4.6 Article

Augmentation of Human Action Datasets with Suboptimal Warping and Representative Data Samples

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

Skeleton edge motion networks for human action recognition

Haoran Wang et al.

Summary: A new human action recognition method, skeleton edge motion networks (SEMN), is proposed in this paper to explore the motion information of human body parts by investigating skeleton edge movements. Experimental results demonstrate the effectiveness of the proposed method on five popular human action recognition datasets.

NEUROCOMPUTING (2021)

Article Computer Science, Artificial Intelligence

Skeleton-based action recognition via spatial and temporal transformer networks

Chiara Plizzari et al.

Summary: In this study, a novel Spatial-Temporal Transformer network (ST-TR) is proposed to model dependencies between joints using the Transformer self-attention operator. The ST-TR model utilizes a Spatial Self Attention module (SSA) to understand intra-frame interactions between different body parts, and a Temporal Self-Attention module (TSA) to model inter-frame correlations, achieving good performance in human activity recognition tasks.

COMPUTER VISION AND IMAGE UNDERSTANDING (2021)

Article Chemistry, Analytical

A Bayesian Dynamical Approach for Human Action Recognition

Amirreza Farnoosh et al.

Summary: The study introduces a generative Bayesian switching dynamical model for action recognition in 3D skeletal data, which parses meaningful intrinsic states in skeletal dynamics for action recognition and explicitly models temporal transitions to be generative. Experimental results demonstrate the superior performance of the model compared to the state-of-the-art methods on large-scale datasets, achieving significant improvements in action classification accuracy and predictive error.

SENSORS (2021)

Proceedings Paper Computer Science, Information Systems

Data Augmentation Strategies for Human Activity Data Using Generative Adversarial Neural Networks

Alexander Hoelzemann et al.

Summary: This paper presents an algorithm comparing two augmentation strategies to extend the dataset size for improving the application of deep learning in Human Activity Recognition. The use of data augmentation techniques can enhance dataset quality and generalization ability, effectively addressing overfitting issues due to limited data.

2021 IEEE INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING AND COMMUNICATIONS WORKSHOPS AND OTHER AFFILIATED EVENTS (PERCOM WORKSHOPS) (2021)

Article Engineering, Biomedical

A novel data augmentation method to enhance deep neural networks for detection of atrial fibrillation

Ping Cao et al.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2020)

Article Chemistry, Analytical

Data Augmentation with Suboptimal Warping for Time-Series Classification

Krzysztof Kamycki et al.

SENSORS (2020)

Article Chemistry, Multidisciplinary

Hand Posture Recognition Using Skeletal Data and Distance Descriptor

Tomasz Kapuscinski et al.

APPLIED SCIENCES-BASEL (2020)

Article Multidisciplinary Sciences

Human Action Recognition Using Bone Pair Descriptor and Distance Descriptor

Dawid Warchol et al.

SYMMETRY-BASEL (2020)

Review Chemistry, Analytical

A Comprehensive Survey of Vision-Based Human Action Recognition Methods

Hong-Bo Zhang et al.

SENSORS (2019)

Article Computer Science, Information Systems

Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE

Georgios Douzas et al.

INFORMATION SCIENCES (2019)

Article Computer Science, Artificial Intelligence

Time series cluster kernel for learning similarities between multivariate time series with missing data

Karl Oyvind Mikalsen et al.

PATTERN RECOGNITION (2018)

Article Computer Science, Artificial Intelligence

Long-Term Recurrent Convolutional Networks for Visual Recognition and Description

Jeff Donahue et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Article Computer Science, Artificial Intelligence

Sparse composition of body poses and atomic actions for human activity recognition in RGB-D videos

Ivan Lillo et al.

IMAGE AND VISION COMPUTING (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Generating synthetic time series to augment sparse datasets

Germain Forestier et al.

2017 17TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM) (2017)

Article Computer Science, Artificial Intelligence

Multimodal Multipart Learning for Action Recognition in Depth Videos

Amir Shahroudy et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2016)

Article Computer Science, Artificial Intelligence

Activity recognition using a supervised non-parametric hierarchical HMM

Natraj Raman et al.

NEUROCOMPUTING (2016)

Article Automation & Control Systems

Learning a Mahalanobis Distance-Based Dynamic Time Warping Measure for Multivariate Time Series Classification

Jiangyuan Mei et al.

IEEE TRANSACTIONS ON CYBERNETICS (2016)

Article Computer Science, Information Systems

Joint movement similarities for robust 3D action recognition using skeletal data

Hossein Pazhoumand-Dar et al.

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION (2015)

Article Computer Science, Artificial Intelligence

Human Activity Recognition Process Using 3-D Posture Data

Salvatore Gaglio et al.

IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS (2015)