retrieval and 60.4% for image retrieval (based on Recall@1).

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
¥17,985 /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 includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. Available at https://storage.googleapis.com/bert_models/2018_10_18/cased_L-12_H-768_A-12.zip

References

  1. 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, pp 6077–6086, 06

  2. Arqub O A, Abo-Hammour ZS (2014) Numerical solution of systems of second-order boundary value problems using continuous genetic algorithm. Inf Sci 279:396–415

    Article  MathSciNet  Google Scholar 

  3. Chen J, Zhuge H (2019) Extractive summarization of documents with images based on multi-modal rnn. Future Gener Comput Syst 99:04

    Google Scholar 

  4. Chung J, Gülçehre Ç, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv:1412.3555

  5. Cornia M, Baraldi L, Tavakoli H R, Cucchiara R (2020) A unified cycle-consistent neural model for text and image retrieval. Multimed Tools Appl 1–25, 07

  6. Devlin J, Chang M-W, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, vol 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, pp 4171–4186

  7. Faghri F, Fleet DJ, Kiros JR, Fidler S (2018) Vse++: improving visual-semantic embeddings with hard negatives. In: BMVC

  8. Frome A, Corrado G S, Shlens J, Bengio S, Dean J, Ranzato M, Mikolov T (2013) Devise: a deep visual-semantic embedding model. In: NIPS, pp 2121–2129

  9. Gu J, Cai J, Joty S, Niu L, Wang G (2018) Look, imagine and match: improving textual-visual cross-modal retrieval with generative models. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 7181–7189

  10. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778

  11. Hou J, Wu X, Qi Y, Zhao W, Luo J, Jia Y (2019) Relational reasoning using prior knowledge for visual captioning. Computer Vision and Pattern Recognition. arXiv:1906.01290

  12. Huang Y, Wang W, Wang L (2017) Instance-aware image and sentence matching with selective multimodal lstm. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 7254–7262

  13. Huang Y, Wu Q, Song C, Wang L (2018) Learning semantic concepts and order for image and sentence matching, pp 6163–6171, 06

  14. Huang F, Zhang X, Zhao Z, Li Z (2019) Bi-directional spatial-semantic attention networks for image-text matching. IEEE Trans Image Process 28:2008–2020

    Article  MathSciNet  Google Scholar 

  15. Karpathy A, Feifei L (2015) Deep visual-semantic alignments for generating image descriptions. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 3128–3137

  16. Kingma D, Adam J B A (2014) A method for stochastic optimization. In: International conference on learning representations, p 12

  17. Kipf T, Welling M (2017) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907

  18. Klein B, Lev G, Sadeh G, Wolf L (2015) Associating neural word embeddings with deep image representations using fisher vectors. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 4437–4446, 06

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

    Article  MathSciNet  Google Scholar 

  20. Lee K, Chen X, Hua G, Hu H, He X (2018) Stacked cross attention for image-text matching. In: ECCV. Springer, Cham, pp 212–228

  21. Li Y, Tarlow D, Brockschmidt M, Zemel R S (2015) Gated graph sequence neural networks. CoRR, arXiv:1511.05493

  22. Li S, Xiao T, Li H, Yang W, Wang X (2017) Identity-aware textual-visual matching with latent co-attention. In: 2017 IEEE international conference on computer vision (ICCV), pp 1908–1917

  23. Li K, Zhang Y, Li K, Li Y, Fu Y (2019) Visual semantic reasoning for image-text matching. In: 2019 IEEE/CVF International conference on computer vision (ICCV), pp 4653–4661

  24. Li L, Gan Z, Cheng Y, Liu J (2019) Relation-aware graph attention network for visual question answering. In: 2019 IEEE/CVF international conference on computer vision (ICCV), pp 10313–10322

  25. Lin X, Parikh D (2016) Leveraging visual question answering for image-caption ranking 9906:261–277, 10

  26. Lin T -Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick C (2014) Microsoft coco: common objects in context, 8693, 04

  27. Liu Y, Guo Y, Liu L, Bakker E M, Lew M S (2019) Cyclematch: a cycle-consistent embedding network for image-text matching. Pattern Recognit 93:365–379, 05

    Article  Google Scholar 

  28. Liu C, Mao Z, Liu A -A, Zhang T, Wang B, Zhang Y (2019) Focus your attention: a bidirectional focal attention network for image-text matching. In: Proceedings of the 27th ACM international conference on multimedia, MM ’19. Association for Computing Machinery, New York, pp 3–11

  29. Liu C, Mao Z, Zhang T, Xie H, Wang B, Zhang Y (2020) Graph structured network for image-text matching. arXiv:2004.00277

  30. Lu J, Batra D, Parikh D, Lee S (2019) Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in neural information processing systems, pp 13–23

  31. Ma L, Lu Z, Shang L, Li H (2015) Multimodal convolutional neural networks for matching image and sentence. In: 2015 IEEE international conference on computer vision (ICCV), pp 2623–2631

