Analysis of Deep Neural Networks for Human Activity Recognition in Videos—A Systematic Literature Review

Abstract

From the past few decades, Human activity recognition (HAR) is one of the vital research areas in computer vision in which much research is ongoing. The researcher's focus is shifting towards this area due to its vast range of real-life applications to assist in daily living. Therefore, it is necessary to validate its performance on standard benchmark datasets and state-of-the-art systems before applying it in real-life applications. The primary objective of this Systematic Literature Review (SLR) is to collect existing research on video-based human activity recognition, summarize, and analyze the state-of-the-art deep learning architectures regarding various methodologies, challenges, and issues. The top five scientific databases (such as ACM, IEEE, ScienceDirect, SpringerLink, and Taylor & Francis) are accessed to accompany this systematic study by summarizing 70 different research articles on human activity recognition after critical review. Human activity recognition in videos is a challenging problem due to its diverse and complex nature. For accurate video classification, extraction of both spatial and temporal features from video sequences is essential. Therefore, this SLR focuses on reviewing the recent advancements in stratified self-deriving feature-based deep learning architectures. Furthermore, it explores various deep learning techniques available for HAR, challenges researchers to face to build a robust model, and state-of-theart datasets used for evaluation. This SLR intends to provide a baseline for video-based human activity recognition research while emphasizing several challenges regarding human activity recognition accuracy in video sequences using deep neural architectures.

Transformer-based spatial-temporal detection of apoptotic cell death in live-cell imaging

“…In human activity recognition benchmark, 3DCNNs(Vrskova et al 2022), two-streams networks(Ye et al 2019), and RNNs(Mohd Noor, Tan, and Ab Wahab 2022) have proved to score the highest accuracy on most kinetic datasets(Ullah et al 2021). However, in most studies for the classification of apoptosis, authors unanimely employed RNNs such as Conv-LSTMs.…”

A Survey on Yogic Posture Recognition

“…There have been several reviews published in the area of human activity recognition in vision [25], [26], [27], [28], [29], [30], [31], sensor [32], [33], [34], [35], [36], [37], machine learning [38], [39], [40], [41], [42], [43], and deep learning-based methodologies [44], [45], [46], [47], [48], [49], [50], [51]. Nevertheless, there needs to be a survey that focuses specifically on yogic posture recognition.…”

Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences

“…3D convolution improves feature learning but increases parameter costs. With MicroNets and asymmetric one-directional 3D convolutions, Ullah et al [5] overcame this problem. They proposed that micro nets improve feature learning by incorporating multiscale 3D convolution branches to handle the different scales of convolutional features in videos.…”

“…Primarily, they focused on traditional machine learning approaches such as Support Vector Machine (SVM), Hidden Markov Models (HMM) and deep learning approaches. Nevertheless, conventional machine learning methods, usually referred to as shallow learning, rely on expert human knowledge to extract data characteristics, restricting the architecture designed for one environment to solving issues in another [5].…”