Human activity recognition (har) using deep learning: Review, methodologies, progress and future research directions

P Kumar, S Chauhan, LK Awasthi - Archives of Computational Methods in …, 2024 - Springer
Human activity recognition is essential in many domains, including the medical and smart
home sectors. Using deep learning, we conduct a comprehensive survey of current state …

Low-cost CNN for automatic violence recognition on embedded system

JC Vieira, A Sartori, SF Stefenon, FL Perez… - IEEE …, 2022 - ieeexplore.ieee.org
Due to the increasing number of violence cases, there is a high demand for efficient
monitoring systems, however, these systems can be susceptible to failure. Therefore, this …

Facial emotion recognition and music recommendation system using CNN-based deep learning techniques

B Bakariya, A Singh, H Singh, P Raju, R Rajpoot… - Evolving Systems, 2024 - Springer
Abstract Facial Expression Recognition (FER) is utilized in various fields, such as education,
gaming, robotics, healthcare, and others. Facial expression techniques, for instance, an …

ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videos

SDS Dass, HB Barua, G Krishnasamy… - … Conference on Pattern …, 2025 - Springer
Human action or activity recognition in videos is a fundamental task in computer vision with
applications in surveillance and monitoring, self-driving cars, sports analytics, human-robot …

Weighted voting ensemble of hybrid CNN-LSTM Models for vision-based human activity recognition

S Aggarwal, G Bhola, DK Vishwakarma - Multimedia Tools and …, 2024 - Springer
This research work aims to propose an ensemble model of different pre-trained CNN
networks combined with LSTM to detect a set of routine human activities practiced by the …

A 3D motion image recognition model based on 3D CNN-GRU model and attention mechanism

C Cheng, H Xu - Image and Vision Computing, 2024 - Elsevier
Moving image recognition has become a well-explored problem in computer vision.
However, it is difficult for the traditional convolutional neural network (CNN) model to …

DeepWE: A Deep Bayesian Active Learning Waypoint Estimator for Indoor walkers

Z Huang, S Poslad, Q Li, B Yang, J Xia… - IEEE Internet of …, 2023 - ieeexplore.ieee.org
Waypoint estimation (WE) has a wide range of applications for indoor walkers, such as fire
rescue and navigation to find exit doors, lifts, or stairs as examples of waypoints, etc. Data …

Lightweight CNN-Based Image Recognition with Ecological IoT Framework for Management of Marine Fishes

L Jia, X Xie, J Yang, F Li, Y Zhou, X Fan… - Journal of Circuits …, 2023 - World Scientific
With the development of emerging information technology, the traditional management
methods of marine fishes are slowly replaced by new methods due to high cost, time …

[PDF][PDF] 基于双流-非局部时空残差卷积神经网络的人体行为识别

钱惠敏, 陈实, 皇甫晓瑛 - 电子与信息学报, 2024 - jeit.ac.cn
3 维卷积神经网络(3D CNN) 与双流卷积神经网络(two-stream CNN) 是视频中人体行为识别
研究的常用架构, 且各有优势. 该文旨在研究结合两种架构且复杂度低, 识别精度高的人体行为 …

Analyzing the Variability of RNN Hyperparameters and Architectures for HAR with Wearable Sensor Data

N Bansal, A Bansal, M Gupta - 2024 3rd International …, 2024 - ieeexplore.ieee.org
Human activity recognition (HAR) is a rapidly growing field of study with important practical
implications in areas as diverse as medicine, sports performance analysis, and the care of …