There are 50 repositories under video-classification topic.
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Video classification tools using 3D ResNet
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Papers, code and datasets about deep learning and multi-modal learning for video analysis
Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
Video Classification using 2 stream CNN
To classify video into various classes using keras library with tensorflow as back-end.
[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)
Tutorial about 3D convolutional network
Simplest and fastest image and text annotation tool.
[ICLR 2022] TAda! Temporally-Adaptive Convolutions for Video Understanding. This codebase provides solutions for video classification, video representation learning and temporal detection.
Explore Action Recognition
Implementation Code of the paper Optical Flow Guided Feature, CVPR 2018
Classify UCF101 videos using one frame at a time with a CNN(InceptionV3)
Exploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.
Easiest way of fine-tuning HuggingFace video classification models
Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification
CricShot10 is a video action recognition dataset consisting of 10 cricket batting shots. This dataset was developed using the videos from YouTube.
Sign Language Recognition for Deaf People
[Neurocomputing 2019] Fast and Robust Dynamic Hand Gesture Recognition via Key Frames Extraction and Feature Fusion
Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, debuted in ICLR 2022
Video Classification based on PyTorch
SoccerAct10 is a dataset which contains 10 different soccer actions. This dataset was developed using the videos from YouTube.
An unofficial implementation of TubeViT in "Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning"
A Comprehensive Tutorial on Video Modeling
Surveillance Perspective Human Action Recognition Dataset: 7759 Videos from 14 Action Classes, aggregated from multiple sources, all cropped spatio-temporally and filmed from a surveillance-camera like position.
Deepfakes Video classification via CNN, LSTM, C3D and triplets [IWBF'20]
Make video classification on UCF101 using CNN and RNN based on Pytorch framework.