A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain

Inflated i3d network with inception backbone, weights transfered from tensorflow

Code for I3D Feature Extraction

I3D features extractor with resnet50 backbone

I3D Nonlocal ResNets in Pytorch

Real-world Anomaly Detection in Surveillance Videos- pytorch Re-implementation

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.

[ECCV 2024] ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video

Extract frames from videos in Python using OpenCV.

DNS-Blocklists: For a better internet - keep the internet clean!

Abnormal Human Behaviors Detection/ Road Accident Detection From Surveillance Videos/ Real-World Anomaly Detection in Surveillance Videos/ C3D Feature Extraction

Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.

save a video / batch of videos as images

Efficient 3D Backbone Network for Temporal Modeling

An instruction to 1) download the Kinetics-400/Kinetics-600, 2) resize the videos, and 3) prepare annotations.