Overview of temporal action detection based on deep learning

Hu, Kai; Shen, Chaowen; Wang, Tianyan; Xu, Keer; Xia, Qingfeng; Xia, Min; Cai, Chengxue

doi:10.1007/s10462-023-10650-w

Cited by 6 publications

(1 citation statement)

References 161 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At each time step t, the input sequence vector, the hidden layer output, and the cell state are considered. The outputs include the LSTM hidden layer output and the cell state [57,58]. The formulas for the forget gate, input gate, and output gate are as follows:…”

Section: Lstm Modulementioning

confidence: 99%

An Interpolation and Prediction Algorithm for XCO2 Based on Multi-Source Time Series Data

Hu,

Zhang,

Feng

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Carbon satellites are an important observation tool for analyzing ground carbon emission. From the perspective of the Earth’s scale, the spatiotemporal sparse characteristics of raw data observed from carbon satellite requires the accurate interpolation of data, and based on only this work, people predict future carbon emission trends and formulate appropriate management and conservation strategies. The existing research work has not fully considered the close correlation between data and seasons, as well as the characteristics accumulated over a long time scale. In this paper, firstly, by employing extreme random forests and auxiliary data, we reconstruct a daily average CO2 dataset at a resolution of 0.25°, and achieve a validated determination coefficient of 0.92. Secondly, introducing technologies such as Time Convolutional Networks (TCN), Channel Attention Mechanism (CAM), and Long Short-Term Memory networks (LSTM), we conduct atmospheric CO2 concentration interpolation and predictions. When conducting predictive analysis for the Yangtze River Delta region, we train the model by using quarterly data from 2016 to 2020; the correlation coefficient in summer is 0.94, and in winter it is 0.91. These experimental data indicate that compared to other algorithms, this algorithm has a significantly better performance.

show abstract

Section: Lstm Modulementioning

confidence: 99%

An Interpolation and Prediction Algorithm for XCO2 Based on Multi-Source Time Series Data

Hu,

Zhang,

Feng

et al. 2024

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

Improving Temporal Action Segmentation and Detection with Hierarchical Task Grammar

Yihui,

Rajan

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A steel defect detection method based on edge feature extraction via the Sobel operator

Wang,

Yin,

Chen

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Scratches and cracks in steel severely affect its service life and performance. However, owing to the irregular shapes and sizes of steel surface defects, defects within the same class may be different, whereas defects between classes may be similar. Existing methods focus only on spatial information, resulting in low detection accuracy. To alleviate these problems, this paper proposes the ECDY (EIFEM CARAFE DyHead) network to enhance the detection capability of steel defects. We first design a feature extraction module that focuses on the edge information of feature contours. This module uses the Sobel operator to extract the edge information of a feature and fuses it with the overall spatial information so that richer semantic information can be obtained. The module has improved accuracy in the YOLOv5, YOLOv8, and YOLOv10 versions, and uses fewer parameters and calculations. In particular, in YOLOv8x, mAP@0.5 increased by 2.5%, and the number of parameters was reduced by 12.4 M. Second, to retain the detailed information in the feature pyramid, and to better reconstruct features, we choose the content-aware reassembly feature method (CARAFE) as the upsampling method. Finally, the detection head was replaced with a dynamic unified detection head (DyHead) to adapt to different defect sizes and different task requirements. Compared with YOLOv8s, the proposed method improves precision by 1.6%, recall by 4%, and mAP@0.5 by 4%. This value is 4.2% higher than the mAP@0.5 of the current SOTA model RT-DETR-L in the field of object detection and has 23.2 M fewer parameters.

show abstract

Overview of temporal action detection based on deep learning

Cited by 6 publications

References 161 publications

An Interpolation and Prediction Algorithm for XCO2 Based on Multi-Source Time Series Data

An Interpolation and Prediction Algorithm for XCO2 Based on Multi-Source Time Series Data

Improving Temporal Action Segmentation and Detection with Hierarchical Task Grammar

A steel defect detection method based on edge feature extraction via the Sobel operator

Contact Info

Product

Resources

About