144 Open source projects that are alternatives of or similar to Mmaction

A curated list of action recognition and related area resources

[CVPR 2021] Multi-shot Temporal Event Localization: a Benchmark

End-to-end Temporal Action Detection with Transformer. [Under review for a journal publication]

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

[ICCV 2021 Oral] Deep Evidential Action Recognition

Temporal Segment Networks (TSN) in PyTorch

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

temporal action detection with SSN

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

A collection of recent video understanding datasets, under construction!

A curated publication list on weakly-supervised temporal action localization

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

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.

ActionVLAD for video action classification (CVPR 2017)

Tools for movie and video research

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

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

Paper list of activity prediction and related area

temporal action detection: benchmark results, features download etc.

TensorFlow code for finetuning I3D model on UCF101.

This repo allocate DAPs code of our ECCV 2016 publication

A Pytorch implemention for some state-of-the-art models for" Temporally Language Grounding in Untrimmed Videos"

Gluon CV Toolkit

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 !!!)

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

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

Temporal Segments LSTM and Temporal-Inception for Activity Recognition

Action recognition using soft attention based deep recurrent neural networks

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

3D ResNets for Action Recognition

PyTorch implementation of two-stream networks for video action recognition

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

This repository host the code for real-time action detection paper

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

Skeleton-based Action Recognition

EPIC-KITCHENS-55 baselines for Action Recognition

3D ResNets for Action Recognition (CVPR 2018)

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

Video Classification based on PyTorch

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

Useful Toolbox for Anomaly Detection

Training Toolbox for Caffe

Implementation for Bottom-Up Temporal Action Localization with Mutual Regularization (ECCV2020)

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

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

Using deep learning to perform action recognition in the sport of tennis.

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

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

Implementation of "Slow-Fast Auditory Streams for Audio Recognition, ICASSP, 2021" in PyTorch

CP-360-Weakly-Supervised-Saliency

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

Identifying Visible Actions in Lifestyle Vlogs

基于kinect 的人体 动作识别

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

Video classification tools using 3D ResNet

ICCV 19 Grouped Spatial-Temporal Aggretation for Efficient Action Recognition

Deep Learning for Computer Vision (CommE 5052) in NTU

NTU-X, which is an extended version of popular NTU dataset

An implementation of the LRCN in Torch

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