Article

Multi-Layer Cross Loss Model for Zero-Shot Human Activity Recognition

Authors:

Zhanghu ZhechenAuthors Info & Claims

Advances in Knowledge Discovery and Data Mining: 24th Pacific-Asia Conference, PAKDD 2020, Singapore, May 11–14, 2020, Proceedings, Part I

Pages 210 - 221

https://doi.org/10.1007/978-3-030-47426-3_17

Published: 11 May 2020 Publication History

Abstract

Most existing methods of human activity recognition are based on supervised learning. These methods can only recognize classes which appear in the training dataset, but are out of work when the classes are not in the training dataset. Zero-shot learning aims at solving this problem. In this paper, we propose a novel model termed Multi-Layer Cross Loss Model (MLCLM). Our model has two novel ideas: (1) In the model, we design a multi-nonlinear layers model to project features to semantic space for that the deeper the network is, the better the network can fit the data’s distribution. (2) A novel objective function combining mean square loss and cross entropy loss is designed for the zero-shot learning task. We have conduct sufficient experiments to evaluate the proposed model on three benchmark datasets. Experiments show that our model outperforms other state-of-the-art methods significantly in zero-shot human activity recognition.

References

[1]

Khojasteh S, Villar J, Chira C, González V, and de la Cal E Improving fall detection using an on-wrist wearable accelerometer Sensors 2018 18 5 1350

[2]

Direkoǧlu C and O’Connor NE Temporal segmentation and recognition of team activities in sports Mach. Vis. Appl. 2018 29 5 891-913

[3]

Inoue M, Inoue S, and Nishida T Deep recurrent neural network for mobile human activity recognition with high throughput Artif. Life Rob. 2017 23 2 173-185

[4]

Cao L, Wang Y, Zhang B, Jin Q, and Vasilakos AV GCHAR: an efficient group-based context-aware human activity recognition on smartphone J. Parallel Distrib. Comput. 2018 118 67-80

[5]

Asghari, P., Soelimani, E., Nazerfard, E.: Online human activity recognition employing hierarchical hidden markov models. arXiv preprint arXiv:1903.04820 (2019)

[6]

Palatucci, M., Pomerleau, D., Hinton, G.E., Mitchell, T.M.: Zero-shot learning with semantic output codes. In: Advances in neural information processing systems, pp. 1410–1418 (2009)

[7]

Cheng, H.T., Sun, F.T., Griss, M., Davis, P., Li, J., You, D.: Nuactiv: recognizing unseen new activities using semantic attribute-based learning. In: Proceeding of the 11th annual international conference on Mobile systems, applications, and services, pp. 361–374. ACM (2013)

[8]

Zheng, V.W., Hu, D.H., Yang, Q.: Cross-domain activity recognition. In: Proceedings of the 11th international conference on Ubiquitous computing, pp. 61–70. ACM (2009)

[9]

Cao, H., Nguyen, M.N., Phua, C., Krishnaswamy, S., Li, X.: An integrated framework for human activity classification. In: UbiComp, pp. 331–340 (2012)

[10]

Wang JS, Lin CW, Yang YTC, and Ho YJ Walking pattern classification and walking distance estimation algorithms using gait phase information IEEE Trans. Biomed. Eng. 2012 59 10 2884-2892

[11]

Shi, D., Wu, Y., Mo, X., Wang, R., Wei, J.: Activity recognition based on the dynamic coordinate transformation of inertial sensor data. In: 2016 Intl IEEE Conferences on Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People, and Smart World Congress (UIC/ATC/ScalCom/CBDCom/IoP/SmartWorld), pp. 1–8. IEEE (2016)

[12]

Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3174–3183 (2017)

[13]

Romera-Paredes, B., Torr, P.: An embarrassingly simple approach to zero-shot learning. In: International Conference on Machine Learning, pp. 2152–2161 (2015)

[14]

Liu, S., Long, M., Wang, J., Jordan., M.I.: Generalized zero-shot learning with deep calibration network. In: Advances in Neural Information Processing Systems, pp. 2005–2015 (2018)

[15]

Wang, W., Miao, C., Hao, S.: Zero-shot human activity recognition via nonlinear compatibility based method. In: Proceedings of the International Conference on Web Intelligence, pp. 322–330. ACM (2017)

[16]

Rohrbach, M., Ebert, S., Schiele, B.: Transfer learning in a transductive setting. In: Advances in neural information processing systems, pp. 46–54 (2013)

[17]

Kodirov, E., Xiang, T., Fu, Z., Gong, S.: Unsupervised domain adaptation for zero-shot learning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2452–2460 (2015)

[18]

Fu, Y., Sigal, L.: Semi-supervised vocabulary-informed learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5337–5346 (2016)

[19]

