4.6 Article

View Enhanced Jigsaw Puzzle for Self-Supervised Feature Learning in 3D Human Action Recognition

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction

Maosen Li et al.

Summary: In this paper, we propose a symbiotic graph neural network model to address the problems of 3D skeleton-based action recognition and motion prediction. The model utilizes graphs of two scales to capture relations among body-joints and body-parts, and achieves better performances on both tasks through joint training of a backbone, an action-recognition head, and a motion-prediction head.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Proceedings Paper Computer Science, Artificial Intelligence

How and What to Learn: Taxonomizing Self-Supervised Learning for 3D Action Recognition

Amor Ben Tanfous et al.

Summary: This study reconciles two different approaches, attractive learning and contrastive learning, as well as representation optimization in decoder output space and network's latent space, by developing a taxonomy of self-supervised learning for action recognition. Combining these methods leads to improved performance and tolerance to transformations.

2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) (2022)

Article Automation & Control Systems

Convolutional Multitimescale Echo State Network

Qianli Ma et al.

Summary: The ConvMESN model is proposed to capture multitimescale dynamics and multiscale temporal dependencies of temporal data, demonstrated through extensive experiments on benchmark datasets. By leveraging a multitimescale memory encoder and a convolutional layer, ConvMESN shows strong learning ability and efficient memory encoding for complex temporal data. The model outperforms existing methods and provides high-computational efficiency, making it a promising approach for modeling complex temporal data.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Computer Science, Information Systems

Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition

Haocong Rao et al.

Summary: The paper proposes a contrastive action learning paradigm named AS-CAL, which learns action representations in an unsupervised manner by contrasting similarities between augmented instances of skeleton sequences and encoding longterm action dynamics using momentum LSTM. The approach significantly outperforms hand-crafted methods and even achieves superior performance to many supervised learning methods.

INFORMATION SCIENCES (2021)

Proceedings Paper Computer Science, Artificial Intelligence

IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos

Gyeongsik Moon et al.

Summary: Current action recognition methods heavily rely on appearance or pose information. Integrating these two approaches is challenging, but a proposed pose-driven feature integration method achieves highly robust performance on action video datasets.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

Article Computer Science, Information Systems

Skeleton-Based Action Recognition With Low-Level Features of Adaptive Graph Convolutional Networks

Jialin Gang et al.

Summary: Skeleton-based action recognition is a significant classification problem in human-computer interaction and video understanding. By introducing a multi-branches structure, this paper combines high-level and low-level features of human skeleton to achieve considerable improvement in action recognition.

IEEE ACCESS (2021)

Article Computer Science, Information Systems

2D Pose-Based Real-Time Human Action Recognition With Occlusion-Handling

Federico Angelini et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2020)

Review Computer Science, Artificial Intelligence

A Comparative Review of Recent Kinect-Based Action Recognition Algorithms

Lei Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

Proceedings Paper Computer Science, Artificial Intelligence

An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition

Chenyang Si et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Article Computer Science, Information Systems

SRNet: Structured Relevance Feature Learning Network From Skeleton Data for Human Action Recognition

Weizhi Nie et al.

IEEE ACCESS (2019)

Article Computer Science, Artificial Intelligence

RGB-D-based human motion recognition with deep learning: A survey

Pichao Wang et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2018)

Article Computer Science, Artificial Intelligence

Learning content and style: Joint action recognition and person identification from human skeletons

Hongsong Wang et al.

PATTERN RECOGNITION (2018)

Article Engineering, Electrical & Electronic

Skeleton embedded motion body partition for human action recognition using depth sequences

Xiaopeng Ji et al.

SIGNAL PROCESSING (2018)

Article Engineering, Electrical & Electronic

SkeletonNet: Mining Deep Part Features for 3-D Action Recognition

Qiuhong Ke et al.

IEEE SIGNAL PROCESSING LETTERS (2017)

Article Computer Science, Artificial Intelligence

Going deeper into action recognition: A survey

Samitha Herath et al.

IMAGE AND VISION COMPUTING (2017)

Article Computer Science, Artificial Intelligence

Enhanced skeleton visualization for view invariant human action recognition

Mengyuan Liu et al.

PATTERN RECOGNITION (2017)

Proceedings Paper Computer Science, Artificial Intelligence

A New Representation of Skeleton Sequences for 3D Action Recognition

Qiuhong Ke et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Ensemble Deep Learning for Skeleton-based Action Recognition using Temporal Sliding LSTM networks

Inwoong Lee et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks

Pichao Wang et al.

MM'16: PROCEEDINGS OF THE 2016 ACM MULTIMEDIA CONFERENCE (2016)

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised Visual Representation Learning by Context Prediction

Carl Doersch et al.

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2015)

Review Computer Science, Artificial Intelligence

Human activity recognition from 3D data: A review

J. K. Aggarwal et al.

PATTERN RECOGNITION LETTERS (2014)