Deep Residual Temporal Convolutional Networks for Skeleton-Based Human Action Recognition

Khamsehashari, Razieh; Gadzicki, Konrad; Zetzsche, Christoph

doi:10.1007/978-3-030-34995-0_34

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advent of the temporal convolutional network (TCN), CNNs have also achieved some competitiveness in temporal analysis, and TCNs have the properties of high interpretability and fast training that RNNs do not have. Depending on the task requirements, encoder-decoder TCNs [15] and residual TCNs [21], which are derived from TCN improvements, have shown superb performance on various temporal tasks. However, the TCN deal with local neighborhoods across time, which can lead to a deficiency in modeling the long-term dependence between temporal patterns of temporal signals.…”

Section: Introductionmentioning

confidence: 99%

Non-invasive dual attention TCN for electromyography and motion data fusion in lower limb ambulation prediction

Zhou

Feng²,

Wang³

et al. 2022

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Recent technological advances show the feasibility of fusing surface electromyography (sEMG) signals and movement data to predict lower limb ambulation intentions. However, since the invasive fusion of different signals is a major impediment to improving predictive performance, searching for a non-invasive fusion mechanism for lower limb ambulation pattern recognition based on different modal features is crucial. Approach. We propose an end-to-end sequence prediction model with non-invasive dual attention temporal convolutional networks (NIDA-TCN) as a core to elegantly address the essential deficiencies of traditional decision models with heterogeneous signal fusion. Notably, the NIDA-TCN is a weighted fusion of sEMG and inertial measurement units (IMU) with time-dependent effective hidden information in the temporal and channel dimensions using TCN and self-attentive mechanisms. The new model can better discriminate between walking, jumping, downstairs, and upstairs four lower limb activities of daily living (ADL). Main results. The results of this study show that the NIDA-TCN models produce predictions that significantly outperform both frame-wise and TCN models in terms of accuracy, sensitivity, precision, F1 score, and stability. Particularly, the NIDA-TCN with sequence decision fusion (NIDA-TCN-SDF) models, have maximum accuracy and stability increments of 3.37% and 4.95% relative to the frame-wise model, respectively, without manual feature-encoding and complex model parameters. Significance. It is concluded that the results demonstrate the validity and feasibility of the NIDA-TCN-SDF models to ensure the prediction of daily lower limb ambulation activities, paving the way to the development of fused heterogeneous signal decoding with better prediction performance.

show abstract

Section: Introductionmentioning

confidence: 99%