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.

Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)

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

Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"

Feature Extractor module for videos using the PySlowFast framework

Motion energy features from video

deep_video_extraction is a powerful repository designed to extract deep feature representations from video inputs using pre-trained models. With support for both visual and aural features from videos. Additionally, you can process audio separately by converting it into spectrograms.

A simple motion extraction for video inspired from posy

Video feature extractor in PyTorch.

Repository with code to extract different features from video and images.

Video Extractor to h5 File Format