Semi-CNN Architecture for Effective Spatio-Temporal Learning in Action Recognition

Leong, Mei Chee; Prasad, Dilip K.; Lee, Yong Tsui; Lin, Feng

doi:10.20944/preprints201912.0086.v1

Cited by 7 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by transfer learning, Stroud et al [150] proposed a Distilled 3D Network (D3D), consisting of a student network and a teacher network, where the student network is trained from RGB videos and also distilling knowledge from the teacher network trained from optical flow sequences. Besides, 2D and 3D CNNs are fused for HAR in [158].…”

Section: Deep Learning Methodsmentioning

confidence: 99%

Human Action Recognition from Various Data Modalities: A Review

Rahmani¹,

Bennamoun²,

Ke³

2021

Preprint

View full text Add to dashboard Cite

show abstract

Section: Deep Learning Methodsmentioning

confidence: 99%

Human Action Recognition from Various Data Modalities: A Review

Rahmani¹,

Bennamoun²,

Ke³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…[ 3 ]. Besides, a ResNet18 model used in previous studies has a considerably higher number of trainable parameters (11 M [ 30 ]) than our proposed models.…”

Section: Models Evaluationmentioning

confidence: 99%

Lightweight deep learning models for detecting COVID-19 from chest X-ray images

Karakanis

Leontidis

2021

Computers in Biology and Medicine

121

View full text Add to dashboard Cite

Deep learning methods have already enjoyed an unprecedented success in medical imaging problems. Similar success has been evidenced when it comes to the detection of COVID-19 from medical images, therefore deep learning approaches are considered good candidates for detecting this disease, in collaboration with radiologists and/or physicians. In this paper, we propose a new approach to detect COVID-19 via exploiting a conditional generative adversarial network to generate synthetic images for augmenting the limited amount of data available. Additionally, we propose two deep learning models following a lightweight architecture, commensurating with the overall amount of data available. Our experiments focused on both binary classification for COVID-19 vs Normal cases and multi-classification that includes a third class for bacterial pneumonia. Our models achieved a competitive performance compared to other studies in literature and also a ResNet8 model. Our binary model achieved 98.7% accuracy, 100% sensitivity and 98.3% specificity, while our three-class model achieved 98.3% accuracy, 99.3% sensitivity and 98.1% specificity. Moreover, via adopting a testing protocol proposed in literature, our models proved to be more robust and reliable in COVID-19 detection than a baseline ResNet8, making them good candidates for detecting COVID-19 from posteroanterior chest X-ray images.

show abstract

“…For efficient learning of spatio-temporal features in video action recognition, a hybrid CNN was introduced in [ 174 ] used a fusion convolutional architecture. 2D and 3D CNN was fused to present temporal encoding with fewer parameters.…”

Section: Deep Learning Techniques Based Modelsmentioning

confidence: 99%

“… The performance of action recognition models as mentioned in [ 174 ]. Including: ( a ) Semi-CNN model based on VGG16 architecture ( b ) Semi-CNN model based on ResNet34 architecture ( c ) Semi-CNN model based on DenseNet121 architecture.…”

Section: Figurementioning

confidence: 99%

A Review on Computer Vision-Based Methods for Human Action Recognition

et al. 2020

View full text Add to dashboard Cite

Human action recognition targets recognising different actions from a sequence of observations and different environmental conditions. A wide different applications is applicable to vision based action recognition research. This can include video surveillance, tracking, health care, and human–computer interaction. However, accurate and effective vision based recognition systems continue to be a big challenging area of research in the field of computer vision. This review introduces the most recent human action recognition systems and provides the advances of state-of-the-art methods. To this end, the direction of this research is sorted out from hand-crafted representation based methods including holistic and local representation methods with various sources of data, to a deep learning technology including discriminative and generative models and multi-modality based methods. Next, the most common datasets of human action recognition are presented. This review introduces several analyses, comparisons and recommendations that help to find out the direction of future research.

show abstract

Semi-CNN Architecture for Effective Spatio-Temporal Learning in Action Recognition

Cited by 7 publications

References 7 publications

Human Action Recognition from Various Data Modalities: A Review

Human Action Recognition from Various Data Modalities: A Review

Lightweight deep learning models for detecting COVID-19 from chest X-ray images

A Review on Computer Vision-Based Methods for Human Action Recognition

Contact Info

Product

Resources

About