Stars
Efficient 3D Backbone Network for Temporal Modeling
PyTorch implementation of a collections of scalable Video Transformer Benchmarks.
[ICCV 2023] Official PyTorch implementation of "Rethinking Mobile Block for Efficient Attention-based Models"
[CVPR 2023] Official repository of paper titled "Fine-tuned CLIP models are efficient video learners".
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
Implementations of Transformers for Video
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Use of Attention Gates in a Convolutional Neural Network / Medical Image Classification and Segmentation
PyTorch demo code for "Spatial-Temporal Pyramid Based Convolutional Neural Network for Action Recognition"
The Pytorch code of the TEA module (Temporal Excitation and Aggregation for Action Recognition)
Code for our CVPR 2021 Paper "Self-Supervised Learning for Semi-Supervised Temporal Action Proposal".
PyTorch implementation of "SlowFast Networks for Video Recognition".
Two-Stream CNNs to Recognize Actions in Videos (with Early Fusion and Late Fusion)
Make video classification on UCF101 using CNN and RNN based on Pytorch framework.
Simple C3D (3D convolutional Network) in Pytorch
PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
Using two stream architecture to implement a classic action recognition method on UCF101 dataset
Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE
An open-source toolbox for action understanding based on PyTorch
Attention Branch Network (CIFAR100, ImageNet models)
OpenMMLab Detection Toolbox and Benchmark