Novel Cross-View Human Action Model Recognition Based on the Powerful View-Invariant Features Technique

Abstract

One of the most important research topics nowadays is human action recognition, which is of significant interest to the computer vision and machine learning communities. Some of the factors that hamper it include changes in postures and shapes and the memory space and time required to gather, store, label, and process the pictures. During our research, we noted a considerable complexity to recognize human actions from different viewpoints, and this can be explained by the position and orientation of the viewer related to the position of the subject. We attempted to address this issue in this paper by learning different special view-invariant facets that are robust to view variations. Moreover, we focused on providing a solution to this challenge by exploring view-specific as well as view-shared facets utilizing a novel deep model called the sample-affinity matrix (SAM). These models can accurately determine the similarities among samples of videos in diverse angles of the camera and enable us to precisely fine-tune transfer between various views and learn more detailed shared facets found in cross-view action identification. Additionally, we proposed a novel view-invariant facets algorithm that enabled us to better comprehend the internal processes of our project. Using a series of experiments applied on INRIA Xmas Motion Acquisition Sequences (IXMAS) and the Northwestern–UCLA Multi-view Action 3D (NUMA) datasets, we were able to show that our technique performs much better than state-of-the-art techniques.

An End-to-End Model of ArVi-MoCoGAN and C3D with Attention Unit for Arbitrary-view Dynamic Gesture Recognition

“…The experimental results on NUMA dataset show that the highest accuracy belongs to (ArVi-MoCoGAN+C3D) with 94.51%, the next ones are 93.81% of Multi-Br TSN -GRU, 92.78% of R34 (2+1)D With CVA, 92.1% of DA-Net [36], 90.3% of TSN [37], and 88.49% of Multi-Br TSN. The worst case happens to SAM [38] with 83.2%. The experiments for two end-to-end methods, ArViAvr and ArViAU (presented in Sec.…”

“…The transformerbased architectures can also be deployed to improve both gesture data generation and recognition. [39] 81.3 ---ST+Spin-Image features [43] 71.7 ---SSM [40] 72.7 ---SAM [38] ---77.2 R-NKTM [26] 74.1 ---WLE [41] 82.…”

Novel Hand Gesture Alert System

“…In today's frameworks, the extraction of Regions of Interest (ROIs) and the representation of characteristics are the two main factors under study [13][14][15][16][17][18]. In [19], the difference in intensity of an individual pixel is incorporated into shape-oriented features to capture salient features.…”

Research on action recognition for college dance teaching based on deep learning

“…Kumar, R. et al constructed a human action recognition system, which is organized to contain all the features of the overall HAR framework, summarized the advantages and disadvantages of all methods of action representation and action analysis, and finally chose deep learning as the main algorithm of the study, and through the graphical data to analyze the performance of the deep learning algorithm, which indicates the future direction for the challenges faced in the field of human action recognition [8]. Mambou, S. et al addressed the human action recognition complexity problem by learning human actions under different positional transformations, using the SAM new depth model, sharing action recognition information, and, in addition, proposed a new view-invariant surface algorithm through the INRIAXms motion capture sequences for multi-view 3D data experiments on student actions at a college in Los Angeles, which proved that the proposed algorithm performs better [9]. Ma, F. in order to improve the effect of dance teaching, put forward three directions of attention: one is to focus on the completeness of the evaluation index, the second is to focus on the ambiguity and uncertainty of the evaluation process, and the third is to ensure the reliability and accuracy of the evaluation.…”