scholarly journals Spatio-Temporal Pyramid Graph Convolutions for Human Action Recognition and Postural Assessment

2021 ◽  
Author(s):  
Jawad Khan
Keyword(s):  
Risk Assessment ◽  
Computer Vision ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Convolutional Network ◽  
Potential Applications ◽  
Postural Assessment ◽  
Spatio Temporal ◽  
Ergonomic Risk Assessment

Recognition of human actions and associated interactions with objects and the environment is animportant problem in computer vision due to its potential applications in a variety of domains. Themost versatile methods can generalize to various environments and deal with cluttered backgrounds,occlusions, and viewpoint variations. Among them, methods based on graph convolutionalnetworks that extract features from the skeleton have demonstrated promising performance. In thispaper, we propose a novel Spatio-Temporal Pyramid Graph Convolutional Network (ST-PGN) foronline action recognition for ergonomic risk assessment that enables the use of features from alllevels of the skeleton feature hierarchy.

scholarly journals Human Action Recognition in Videos using a Robust CNN LSTM Approach

2020 ◽  
pp. 21-34
Author(s):  
Carlos Ismael Orozco ◽  
Eduardo Xamena ◽  
María Elena Buemi ◽  
Julio Jacobo Berlles
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Convolutional Neural Network ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Public Spaces ◽  
Human Action ◽  
Multimedia Indexing ◽  
Potential Applications ◽  
Evaluation Metric

Action recognition in videos is currently a topic of interest in the area of computer vision, due to potential applications such as: multimedia indexing, surveillance in public spaces, among others. In this paper we propose (1) Implement a CNN–LSTM architecture. First, a pre-trained VGG16 convolutional neural network extracts the features of the input video. Then, an LSTM classifies the video in a particular class. (2) Study how the number of LSTM units affects the performance of the system. To carry out the training and test phases, we used the KTH, UCF-11 and HMDB-51 datasets. (3) Evaluate the performance of our system using accuracy as evaluation metric. We obtain 93%, 91% and 47% accuracy respectively for each dataset. 

Human Action Recognition Combining Sequential Dynamic Images and Two-Stream Convolutional Network

2021 ◽  
Vol 58 (2) ◽  
pp. 0210007
Author(s):  
张文强 Zhang Wenqiang ◽  
王增强 Wang Zengqiang ◽  
张良 Zhang Liang
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Convolutional Network

scholarly journals Learning Graph Convolutional Network for Skeleton-Based Human Action Recognition by Neural Searching

2020 ◽  
Vol 34 (03) ◽  
pp. 2669-2676 ◽  
Author(s):  
Wei Peng ◽  
Xiaopeng Hong ◽  
Haoyu Chen ◽  
Guoying Zhao
Keyword(s):  
Action Recognition ◽  
Large Scale ◽  
Order Approximation ◽  
Human Action Recognition ◽  
Search Space ◽  
Human Action ◽  
Higher Order ◽  
Dynamic Graph ◽  
Convolutional Network ◽  
Representational Capacity

Human action recognition from skeleton data, fuelled by the Graph Convolutional Network (GCN) with its powerful capability of modeling non-Euclidean data, has attracted lots of attention. However, many existing GCNs provide a pre-defined graph structure and share it through the entire network, which can loss implicit joint correlations especially for the higher-level features. Besides, the mainstream spectral GCN is approximated by one-order hop such that higher-order connections are not well involved. All of these require huge efforts to design a better GCN architecture. To address these problems, we turn to Neural Architecture Search (NAS) and propose the first automatically designed GCN for this task. Specifically, we explore the spatial-temporal correlations between nodes and build a search space with multiple dynamic graph modules. Besides, we introduce multiple-hop modules and expect to break the limitation of representational capacity caused by one-order approximation. Moreover, a corresponding sampling- and memory-efficient evolution strategy is proposed to search in this space. The resulted architecture proves the effectiveness of the higher-order approximation and the layer-wise dynamic graph modules. To evaluate the performance of the searched model, we conduct extensive experiments on two very large scale skeleton-based action recognition datasets. The results show that our model gets the state-of-the-art results in term of given metrics.

Spatio-temporal SRU with global context-aware attention for 3D human action recognition

2020 ◽  
Vol 79 (17-18) ◽  
pp. 12349-12371
Author(s):  
Qingshan She ◽  
Gaoyuan Mu ◽  
Haitao Gan ◽  
Yingle Fan
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Context Aware ◽  
Global Context ◽  
Spatio Temporal

scholarly journals Agglomerative Clustering and Residual-VLAD Encoding for Human Action Recognition

2020 ◽  
Vol 10 (12) ◽  
pp. 4412
Author(s):  
Ammar Mohsin Butt ◽  
Muhammad Haroon Yousaf ◽  
Fiza Murtaza ◽  
Saima Nazir ◽  
Serestina Viriri ◽  
...  
Keyword(s):  
Action Recognition ◽  
Feature Vector ◽  
Human Action Recognition ◽  
Human Action ◽  
Compact Representation ◽  
Agglomerative Clustering ◽  
Residual Vector ◽  
Benchmark Datasets ◽  
Codebook Generation ◽  
Spatio Temporal

Human action recognition has gathered significant attention in recent years due to its high demand in various application domains. In this work, we propose a novel codebook generation and hybrid encoding scheme for classification of action videos. The proposed scheme develops a discriminative codebook and a hybrid feature vector by encoding the features extracted from CNNs (convolutional neural networks). We explore different CNN architectures for extracting spatio-temporal features. We employ an agglomerative clustering approach for codebook generation, which intends to combine the advantages of global and class-specific codebooks. We propose a Residual Vector of Locally Aggregated Descriptors (R-VLAD) and fuse it with locality-based coding to form a hybrid feature vector. It provides a compact representation along with high order statistics. We evaluated our work on two publicly available standard benchmark datasets HMDB-51 and UCF-101. The proposed method achieves 72.6% and 96.2% on HMDB51 and UCF101, respectively. We conclude that the proposed scheme is able to boost recognition accuracy for human action recognition.

Sign in / Sign up

Export Citation Format

Share Document