EPIC-KITCHENS-55 baselines for Action Recognition

🌱 Starter kit for working with the EPIC-KITCHENS-55 dataset for action recognition or anticipation

☕ EPIC-KITCHENS-55 dataset python library

Simple PyTorch Dataset for the EPIC-Kitchens-55 and EPIC-Kitchens-100 that handles frames and features (rgb, optical flow, and objects) for the Action Recognition and the Action Anticipation Tasks!

Epic Kitchens Object Detector and Feature Extractor using Faster-RCNN with Detectron2

Attribution (or visual explanation) methods for understanding video classification networks. Demo codes for WACV2021 paper: Towards Visually Explaining Video Understanding Networks with Perturbation.

Attention-based Temporal Binding Network

A video feature extractor using the epic fusion model

Various flavours of algorithms attempted to solve the EPIC Kitchens Challenge

Epic-kitchen video player

Lightning implementation of TA3N, the SOTA model for Unsupervised Action Domain Adaptation.

Multimodal version of SlowFast (Vision + Audio inputs)

Invariant Risk Minimization on EPIC KITCHEN ResNet 50 Features

This repo provides some filters for NeRF data preparation for the EPIC Kitchens Dataset. We will be releasing the dataset soon.