Hybrid and hierarchical fusion networks: a deep cross-modal learning architecture for action recognition

Abstract

Two-stream networks have provided an alternate way of exploiting the spatiotemporal information for action recognition problem. Nevertheless, most of the two-stream variants perform the fusion of homogeneous modalities which cannot efficiently capture the action-motion dynamics from the videos. Moreover, the existing studies cannot extend the streams beyond the number of modalities. To address these limitations, we propose a hybrid and hierarchical fusion (HHF) networks. The hybrid fusion handles non-homogeneous modalities and introduces a cross-modal learning stream for effective modeling of motion dynamics while extending the networks from existing two-stream variants to three and six streams. On the other hand, the hierarchical fusion makes the modalities consistent by modeling long-term temporal information along with the combination of multiple streams to improve the recognition performance. The proposed network architecture comprises of three fusion tiers: the hybrid fusion itself, the long-term fusion pooling layer which models the long-term dynamics from RGB and optical flow modalities, and the adaptive weighting scheme for combining the classification scores from several streams. We show that the hybrid fusion has different representations from the base modalities for training the cross-modal learning stream. We have conducted extensive experiments and shown that the proposed six-stream HHF network outperforms the existing two- and four-stream networks, achieving the state-of-the-art recognition performance, 97.2% and 76.7% accuracies on UCF101 and HMDB51 datasets, respectively, which are widely used in action recognition studies.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3

References

  1. 1.

    Gan C, Lin M, Yang Y et al (2016) Concepts not alone: exploring pairwise relationships for zero-shot video activity recognition. In: AAAI thirteenth conference on artificial intelligence, pp 3487–3493

  2. 2.

    Wang H, Schmid C (2013) Action recognition with improved trajectories. In: 2013 IEEE international conference on computer vision. IEEE, pp 3551–3558

  3. 3.

    Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. In: 15th International conference on multimedia—MULTIMEDIA’07. ACM Press, New York, NY, USA, pp 357–360

  4. 4.

    Bobick AF, Davis JW (2001) The recognition of human movement using temporal templates. IEEE Trans Pattern Anal Mach Intell 23:257–267. https://doi.org/10.1109/34.910878

    Article  Google Scholar 

  5. 5.

    Bilen H, Fernando B, Gavves E et al (2016) Dynamic image networks for action recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 3034–3042

  6. 6.

    Khowaja SA, Lee S-L (2019) Semantic image networks for human action recognition, ArXiv Prepr http://arxiv.org/abs/1901.06792 (2019). (to appear in IJCV)

  7. 7.

    Fernando B, Gavves E, Jose Oramas M et al (2015) Modeling video evolution for action recognition. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 5378–5387

  8. 8.

    Ng JY-H, Hausknecht M, Vijayanarasimhan S et al (2015) Beyond short snippets: deep networks for video classification. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 4694–4702

  9. 9.

    Tran D, Bourdev L, Fergus R et al (2015) Learning spatiotemporal features with 3D convolutional networks. In: 2015 IEEE international conference on computer vision (ICCV). IEEE, pp 4489–4497

  10. 10.

    Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Advances in neural information processing systems, pp 1–9

  11. 11.

    Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 1933–1941

  12. 12.

    Ma C-Y, Chen M-H, Kira Z, AlRegib G (2018) TS-LSTM and temporal-inception: exploiting spatiotemporal dynamics for activity recognition. Signal Process Image Commun. https://doi.org/10.1016/j.image.2018.09.003

    Article  Google Scholar 

  13. 13.

    Wu Z, Wang X, Jiang Y-G et al (2015) Modeling spatial–temporal clues in a hybrid deep learning framework for video classification. In: 23rd ACM international conference on multimedia—MM’15. ACM Press, New York, NY, USA, pp 461–470

  14. 14.

    Wang L, Qiao Y, Tang X (2015) Action recognition with trajectory-pooled deep-convolutional descriptors. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 4305–4314

  15. 15.

    Wang L, Xiong Y, Wang Z et al (2016) Temporal segment networks: towards good practices for deep action recognition. In: European conference on computer vision, pp 20–36

  16. 16.

    Lan Z, Zhu Y, Hauptmann AG, Newsam S (2017) Deep local video feature for action recognition. In: IEEE conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 1219–1225

  17. 17.

    Diba A, Sharma V, Van Gool L (2017) Deep temporal linear encoding networks. In: IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 1541–1550

  18. 18.

