Large-Scale Self-Supervised Human Activity Recognition

被引：0

作者：

Zadeh, Mohammad Zaki ^{[1
]}

Jaiswal, Ashish ^{[1
]}

Pavel, Hamza Reza ^{[1
]}

Hebri, Aref ^{[1
]}

Kapoor, Rithik ^{[1
]}

Makedon, Fillia ^{[1
]}

机构：

[1] Univ Texas Arlington, Arlington, TX 76019 USA

来源：

PROCEEDINGS OF THE 15TH INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS, PETRA 2022 | 2022年

关键词：

computer vision; deep learning; self-supervised learning;

D O I：

10.1145/3529190.3534720

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this paper, a self-supervised approach is used to obtain an effective human activity representation using a limited set of annotated data. This research is aimed on acquiring human activity representation in order to improve the accuracy of classifying videos of human activities in the NTU RGB+D 120 dataset. The effectiveness of various self-supervised approaches, as well as a supervised method, is studied. The results reveal that when the training set gets smaller, the performance of supervised learning approaches diminishes, whereas self-supervised methods maintain their performance by utilizing unlabeled data.

引用

页码：298 / 299

页数：2

共 50 条

[31] Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion
Taghanaki, Setareh Rahimi
Rainbow, Michael
Etemad, Ali
IWSC'21: PROCEEDINGS OF THE 2021 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS, 2021, : 23 - 27
[32] Self-supervised multimodal fusion transformer for passive activity recognition
Koupai, Armand K.
Bocus, Mohammud J.
Santos-Rodriguez, Raul
Piechocki, Robert J.
McConville, Ryan
IET WIRELESS SENSOR SYSTEMS, 2022, 12 (5-6) : 149 - 160
[33] Self-supervised Mining of Human Activity from CGM
Nguyen Minh The
Kawamura, Takahiro
Nakagawa, Hiroyuki
Tahara, Yasuyuki
Ohsuga, Akihiko
KNOWLEDGE MANAGEMENT AND ACQUISITION FOR SMART SYSTEMS AND SERVICES, 2010, 6232 : 61 - 72
[34] Self-supervised mining of human activity from CGM
Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan
Lect. Notes Comput. Sci., (61-72):
[35] Self-supervised learning for visual tracking and recognition of human hand
Wu, Y
Huang, TS
SEVENTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-2001) / TWELFTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (IAAI-2000), 2000, : 243 - 248
[36] Progressive Multi-scale Self-supervised Learning for Speech Recognition
Wan, Genshun
Chen, Hang
Liu, Tan
Wang, Chenxi
Pan, Jia
Ye, Zhongfu
2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC, 2023, : 978 - 982
[37] Foundation Model for Endoscopy Video Analysis via Large-Scale Self-supervised Pre-train
Wang, Zhao
Liu, Chang
Zhang, Shaoting
Dou, Qi
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2023, PT IX, 2023, 14228 : 101 - 111
[38] Temporal Contrastive Learning for Sensor-Based Human Activity Recognition: A Self-Supervised Approach
Chen, Xiaobing
Zhou, Xiangwei
Sun, Mingxuan
Wang, Hao
IEEE SENSORS JOURNAL, 2025, 25 (01) : 1839 - 1850
[39] Self-Supervised Human Activity Recognition With Localized Time-Frequency Contrastive Representation Learning
Taghanaki, Setareh Rahimi
Rainbow, Michael
Etemad, Ali
IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, 2023, 53 (06) : 1027 - 1037
[40] Self-supervised learning with randomized cross-sensor masked reconstruction for human activity recognition
Logacjov, Aleksej
Bach, Kerstin
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 128

← 1 2 3 4 5 →