Abstract
We propose DeepGRU, a novel end-to-end deep network model informed by recent developments in deep learning for gesture and action recognition, that is streamlined and device-agnostic. DeepGRU, which uses only raw skeleton, pose or vector data is quickly understood, implemented, and trained, and yet achieves state-of-the-art results on challenging datasets. At the heart of our method lies a set of stacked gated recurrent units (GRU), two fully-connected layers and a novel global attention model. We evaluate our method on seven publicly available datasets, containing various number of samples and spanning over a broad range of interactions (full-body, multi-actor, hand gestures, etc.). In all but one case we outperform the state-of-the-art pose-based methods. For instance, we achieve a recognition accuracy of 84.9% and 92.3% on cross-subject and cross-view tests of the NTU RGB+D dataset respectively, and also 100% recognition accuracy on the UT-Kinect dataset. We show that even in the absence of powerful hardware, or a large amount of training data, and with as little as four samples per class, DeepGRU can be trained in under 10 min while beating traditional methods specifically designed for small training sets, making it an enticing choice for rapid application prototyping and development.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Change history
21 October 2019
The given name and family name of an author were not tagged correctly in the originally published article. The author’s given name is “Joseph J.” and his family name is “LaViola.” This was corrected.
Notes
- 1.
Reference implementation is available at: https://github.com/Maghoumi/DeepGRU.
- 2.
A factor of ±0.3 indicates that samples are randomly and non-uniformly (e.g. ) scaled along all axes to [0.7, 1.3] of their original size.
- 3.
Refer to our supplementary material for more details: https://arxiv.org/abs/1810.12514.
References
Anirudh, R., Turaga, P., Su, J., Srivastava, A.: Elastic functional coding of human actions: from vector-fields to latent variables. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3147–3155 (2015)
Avola, D., Bernardi, M., Cinque, L., Foresti, G.L., Massaroni, C.: Exploiting recurrent neural networks and leap motion controller for the recognition of sign language and semaphoric hand gestures. IEEE Trans. Multimed. 21, 234–245 (2018)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of ICLR (2015)
Baradel, F., Wolf, C., Mille, J.: Human action recognition: pose-based attention draws focus to hands. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 604–613 (2017)
Baradel, F., Wolf, C., Mille, J., Taylor, G.W.: Glimpse clouds: human activity recognition from unstructured feature points. In: The IEEE Conference on Computer Vision and Pattern Recognition (2018)
Boiman, O., Shechtman, E., Irani, M.: In defense of nearest-neighbor based image classification. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2008)
Boulahia, S.Y., Anquetil, E., Multon, F., Kulpa, R.: Dynamic hand gesture recognition based on 3D pattern assembled trajectories. In: 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 1–6 (2017)
Caputo, F.M., et al.: Online gesture recognition. In: Eurographics Workshop on 3D Object Retrieval (2019)
Cheema, S., Hoffman, M., LaViola, J.J.: 3D gesture classification with linear acceleration and angular velocity sensing devices for video games. Entertain. Comput. 4(1), 11–24 (2013)
Chen, X., Guo, H., Wang, G., Zhang, L.: Motion feature augmented recurrent neural network for skeleton-based dynamic hand gesture recognition. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 2881–2885 (2017)
Cherian, A., Sra, S., Gould, S., Hartley, R.: Non-linear temporal subspace representations for activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2197–2206 (2018)
Cho, K., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734 (2014)
De Smedt, Q., Wannous, H., Vandeborre, J.P.: Skeleton-based dynamic hand gesture recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1–9 (2016)
De Smedt, Q., Wannous, H., Vandeborre, J.-P.: 3D hand gesture recognition by analysing set-of-joints trajectories. In: Wannous, H., Pala, P., Daoudi, M., Flórez-Revuelta, F. (eds.) UHA3DS 2016. LNCS, vol. 10188, pp. 86–97. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91863-1_7
De Smedt, Q., Wannous, H., Vandeborre, J.P., Guerry, J., Le Saux, B., Filliat, D.: Shrec’17 track: 3D hand gesture recognition using a depth and skeletal dataset. In: 10th Eurographics Workshop on 3D Object Retrieval (2017)
Devineau, G., Moutarde, F., Xi, W., Yang, J.: Deep learning for hand gesture recognition on skeletal data. In: 2018 13th IEEE International Conference on Automatic Face Gesture Recognition (FG 2018), pp. 106–113 (2018)
Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110–1118 (2015)
Fernández-Ramírez, J., Álvarez-Meza, A., Orozco-Gutiérrez, Á.: Video-based human action recognition using kernel relevance analysis. In: Bebis, G., et al. (eds.) ISVC 2018. LNCS, vol. 11241, pp. 116–125. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03801-4_11
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Hu, J., Zheng, W., Lai, J., Zhang, J.: Jointly learning heterogeneous features for rgb-d activity recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2186–2200 (2017)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift, pp. 448–456 (2015)
Ke, Q., An, S., Bennamoun, M., Sohel, F., Boussaid, F.: Skeletonnet: mining deep part features for 3-D action recognition. IEEE Signal Process. Lett. 24(6), 731–735 (2017)
Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: A new representation of skeleton sequences for 3D action recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 4570–4579. IEEE (2017)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kratz, S., Rohs, M.: The \$3 recognizer: Simple 3D gesture recognition on mobile devices. In: Proceedings of the 15th International Conference on Intelligent User Interfaces (2010)
Kratz, S., Rohs, M.: Protractor3D: a closed-form solution to rotation-invariant 3D gestures. In: Proceedings of the 16th International Conference on Intelligent User Interfaces (2011)
Liu, J., Wang, G., Duan, L., Abdiyeva, K., Kot, A.C.: Skeleton-based human action recognition with global context-aware attention lstm networks. IEEE Trans. Image Process. 27(4), 1586–1599 (2018)
Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816–833. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_50
Liu, M., Liu, H., Chen, C.: Enhanced skeleton visualization for view invariant human action recognition. Pattern Recogn. 68(C), 346–362 (2017)
Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (2015)
Luvizon, D.C., Picard, D., Tabia, H.: 2D/3D pose estimation and action recognition using multitask deep learning. In: The IEEE Conference on Computer Vision and Pattern Recognition, vol. 2 (2018)
Núñez, J.C., Cabido, R., Pantrigo, J.J., Montemayor, A.S., Vélez, J.F.: Convolutional neural networks and long short-term memory for skeleton-based human activity and hand gesture recognition. Pattern Recogn. 76(C), 80–94 (2018)
Ohn-Bar, E., Trivedi, M.M.: Joint angles similarities and HOG2 for action recognition. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (2013)
Paszke, A., et al.: Automatic differentiation in pytorch. In: NIPS-W (2017)
Pittman, C.R., LaViola Jr., J.J.: Multiwave: complex hand gesture recognition using the doppler effect. In: Proceedings of the 43rd Graphics Interface Conference. pp. 97–106 (2017)
Shahroudy, A., Ng, T., Gong, Y., Wang, G.: Deep multimodal feature analysis for action recognition in RGB+D videos. IEEE Trans. Pattern Anal. Mach. Intell. 40(5), 1045–1058 (2018)
Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTURGB+D: a large scale dataset for 3D human activity analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)
Smedt, Q.D., Wannous, H., Vandeborre, J.: Skeleton-based dynamic hand gesture recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1206–1214 (2016)
Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. AAAI. 1, 4263–4270 (2017)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)
Tang, Y., Tian, Y., Lu, J., Li, P., Zhou, J.: Deep progressive reinforcement learning for skeleton-based action recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (2018)
Taranta, II, E.M., LaViola Jr., J.J.: Penny pincher: a blazing fast, highly accurate \$-family recognizer. In: Proceedings of the 41st Graphics Interface Conference, pp. 195–202 (2015)
Taranta II, E.M., Maghoumi, M., Pittman, C.R., LaViola Jr., J.J.: A rapid prototyping approach to synthetic data generation for improved 2D gesture recognition. In: Proceedings of the 29th Symposium on User Interface Software and Technology, pp. 873–885. ACM (2016)
Taranta II, E.M., Samiei, A., Maghoumi, M., Khaloo, P., Pittman, C.R., LaViola Jr., J.J.: Jackknife: a reliable recognizer with few samples and many modalities. In: Proceedings of the 2017 Conference on Human Factors in Computing Systems, pp. 5850–5861 (2017)
Tas, Y., Koniusz, P.: CNN-based action recognition and supervised domain adaptation on 3D body skeletons via kernel feature maps. In: BMVC (2018)
Tewari, A., Taetz, B., Grandidier, F., Stricker, D.: Two phase classification for early hand gesture recognition in 3D top view data. In: Bebis, G., et al. (eds.) ISVC 2016. LNCS, vol. 10072, pp. 353–363. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50835-1_33
Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 588–595 (2014)
Vrigkas, M., Mastora, E., Nikou, C., Kakadiaris, I.A.: Robust incremental hidden conditional random fields for human action recognition. In: Bebis, G., et al. (eds.) ISVC 2018. LNCS, vol. 11241, pp. 126–136. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03801-4_12
Weng, J., Weng, C., Yuan, J.: Spatio-temporal naive-bayes nearest-neighbor (ST-NBNN) for skeleton-based action recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 445–454 (2017)
Weng, J., Liu, M., Jiang, X., Yuan, J.: Deformable pose traversal convolution for 3D action and gesture recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 142–157. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_9
Xia, L., Chen, C., Aggarwal, J.: View invariant human action recognition using histograms of 3D joints. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 20–27. IEEE (2012)
Yun, K., Honorio, J., Chattopadhyay, D., Berg, T.L., Samaras, D.: Two-person interaction detection using body-pose features and multiple instance learning. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. IEEE (2012)
Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., Zheng, N.: View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2136–2145 (2017)
Zhu, W., Lan, C., Xing, J., Zeng, W., Li, Y., Shen, L., Xie, X.: Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 3697–3703 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Maghoumi, M., LaViola, J.J. (2019). DeepGRU: Deep Gesture Recognition Utility. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2019. Lecture Notes in Computer Science(), vol 11844. Springer, Cham. https://doi.org/10.1007/978-3-030-33720-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-33720-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33719-3
Online ISBN: 978-3-030-33720-9
eBook Packages: Computer ScienceComputer Science (R0)