An action recognition method based on neural architecture search

Kangyong Yin; Zhechen Huang; Suo Qiu; Zhi Wang; Fengbo Tao; Wei Liang; Haosheng Huang

doi:10.1117/12.2673723

22 May 2023 An action recognition method based on neural architecture search

Kangyong Yin, Zhechen Huang, Suo Qiu, Zhi Wang, Fengbo Tao, Wei Liang, Haosheng Huang

Proceedings Volume 12640, International Conference on Internet of Things and Machine Learning (IoTML 2022); 126401Q (2023) https://doi.org/10.1117/12.2673723
Event: International Conference on Internet of Things and Machine Learning (IoTML 2022), 2022, Harbin, China

Abstract

Facing complex and diverse action recognition scenarios, artificially designed neural networks show poor generalization performance. Therefore, an automatic designing method of 3D convolutional neural networks based on neural architecture search is proposed. Firstly, a variety of human behaviors are extracted to construct training sets and validation sets. Additionally, the weights of neuron connections are updated using the loss on the training set, the discrete network architecture search space is continuous through continuous relaxation, and the search space is reduced by using the hierarchical idea. What’s more, the objective function is optimized by combining gradient descent, realizing fast search, and stacking the obtained computing units to form an overall network at the same time. Evaluations based on public data sets show that the designed neural network model achieves comparable performance to the artificially designed network model in the task of human action recognition, solving the difficulty of deep learning method migration between working at different scenarios by automatically customizing the network.

Citation Download Citation

Kangyong Yin, Zhechen Huang, Suo Qiu, Zhi Wang, Fengbo Tao, Wei Liang, and Haosheng Huang "An action recognition method based on neural architecture search", Proc. SPIE 12640, International Conference on Internet of Things and Machine Learning (IoTML 2022), 126401Q (22 May 2023); https://doi.org/10.1117/12.2673723

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available