Vision-based Human Action Recognition on Pre-trained AlexNet

Zamri, NorulNarijah Mohamed; Ling, Goh Fan; Pang, Ying Han; Yin, Ooi Shih

doi:10.1109/iccsce47578.2019.9068586

Cited by 10 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CNN is tested using UCF101 and HMDB51 datasets with accuracies of 94.5% and 69.8%, respectively. Mohamed et al [36] also proposed a vision-based human action recognition via transfer learning. Their approach uses AlexNet as a pre-trained CNN to extract low-level features from three different image maps, i.e., motion history image that sustains spatiotemporal data, binary motion energy image that captures the motion region data, and optical flow information that holds accumulative motion speed data.…”

Section: B Fusion Methodsmentioning

confidence: 99%

Transfer Learning Models for CNN Fusion With Fisher Vector for Codebook Optimization of Foreground Features

Kamaleldin,

Abu-Bakar,

Sheikh

2024

IEEE Access

View full text Add to dashboard Cite

Human action recognition has become one of the main topics in the computer vision field due to its high demand and competitiveness in real-world applications. The main goals of human action recognition are to improve classification accuracy and reduce computational complexity. Previous studies have mainly used two approaches: the handcrafted feature extraction approach and the deep learning approach. The hand-crafted approach is simple, which confers it with an added advantage in terms of computational complexity. However, this method is low in accuracy. Conversely, the deep learning approach achieves high accuracy even for complex datasets, but it suffers in terms of computational complexity and long training time as it needs to process huge datasets during training. Other approaches include the use of pre-trained deep learning networks to fuse both methods. In this paper, we will introduce a combination of pre-trained convolutional neural networks (CNN) to extract features, an improved Fisher vector (iFV) codebook, and an optimized support vector machine SVM to achieve improved human action recognition. We leveraged three pre-trained CNNs, namely, Inception-ResNet-v2, NASNet-Large, and Xception, to extract the features. Then, we applied the improved Fisher vector codebook to encode them. We subsequently trained the codebook using SVM for classification and re-adjusted the SVM weights using five different optimization techniques, which are SGD, Adagrad, ADAM, Adamax, and Nadam. To evaluate the performance, we utilized UCF101 and HMDB51 datasets. The results demonstrate that the accuracy and computational complexity of our approach are comparable to state-of-the-art techniques.

show abstract

Section: B Fusion Methodsmentioning

confidence: 99%

Transfer Learning Models for CNN Fusion With Fisher Vector for Codebook Optimization of Foreground Features

Kamaleldin,

Abu-Bakar,

Sheikh

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In order to maintain the consistency of the feature map size before the feature map fusion, we down-sample the output feature maps of Block1 to Block4. In network training, migration learning can reduce the time of network training [25], so the weight of the vgg16 pre-trained model on ImageNet is used when initializing the convolutional layer in the multi-layer fusion module [26].…”

Section: ) Multi-layer Fusion Modulementioning

confidence: 99%

Railway Insulator Detection Based on Adaptive Cascaded Convolutional Neural Network

et al. 2021

View full text Add to dashboard Cite

Insulator failure is one of the important causes of railway power transmission accidents. In the automatic detection system of railway insulators, the detection and classification of insulator faults is a challenging task due to the complex background, small insulators and unobvious failures. In this article, we propose a railway insulator fault detection network based on convolutional neural network, which can detect faulty insulators from images with high resolution and complex background. The insulator fault detection network realizes the position detection and fault classification of the insulator by cascading the detection network and the fault classification network. The method of cascading two networks can reduce the amount of network calculations and improve the accuracy of fault classification. The insulator detection network uses low-resolution images for position detection, and this method can prevent the detection network from paying too much attention to the details of the image, thereby reducing the amount of network calculations. The fault classification network uses high-resolution insulator images for fault classification. The high-resolution images in this method have rich detailed information, which helps to improve the accuracy of fault classification. The trained insulator detection network and the fault classification network are cascaded to form an insulator fault detection network. The precision, recall and mAP values of the insulator fault detection network are 94.10%, 92.88% and 93.46% respectively. Experiment shows show that this network cascading method can significantly improve the accuracy and robustness of insulator fault detection.

show abstract

“…We proposed using AlexNet [3], ResNet18 [4] and SqueezeNet1_0 [5] deep learning models to classify and evaluate the accuracy of dances to its class. Several works have been done to classify human movements such as proposed by Yildirim and Çinar [6], Kumar and Harikiran [7] and Zamri et al [8] that uses deep learning models. However, those works are similar in method whereby the authors utilized singular images of ISSN: 2252-8938  a human performing an action to train their deep learning models.…”

Section: Introductionmentioning

confidence: 99%

Classification of dances using AlexNet, ResNet18 and SqueezeNet1_0

Zakry

Hipiny

Ujir

2023

IJ-AI

View full text Add to dashboard Cite

Dancing is an art form of creative expression that is based on movement. Dancing comprises varying styles, pacing and composition to convey an artist’s expression. Thus, the classification of any dance to a certain genre or type depends on how accurate or similar it is to what is generally understood to be the specific movements of that dance type. This presents a problem for new dancers to assess if the dance movements that they have just learned is accurate or not to what the original dance type is. This paper proposed that deep learning models can classify dance videos of amateur dancers according to the similar movements of actions of several dance classes. For this study, AlexNet, ResNet and SqueezeNet models was used to perform training on multiple frames of actions of several dance videos for label prediction and the classification accuracy of the models during each training epoch is compared. This study observed that the average classification accuracy of the deep learning models is 94.9669% and is comparable to other approaches used for dance classifications.

show abstract

Vision-based Human Action Recognition on Pre-trained AlexNet

Cited by 10 publications

References 14 publications

Transfer Learning Models for CNN Fusion With Fisher Vector for Codebook Optimization of Foreground Features

Transfer Learning Models for CNN Fusion With Fisher Vector for Codebook Optimization of Foreground Features

Railway Insulator Detection Based on Adaptive Cascaded Convolutional Neural Network

Classification of dances using AlexNet, ResNet18 and SqueezeNet1_0

Contact Info

Product

Resources

About