video-features

There are 1 repository under video-features topic.

v-iashin / video_features
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.
audio-features clip feature-extraction i3d ig65m laion multi-gpu optical-flow parallel pytorch r2plus1d raft resnet s3d swin timm vggish video-features visual-features vit
Language:Python 456
v-iashin / SpecVQGAN
Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)
transformer vqvae gan pytorch audio-generation video-features melgan multi-modal video-understanding vggsound vas bmvc evaluation-metrics audio video
Language:Jupyter Notebook 323
BMT
v-iashin / BMT
Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)
activitynet-captions audio bi-modal-encoder bi-modal-transformer bmt bmvc bmvc20 dense-video-captioning i3d multimodal-fusion proposal-generator pytorch temporal-action-proposals transformer video video-features
Language:Jupyter Notebook 222
linjieli222 / HERO_Video_Feature_Extractor
Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"
pytorch slowfast resnet video-features vision-and-language
Language:Python 91
tridivb / slowfast_feature_extractor
Feature Extractor module for videos using the PySlowFast framework
slowfast-networks feature-extraction video-features
Language:Python 74
gallantlab / pymoten
Motion energy features from video
neuroscience computer-vision gabor-filters video-features spatiotemporal-energy-model
Language:Python 27
theopsall / deep_video_extraction
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.
feature-extraction deep-feature-extraction video-features audio-visual-features audio-processing computer-vision deep-learning object-recognition pre-trained-model pytorch spectogram video-processing multimedia-analysis
Language:Python 9
Chocochip101 / Video-Feature-Extractor
Video Extractor to h5 File Format
cnn video-features h5py h5 numpy
Language:Python 7
ricoms / video_image_features
Repository with code to extract different features from video and images.
image-processing mediaeval audio scikit-image python opencv video feature-extraction video-features
Language:Python 7
Tramac / awesome-video-feature-extractor
Video feature extractor in PyTorch.
video-features pretrained-networks pytorch
Language:Python 7
mochiron-desu / VideoMotionExtractor
A simple motion extraction for video inspired from posy
cv2 motion-extraction numpy python python3 video video-features
Language:Python 0