Convolutional neural network model for video classification trained on the Kinetics dataset.
The main features of deepmind/kinetics-i3d are: Generative Models, Video Analysis, Video Representation Learning.
Open-source alternatives to deepmind/kinetics-i3d include: feichtenhofer/twostreamfusion — Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016. yjxiong/temporal-segment-networks — Code & Models for Temporal Segment Networks (TSN) in ECCV 2016. facebookresearch/video-nonlocal-net — Non-local Neural Networks for Video Classification. facebookresearch/slowfast — SlowFast is a PyTorch video understanding framework and spatiotemporal neural network library. It serves as a toolset… facebookresearch/jepa — This is a PyTorch self-supervised learning framework designed to train models that learn visual representations from… ajabri/videowalk.
Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.
Non-local Neural Networks for Video Classification
SlowFast is a PyTorch video understanding framework and spatiotemporal neural network library. It serves as a toolset for video action recognition, enabling the training and evaluation of models designed to classify complex activities and objects within video sequences. The framework is distinguished by its use of dual-pathway spatiotemporal sampling to capture both slow and fast motions. It supports self-supervised video learning for pre-training models on unlabeled data and employs multigrid spatiotemporal training to optimize learning across multiple spatial and temporal resolutions. The
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016