OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

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.

Inflated i3d network with inception backbone, weights transfered from tensorflow

Transforms for video datasets in pytorch

Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)

Video Platform for Action Recognition and Object Detection in Pytorch

I3D and 3D-ResNets in PyTorch

Pytorch model zoo for human, include all kinds of 2D CNN, 3D CNN, and CRNN

TensorFlow code for finetuning I3D model on UCF101.

PyTorch implementation of Multi-modal Dense Video Captioning (CVPR 2020 Workshops)

A one stop shop for all of your activity recognition needs.

Sign Language Recognition for Deaf People

Rewriting the I3D blender addon from scratch and adding long-sought community features

Video Classification based on PyTorch

I3D features extractor with resnet50 backbone

Blender add-on for importing Farming Simulator 25 .i3d files with all details such as materials, primary and secondary UVs, vertex colors and custom shader properties. Includes both re-exportable and PBR-ready debug materials to get the full material look also in Blender (dirt, moss, snow overlays, additional surface details, clear coat...).

[CVPR2020] Clean-Label Backdoor Attacks on Video Recognition Models

I3D implemetation in Keras + video preprocessing + visualization of results

动作识别(Action Recognition)常见模型的Pytorch实现