Cheng, H.T., Griss, M., Davis, P., Li, J., You, D.: Towards zero-shot learning for human activity recognition using semantic attribute sequence model. In: Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 355–358. ACM (2013)

[20]

Huynh T, Fritz M, and Schiele B Discovery of activity patterns using topic models UbiComp 2008 8 10-19

[21]

Reiss, A., Stricker, D.: Introducing a new benchmarked dataset for activity monitoring. In: 2012 16th International Symposium on Wearable Computers, pp. 108–109. IEEE (2012)

[22]

Roggen, D., et al.: Collecting complex activity datasets in highly rich networked sensor environments. In: 2010 Seventh international conference on networked sensing systems (INSS), pp. 233–240. IEEE (2010)

[23]

Hammerla, N.Y., Halloran, S., Plötz, T.: Deep, convolutional, and recurrent models for human activity recognition using wearables. arXiv preprint arXiv:1604.08880 (2016)

[24]

Xian Y, Lampert CH, Schiele B, and Akata Z Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly IEEE Trans. Pattern Anal. Mach. Intell. 2018 41 2251-2265

[25]

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

[26]

Lampert CH, Nickisch H, and Harmeling S Attribute-based classification for zero-shot visual object categorization IEEE Trans. Pattern Anal. Mach. Intell. 2013 36 3 453-465

Cited By

Xia KLi WGan SLu S(2024)TS2ACTProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36314457:4(1-22)Online publication date: 12-Jan-2024
https://dl.acm.org/doi/10.1145/3631445
Zhang XChowdhury RZhang JHong DGupta RShang JFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Unleashing the Power of Shared Label Structures for Human Activity RecognitionProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615101(3340-3350)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3615101
Wang WLi Q(2023)Generalized Zero-Shot Activity Recognition with Embedding-Based MethodACM Transactions on Sensor Networks10.1145/358269019:3(1-25)Online publication date: 5-Apr-2023
https://dl.acm.org/doi/10.1145/3582690
Show More Cited By

Index Terms

Multi-Layer Cross Loss Model for Zero-Shot Human Activity Recognition
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches
      1. Neural networks

Index terms have been assigned to the content through auto-classification.

Recommendations

Zero-Shot Learning for IMU-Based Activity Recognition Using Video Embeddings

The Activity Recognition Chain generally precludes the challenging scenario of recognizing new activities that were unseen during training, despite this scenario being a practical and common one as users perform diverse activities at test time. A few ...
Towards zero-shot learning for human activity recognition using semantic attribute sequence model
UbiComp '13: Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing

Understanding human activities is important for user-centric and context-aware applications. Previous studies showed promising results using various machine learning algorithms. However, most existing methods can only recognize the activities that were ...
Few-Shot Human Activity Recognition on Noisy Wearable Sensor Data
Database Systems for Advanced Applications
Abstract
Most existing wearable sensor-based human activity recognition (HAR) models are trained on substantial labeled data. It is difficult for HAR to learn new-class activities unseen during training from a few samples. Very few researches of few-shot ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

Advances in Knowledge Discovery and Data Mining: 24th Pacific-Asia Conference, PAKDD 2020, Singapore, May 11–14, 2020, Proceedings, Part I

May 2020

905 pages

ISBN:978-3-030-47425-6

DOI:10.1007/978-3-030-47426-3

Editors:
Hady W. Lauw
School of Information Systems, Singapore Management University, Singapore, Singapore
,
Raymond Chi-Wing Wong
Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong
,
Alexandros Ntoulas
Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece
,
Ee-Peng Lim
School of Information Systems, Singapore Management University, Singapore, Singapore
,
See-Kiong Ng
Institute of Data Science, National University of Singapore, Singapore, Singapore
,
Sinno Jialin Pan
School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore

© Springer Nature Switzerland AG 2020.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 11 May 2020

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 07 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Xia KLi WGan SLu S(2024)TS2ACTProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36314457:4(1-22)Online publication date: 12-Jan-2024
https://dl.acm.org/doi/10.1145/3631445
Zhang XChowdhury RZhang JHong DGupta RShang JFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Unleashing the Power of Shared Label Structures for Human Activity RecognitionProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615101(3340-3350)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3615101
Wang WLi Q(2023)Generalized Zero-Shot Activity Recognition with Embedding-Based MethodACM Transactions on Sensor Networks10.1145/358269019:3(1-25)Online publication date: 5-Apr-2023
https://dl.acm.org/doi/10.1145/3582690
Xefteris VTsanousa AMavropoulos TMeditskos GVrochidis SKompatsiaris I(2022)Human Activity Recognition with IMU and Vital Signs Feature FusionMultiMedia Modeling10.1007/978-3-030-98358-1_23(287-298)Online publication date: 6-Jun-2022
https://dl.acm.org/doi/10.1007/978-3-030-98358-1_23

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents