Computer Vision Toolbox Model for R(2+1)D Video Classification

Pretrained R(2+1)D model for Video Classification
Updated 13 Dec 2023
The model is pre-trained on the Kinetics-400 dataset that contains 18 Spatio-Temporal residual layers as the backbone architecture. Out-of-the-box video classification support for 400 action classes from Kinetics-400 dataset.
MATLAB Release Compatibility
Created with R2021b
Compatible with R2021b to R2024a
Platform Compatibility
Windows macOS (Apple silicon) macOS (Intel) Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!