There is a newer version of the record available.

Published August 14, 2021 | Version v6
Dataset Open

TAD-Net: An Approach for Realtime Action Detection Based on TCN and GCN in Digital Twin Shop-floor

Creators

Description

We proposed a real-time detection approach for shop-floor production action, this approach took the sequence data of continuous human skeleton joints sequence as input, reconstructed the Joint Classification-Regression Recurrent Neural Networks (JCR-RNN) based on Temporal Convolution Network (TCN) and Graph Convolution Network (GCN), constructed our Temporal Action Detection Net (TAD-Net), realized real-time shop-floor production action detection.

Files

confuseMatrix1.csv

Files (145.7 MB)

Name Size Download all
Checksum: md5:4afb207cbcb25747a6a498a5ceb98c6f

PID: http://hdl.handle.net/11304/734405b6-2e67-471e-807b-f6c3ad76884c
6.6 kB Preview Download
Checksum: md5:db601b78791cf447aebfea544a666fcd

PID: http://hdl.handle.net/11304/5938add7-de8e-4b9f-8ce7-1461dd7645f2
108.7 MB Download
Checksum: md5:d67758a5d6e26b1c7b502c9c710bf193

PID: http://hdl.handle.net/11304/8e52f1e3-0983-4b8e-ae3f-d4b5dfaf797e
37.0 MB Download
Checksum: md5:44fdd80ed94cad255bdc276eea049c2e

PID: http://hdl.handle.net/11304/a94b004b-96f6-451c-9fb7-4369a1b11cd6
34.7 kB Download

Additional details

Identifiers

B2SHARE Legacy Record ID
532a2466eeaf416c8aa728dcceb4530c
B2SHARE Legacy Record ID
d731510f5bce4f6d8b075df6e84af00e

InGRID metadata

Access
Freely accessible for non-commercial use
Data providers
Qing Hong
Guidelines for use available
True
Indicators available
True
Search or browse function available online
True
Text documents available
True