Lite-3DCNN Combined with Attention Mechanism for Complex Human Movement Recognition

Zhu, Maochang; Bin, Sheng; Sun, Gengxin

doi:10.1155/2022/4816549

Cited by 4 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Zhu et al developed an attention-based 3D model for human motion recognition, including extraction of both spatial and temporal features. Their model increased Dice scores by 5–10% over traditional models, yielding average scores of 84.8–91.6% [40] . Thus, our model’s 25% improvement in diaphysis segmentation accuracy compares favourably to the accuracy gains produced by this and other recent attention-based U-Net models.…”

Section: Discussionmentioning

confidence: 98%

A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data

Morris,

Wang,

Papanastasiou

et al. 2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 98%

A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data

Morris,

Wang,

Papanastasiou

et al. 2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

“…In terms of skeletal motion recognition, previous methods treat the skeleton as a false image or sequence, and then use convolutional neural nets or recurrent neural nets to further extract motion characteristics [23]. This paper represents the human skeleton as a diagram based on the physical structure of the body to make it more natural.…”

Section: B Action Recognition Algorithm Based On Selective Hypergraph...mentioning

confidence: 99%

A Hybrid Deep Learning-Based Intelligent System for Sports Action Recognition via Visual Knowledge Discovery

Zhao

2023

IEEE Access

View full text Add to dashboard Cite

The intelligent recognition systems for sports actions have been a more general demand, so as to facilitate technical analysis of health management. This highly relies on deep analysis towards frame-level image data from the perspective of visual knowledge discovery. In recent years, the rapid development of deep learning technology has well boosted a number of technical breakthrough in computer vision. In this context, this work takes aerobics as the main object, and proposes a hybrid deep learning-based intelligent system for sports action recognition via visual knowledge discovery. Specifically, the human skeleton is represented as a graph based on the physical structure of the human body in this paper, and the selective hypergraph convolution network is selected to adaptively extract the multi-scale information in the skeleton. And the selective-frame temporal convolution is specially selected for the situation to construct recognition model. Upon the basis of proper feature extraction, a triple loss-based error measurement method is employed to construct objective function, and a recurrent neural network structure is further developed to model dynamic action sequence characteristics. The data source of this article is mainly the private data compiled by the research group. Finally, experiments are carried out on the CMU motion capture dataset, and the effectiveness of the proposed algorithm is verified by comparing the experimental results with those of the existing algorithms.INDEX TERMS Hybrid deep learning, intelligent systems, action recognition, visual knowledge discovery.

show abstract

“…In [ 30 ], a residual self-attention deep neural network is proposed to capture local, global, and spatial information of magnetic resonance images to improve diagnostic performance. In [ 31 ], a very similar self-attention block as in [ 30 ] is proposed for complex human motion video classification.…”

Section: Related Workmentioning

confidence: 99%

Shot Boundary Detection with 3D Depthwise Convolutions and Visual Attention

Esteve Brotons,

Lucendo,

Javier

et al. 2023

Sensors

View full text Add to dashboard Cite

Shot boundary detection is the process of identifying and locating the boundaries between individual shots in a video sequence. A shot is a continuous sequence of frames that are captured by a single camera, without any cuts or edits. Recent investigations have shown the effectiveness of the use of 3D convolutional networks to solve this task due to its high capacity to extract spatiotemporal features of the video and determine in which frame a transition or shot change occurs. When this task is used as part of a scene segmentation use case with the aim of improving the experience of viewing content from streaming platforms, the speed of segmentation is very important for live and near-live use cases such as start-over. The problem with models based on 3D convolutions is the large number of parameters that they entail. Standard 3D convolutions impose much higher CPU and memory requirements than do the same 2D operations. In this paper, we rely on depthwise separable convolutions to address the problem but with a scheme that significantly reduces the number of parameters. To compensate for the slight loss of performance, we analyze and propose the use of visual self-attention as a mechanism of improvement.

show abstract

Lite-3DCNN Combined with Attention Mechanism for Complex Human Movement Recognition

Cited by 4 publications

References 27 publications

A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data

A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data

A Hybrid Deep Learning-Based Intelligent System for Sports Action Recognition via Visual Knowledge Discovery

Shot Boundary Detection with 3D Depthwise Convolutions and Visual Attention

Contact Info

Product

Resources

About