Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data

A CPU based video summarization and classification tool. Extracts every movement out of a given video, aggregates the extracted changes into movement layers, which can be exported or further analysed and classified..

Reads a video stream using ffmpeg libraries and converts into OpenCV Mat object

Common Wrapper/Interface around various video reading/writing tools to make video reading stable, consistent, and super easy around different systems and OS.

CeLux: High-performance video processing for Python, powered by FFmpeg and PyTorch. Ultra-fast video decoding directly to tensors with CPU and CUDA support.

VideoUltimate is a .NET Video Reader and a .NET Video Thumbnailer which can read any video file format on the planet. It supports .NET 5.0+ or .NET Core 2.0+ and .NET Framework 4.7.2+ web/console/desktop applications.

Various video readers for PyTorch models training and a benchmark

PyAV-based video reader plugin for Napari

Python interface implementation of classes for reading frame from video and folder