RNNs, CNNs and Transformers in Human Action Recognition: A Survey and A Hybrid Model

K Alomar, HI Aysel, X Cai - arXiv preprint arXiv:2407.06162, 2024 - arxiv.org
Human Action Recognition (HAR) encompasses the task of monitoring human activities
across various domains, including but not limited to medical, educational, entertainment …

RL-CWtrans Net: multimodal swimming coaching driven via robot vision

G Wang - Frontiers in Neurorobotics, 2024 - frontiersin.org
In swimming, the posture and technique of athletes are crucial for improving performance.
However, traditional swimming coaches often struggle to capture and analyze athletes' …

Micro-Action Recognition via Hierarchical Fusion and Inference

F Gong, J Chen, J Zhu, Q Bao, F Gao, R Gu… - Proceedings of the 32nd …, 2024 - dl.acm.org
Micro-actions are spontaneous body movements that indicate a person's true feelings and
potential intentions, and micro-action recognition is important in human behavior analysis …

Hybrid Transformer-EfficientNet Model for Robust Human Activity Recognition: The BiTransAct Approach

AU Nabi, J Shi, AK Jumani, JA Bhutto - IEEE Access, 2024 - ieeexplore.ieee.org
Human Activity Recognition (HAR) has been employed in a number of applications
including sports analytic, healthcare monitoring, surveillance, and human-computer …

Human Action Classification Method Based on Deep Features to Assist Visually Impaired People

M Badri, M Frikha, M Hammami - Procedia Computer Science, 2024 - Elsevier
Assisting visually impaired people to be more independent in their daily activities has
always been a promising research area. In this context, we proposed a novel human action …

Novel Deep Learning Method for Forecasting ENSO

M Naisipour, I Saeedpanah, A Adib - Journal of Hydraulic Structures, 2024 - jhs.scu.ac.ir
Ability of predicting climate phenomena enables international organization and
governments to manage natural disasters such as droughts. El Niño Sothern Oscillation …

DESformer: A Dual-branch Encoding Strategy for Semantic Segmentation of Very-High-Resolution Remote Sensing Images based on Feature Interaction and Multi …

W Liu, N Cui, L Guo, S Du… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Global contextual information is crucial for the semantic segmentation of remote sensing
(RS) images. However, the majority of current approaches depend on convolutional neural …