PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
-
Updated
Dec 27, 2023 - Python
#
r2plus1d
Here are 6 public repositories matching this topic...
Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.
raft audio-features parallel pytorch feature-extraction resnet vit optical-flow clip multi-gpu i3d s3d video-features vggish r2plus1d swin visual-features timm ig65m laion
-
Updated
Jan 31, 2025 - Python
Human action classification system with pose-based (MediaPipe) and video-based (3D CNN) models. Features 100+ architectures for real-time pose classification and temporal models pretrained on UCF-101/HMDB51. Applications include autonomous vehicles, video surveillance, and action recognition research.
computer-vision deep-learning pytorch convolutional-neural-networks transfer-learning pose-estimation video-classification video-recognition human-action-recognition hmdb51 video-analysis ucf-101 r2plus1d mobilenetv3 mediapipe pose-classification video-classification-models timm real-time-inference r3d-18
-
Updated
Nov 21, 2025 - Python
A PyTorch implementation of R2Plus1D and C3D based on CVPR 2017 paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition" and CVPR 2014 paper "Learning Spatiotemporal Features with 3D Convolutional Networks"
-
Updated
Jun 15, 2019 - Python
Video Classification using R(2+1)D based on ResNet18 on UCF-101 dataset. PyTorch Implementation.
-
Updated
Mar 30, 2023 - Python
An implementation of R2plus1D and 3DMobileNets in pytorch for Action Classification
-
Updated
Nov 24, 2020 - Python
Improve this page
Add a description, image, and links to the r2plus1d topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the r2plus1d topic, visit your repo's landing page and select "manage topics."