    Ji S, Xu W, Yang M, Yu K (2013) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35:221–231. https://doi.org/10.1109/TPAMI.2012.59

    Article  Google Scholar 

  19. 19.

    Wang X, Gao L, Wang P et al (2018) Two-stream 3-D convNet fusion for action recognition in videos with arbitrary size and length. IEEE Trans Multimed 20:634–644. https://doi.org/10.1109/TMM.2017.2749159

    Article  Google Scholar 

  20. 20.

    Bilen H, Fernando B, Gavves E, Vedaldi A (2018) Action recognition with dynamic image networks. IEEE Trans Pattern Anal Mach Intell 40:2799–2813. https://doi.org/10.1109/TPAMI.2017.2769085

    Article  Google Scholar 

  21. 21.

    Zhang G, Liu J, Li H et al (2017) Joint human detection and head pose estimation via multistream networks for RGB-D videos. IEEE Signal Process Lett 24:1666–1670. https://doi.org/10.1109/LSP.2017.2731952

    Article  Google Scholar 

  22. 22.

    Wu Z, Jiang Y-G, Wang X, et al (2016) Multi-stream multi-class fusion of deep networks for video classification. In: ACM on multimedia conference—MM’16. ACM Press, New York, NY, USA, pp 791–800

  23. 23.

    Donahue J, Hendricks LA, Rohrbach M et al (2017) Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans Pattern Anal Mach Intell 39:677–691. https://doi.org/10.1109/TPAMI.2016.2599174

    Article  Google Scholar 

  24. 24.

    Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: Thirty-first association for the advancement of artificial intelligence (AAAI), pp 4278–4284

  25. 25.

    Khowaja SA, Yahya BN, Lee S-L (2017) Hierarchical classification method based on selective learning of slacked hierarchy for activity recognition systems. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2017.06.040

    Article  Google Scholar 

  26. 26.

    Ryoo MS, Rothrock B, Matthies L (2015) Pooled motion features for first-person videos. In: IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 896–904

  27. 27.

    Kwon H, Kim Y, Lee JS, Cho M (2018) First person action recognition via two-stream ConvNet with long-term fusion pooling. Pattern Recognit Lett 112:161–167. https://doi.org/10.1016/j.patrec.2018.07.011

    Article  Google Scholar 

  28. 28.

    Soomro K, Zamir AR, Shah M (2012) UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint. arXiv:1212.0402

  29. 29.

    Kuehne H, Jhuang H, Garrote E et al (2011) HMDB: a large video database for human motion recognition. In: 2011 International conference on computer vision. IEEE, pp 2556–2563

  30. 30.

    Russakovsky O, Deng J, Su H et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115:211–252. https://doi.org/10.1007/s11263-015-0816-y

    MathSciNet  Article  Google Scholar 

  31. 31.

    Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: Proceedings of the 30th international conference on machine learning, pp 1310–1318

  32. 32.

    Varol G, Laptev I, Schmid C (2018) Long-term temporal convolutions for action recognition. IEEE Trans Pattern Anal Mach Intell 40:1510–1517. https://doi.org/10.1109/TPAMI.2017.2712608

    Article  Google Scholar 

  33. 33.

    Sun L, Jia K, Yeung D-Y, Shi BE (2015) Human action recognition using factorized spatio-temporal convolutional networks. In: 2015 IEEE international conference on computer vision (ICCV). IEEE, pp 4597–4605

  34. 34.

    Carreira J, Zisserman A (2017) Quo Vadis, action recognition? A new model and the kinetics dataset. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 4724–4733

  35. 35.

    Wang Y, Long M, Wang J, Yu PS (2017) Spatiotemporal pyramid network for video action recognition. In: IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2097–2106

Download references

Acknowledgements

This research was supported by Hankuk University of Foreign Studies Research Fund (Grant No. 2019-1) and also supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2018R1D1A1B07049113).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Seok-Lyong Lee.

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

Verify currency and authenticity via CrossMark

Cite this article

Khowaja, S.A., Lee, SL. Hybrid and hierarchical fusion networks: a deep cross-modal learning architecture for action recognition. Neural Comput & Applic 32, 10423–10434 (2020). https://doi.org/10.1007/s00521-019-04578-y

Download citation

Keywords

  • Action recognition
  • Deep architectures
  • Inception-ResNets
  • Video representations
  • Non-homogeneous fusion