157 Open source projects that are alternatives of or similar to Awesome Activity Prediction

STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)

A curated list of action recognition and related area resources

HAKE: Human Activity Knowledge Engine (CVPR'18/19/20, NeurIPS'20)

A collection of recent video understanding datasets, under construction!

A one stop shop for all of your activity recognition needs.

HAKE-Action in PyTorch

Temporal Segment Networks (TSN) in PyTorch

What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment [CVPR 2019]

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Temporal Segments LSTM and Temporal-Inception for Activity Recognition

Timeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)

ActionVLAD for video action classification (CVPR 2017)

TensorFlow code for finetuning I3D model on UCF101.

C3D for Keras + TensorFlow

A new codebase for Group Activity Recognition. It contains codes for ICCV 2021 paper: Spatio-Temporal Dynamic Inference Network for Group Activity Recognition and some other methods.

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

Code for : [Pattern Recognit. Lett. 2021] "Learn to cycle: Time-consistent feature discovery for action recognition" and [IJCNN 2021] "Multi-Temporal Convolutions for Human Action Recognition in Videos".

temporal action detection with SSN

Tools for movie and video research

As a part of the HAKE project, includes the reproduced SOTA models and the corresponding HAKE-enhanced versions (CVPR2020).

Pytorch implementation of the paper "Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points", F. Baradel, C. Wolf, J. Mille , G.W. Taylor, CVPR 2018

Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data

[ICCV 2021 Oral] Deep Evidential Action Recognition

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

Comprehensive, latest, and deployable video deep learning algorithm, including video recognition, action localization, and temporal action detection tasks. It's a high-performance, light-weight codebase provides practical models for video understanding research and application

Deep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data. Human Activity Recognition Challenge. Springer SIST (2020)

An open-source toolbox for action understanding based on PyTorch

EPIC-KITCHENS-55 baselines for Action Recognition

Trajectory-pooled Deep-Convolutional Descriptors

Real time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition

Training Toolbox for Caffe

Temporal 3D ConvNet

ResGCN: an efficient baseline for skeleton-based human action recognition.

Detects Chinese traffic police commanding poses 检测中国交警指挥手势

3D ResNets for Action Recognition

Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

一些关于机器学习的学习资料与研究介绍

Generic PyTorch Dataset Implementation for Loading, Preprocessing and Augmenting Video Datasets

Video classification tools using 3D ResNet

Hierarchical Co-occurrence Network with Prototype Loss for Few-shot Learning (PyTorch)

Action recognition.基于C3D的视频动作识别

Skeleton-based Action Recognition Papers and Small Notes and Top 2 Leaderboard for NTU-RGBD

Video Classification based on PyTorch

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

Explore Action Recognition

Dataset, code and model for the CVPR'20 paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction". And for the ECCV'20 SimAug paper.

🍴 Annotations for the EPIC KITCHENS-55 Dataset.

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

Enhance your application with the ability to see and interact with humans using any RGB camera.

Gluon CV Toolkit

To keep updates with VRU Grand Challenge, please use https://github.com/NExTplusplus/VidVRD-helper

PyTorch implementation of two-stream networks for video action recognition

keras implementation of inflated 3d from Quo Vardis paper + weights

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

This repo allocate DAPs code of our ECCV 2016 publication

Skeleton-based Action Recognition

Exploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.

Pytorch model zoo for human, include all kinds of 2D CNN, 3D CNN, and CRNN