  32. Ma L, Jiang W, Jie Z, Wang X (2019) Bidirectional image-sentence retrieval by local and global deep matching. Neurocomputing 345:36–44, 02

    Article  Google Scholar 

  33. Messina N, Falchi F, Esuli A, Amato G (2020) Transformer reasoning network for image-text matching and retrieval. arXiv:2004.09144

  34. Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv:1301.3781

  35. Nam H, Ha J, Kim J (2017) Dual attention networks for multimodal reasoning and matching. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 2156–2164

  36. Norcliffebrown W, Vafeias S, Parisot S (2018) Learning conditioned graph structures for interpretable visual question answering. In: NeurIPS, pp 8334–8343

  37. Paszke A, Gross S, Chintala S, Chanan G, Yang E, Devito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in pytorch

  38. Qi D, Su L, Song J, Cui E, Bharti T, Sacheti A (2020) Imagebert: cross-modal pre-training with large-scale weak-supervised image-text data. Comput Vis Pattern Recognit. arXiv:2001.07966

  39. Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137–1149, 06

    Article  Google Scholar 

  40. Scarselli F, Gori M, Tsoi A C, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Netw 20(1):61–80

    Article  Google Scholar 

  41. Trott A, Xiong C, Socher R (2018) Interpretable counting for visual question answering. arXiv:1712.08697

  42. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: NIPS

  43. Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. arXiv:1710.10903

  44. Venugopalan S, Rohrbach M, Donahue J, Mooney R J, Darrell T, Saenko K (2015) Sequence to sequence—video to text. In: 2015 IEEE international conference on computer vision (ICCV), pp 4534–4542

  45. Wang L, Li Y, Lazebnik S (2016) Learning deep structure-preserving image-text embeddings. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 5005–5013, 06

  46. Wang Y, Yang H, Qian X, Ma L, Lu J, Li B, Fan X (2019) Position focused attention network for image-text matching. Computation and Language. arXiv:1907.09748

  47. Wang L, Li Y, Huang J, Lazebnik S (2019) Learning two-branch neural networks for image-text matching tasks. IEEE Trans Pattern Anal Mach Intell 41(2):394–407

    Article  Google Scholar 

  48. Wang T, Xu X, Yang Y, Hanjalic A, Shen H, Song J (2019) Matching images and text with multi-modal tensor fusion and re-ranking. In: Proceedings of the 27th ACM international conference on multimedia, pp 12–20, 10

  49. Wang P, Wu Q, Cao J, Shen C, Gao L, Van Den Hengel A (2019) Neighbourhood watch: referring expression comprehension via language-guided graph attention networks. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 1960–1968

  50. Wei Y, Zhao Y, Lu C, Wei S, Liu L, Zhu Z, Yan S (2017) Cross-modal retrieval with cnn visual features: a new baseline. IEEE Trans Syst Man Cybern 47(2):449–460

    Google Scholar 

  51. Xu X, Wang T, Yang Y, Zuo L, Shen F, Shen H T (2020) Cross-modal attention with semantic consistence for image-text matching. IEEE Trans Neural Netw Learn Syst 02:1–14

    Google Scholar 

  52. Yang Z, Qin Z, Yu J, Hu Y (2018) Scene graph reasoning with prior visual relationship for visual question answering. arXiv: Multimedia

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

  54. Young P, Lai A, Hodosh M, Hockenmaier J (2014) From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist 2(1):67–78

    Article  Google Scholar 

  55. Zhang Y, Lu H (2018) Deep cross-modal projection learning for image-text matching. In: The European conference on computer vision (ECCV), pp 707–723

  56. Zhang Y, Hare J S, Prugelbennett A (2018) Learning to count objects in natural images for visual question answering. arXiv:1802.05766

  57. Zheng Z, Zheng L, Garrett M, Yang Y, Xu M, Shen Y -D (2020) Dual-path convolutional image-text embeddings with instance loss. ACM Trans Multimed Comput Commun Appl 16(2): 1–23

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China under Grant 61871278, the Industrial Cluster Collaborative Innovation Project of Chengdu (no. 2016-XT00-00015-GX), the Sichuan Science and Technology Program (no. 2018HH0143).

Author information

Authors and Affiliations

  1. College of Electronics and Information Engineering, Sichuan University, Chengdu, Sichuan, 610064, China

    Jin Zhang, Xiaohai He, Linbo Qing, Luping Liu & Xiaodong Luo

Authors
  1. Jin Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Xiaohai He
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Linbo Qing
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Luping Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Xiaodong Luo
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Xiaohai He.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

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

Zhang, J., He, X., Qing, L. et al. Cross-modal multi-relationship aware reasoning for image-text matching. Multimed Tools Appl 81, 12005–12027 (2022). https://doi.org/10.1007/s11042-020-10466-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-10466-8

Keywords