Low-Cost Network Scheduling of 3D-CNN Processing for Embedded Action Recognition

Lee, Hyunhoon; Kim, Young-Seok; Kim, Mi‐Jung; Lee, Young‐Joo

doi:10.1109/access.2021.3087509

Cited by 12 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DNN-based Models: We compare the performance and the model complexities of current state-of-the-art DNN-based models (Carreira and Zisserman, 2017 ; Wang Q. et al, 2019 ; Bi et al, 2020 ; Lee et al, 2021 ; Wang et al, 2021 ) with our proposed HRSNN models.…”

Section: Resultsmentioning

confidence: 99%

“…• DNN-based Models: We compare the performance and the model complexities of current state-of-the-art DNN-based models (Carreira and Zisserman, 2017;Wang Q. et al, 2019;Bi et al, 2020;Lee et al, 2021;Wang et al, 2021) with our proposed HRSNN models. • Backpropagation-based SNN Models: We compare the performance of backpropagation-based SNN models with HoNB and HeNB-based RSNN models.…”

Section: Comparison With Prior Workmentioning

confidence: 99%

See 1 more Smart Citation

Heterogeneous recurrent spiking neural network for spatio-temporal classification

Chakraborty

Mukhopadhyay

2023

Front. Neurosci.

View full text Add to dashboard Cite

Spiking Neural Networks are often touted as brain-inspired learning models for the third wave of Artificial Intelligence. Although recent SNNs trained with supervised backpropagation show classification accuracy comparable to deep networks, the performance of unsupervised learning-based SNNs remains much lower. This paper presents a heterogeneous recurrent spiking neural network (HRSNN) with unsupervised learning for spatio-temporal classification of video activity recognition tasks on RGB (KTH, UCF11, UCF101) and event-based datasets (DVS128 Gesture). We observed an accuracy of 94.32% for the KTH dataset, 79.58% and 77.53% for the UCF11 and UCF101 datasets, respectively, and an accuracy of 96.54% on the event-based DVS Gesture dataset using the novel unsupervised HRSNN model. The key novelty of the HRSNN is that the recurrent layer in HRSNN consists of heterogeneous neurons with varying firing/relaxation dynamics, and they are trained via heterogeneous spike-time-dependent-plasticity (STDP) with varying learning dynamics for each synapse. We show that this novel combination of heterogeneity in architecture and learning method outperforms current homogeneous spiking neural networks. We further show that HRSNN can achieve similar performance to state-of-the-art backpropagation trained supervised SNN, but with less computation (fewer neurons and sparse connection) and less training data.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Comparison With Prior Workmentioning

confidence: 99%

Heterogeneous recurrent spiking neural network for spatio-temporal classification

Chakraborty

Mukhopadhyay

2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Recently, the embedded system has been used to deploy CNN networks to complete real-time recognition and detection tasks, e.g. vehicle plate recognition [ 27 ], fire detection [ 28 ], handwriting recognition [ 29 ] and action recognition [ 30 , 31 ]. Normally, the embedded hardware has limited computation capacity and on-board memory; thus, lightweight CNN architectures are more feasible to be deployed in the embedded environment.…”

Section: Introductionmentioning

confidence: 99%

A new lightweight deep neural network for surface scratch detection

Zhang²,

Wu³

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

This paper aims to develop a lightweight convolutional neural network, WearNet , to realise automatic scratch detection for components in contact sliding such as those in metal forming. To this end, a large surface scratch dataset obtained from cylinder-on-flat sliding tests was used to train the WearNet with appropriate training parameters such as learning rate, gradient algorithm and mini-batch size. A comprehensive investigation on the network response and decision mechanism was also conducted to show the capability of the developed WearNet . It was found that compared with the existing networks, WearNet can realise an excellent classification accuracy of 94.16% with a much smaller model size and faster detection speed. Besides, WearNet outperformed other state-of-the-art networks when a public image database was used for network evaluation. The application of WearNet in an embedded system further demonstrated such advantages in the detection of surface scratches in sheet metal forming processes.

show abstract

“…It uses the joint points of the human body as vertices and the natural connections between the joint points as edges to construct a topology map for the joint data. At the same time, the high-dimensional features of the skeleton data are used to construct the human skeleton data, which is then used to construct the human skeleton data using a graph convolutional neural network [19][20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

An Action Recognition Technology for Badminton Players Using Deep Learning

Liu

Liang

2022

Mobile Information Systems

View full text Add to dashboard Cite

With the fast development of sports in recent years, the number of people participating in various sports has increased day by day. Because of the advantages of fewer constraints on the field and ease of learning, badminton became one of the most popular sports among them. Numerous works have been done specifically for the recognition of action of badminton players to improve and popularize it, but the traditional badminton player’s badminton action recognition algorithm employs the method of manually constructing a topology map to model the action sequence contained in multiple video frames. Besides, it learns each video frame in a targeted manner to reflect data changes, which is prone to high computational cost, low network generalization, and catastrophic forgetting. In response to the above problems, this paper proposes a deep learning-based action recognition technology for badminton players, which re-encodes the human hitting action sequence data with multirelational characteristics into relational triples, and learns by decoupling based on long short-term memory network. At the same time, this paper designs and completes a set of badminton action recognition schemes based on acceleration and angular velocity signals. Experimental results show that the proposed method achieves 63%, 84%, and 92%, respectively, recognition accuracy on multiple benchmark datasets, which improves the accuracy of human hitting action recognition. As a result, the evaluation will be useful in future work to improve the structure of current deep learning models for higher results in badminton action recognition.

show abstract

Low-Cost Network Scheduling of 3D-CNN Processing for Embedded Action Recognition

Cited by 12 publications

References 42 publications

Heterogeneous recurrent spiking neural network for spatio-temporal classification

Heterogeneous recurrent spiking neural network for spatio-temporal classification

A new lightweight deep neural network for surface scratch detection

An Action Recognition Technology for Badminton Players Using Deep Learning

Contact Info

Product

Resources

About