LintelA Python module to decode video frames directly, using the FFmpeg C API.
AlphactionSpatio-Temporal Action Localization System
Ms G3d[CVPR 2020 Oral] PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition"
Action recognition zooCodes for popular action recognition models, verified on the something-something data set.
Ican[BMVC 2018] iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection
PaddlevideoComprehensive, 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
Ta3n[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)
ActionvladActionVLAD for video action classification (CVPR 2017)
Ig65m PytorchPyTorch 3D video classification models pre-trained on 65 million Instagram videos
StepSTEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)
MmskeletonA OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.
AmassData preparation and loader for AMASS
Hidden Two StreamCaffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
VipVideo Platform for Action Recognition and Object Detection in Pytorch
Hand pose actionDataset and code for the paper "First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations", CVPR 2018.
Video CaffeVideo-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
Dd NetA lightweight network for body/hand action recognition
TimeceptionTimeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)
UntrimmednetWeakly Supervised Action Recognition and Detection
HakeHAKE: Human Activity Knowledge Engine (CVPR'18/19/20, NeurIPS'20)
Action RecognitionExploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.
MmactionAn open-source toolbox for action understanding based on PyTorch
I3d finetuneTensorFlow code for finetuning I3D model on UCF101.
ModelfeastPytorch model zoo for human, include all kinds of 2D CNN, 3D CNN, and CRNN
TddTrajectory-pooled Deep-Convolutional Descriptors
M PactA one stop shop for all of your activity recognition needs.
Vidvrd HelperTo keep updates with VRU Grand Challenge, please use https://github.com/NExTplusplus/VidVRD-helper
DapsThis repo allocate DAPs code of our ECCV 2016 publication
Tdn[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition
Hake ActionAs a part of the HAKE project, includes the reproduced SOTA models and the corresponding HAKE-enhanced versions (CVPR2020).
Fight detectionReal time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition
Resgcnv1ResGCN: an efficient baseline for skeleton-based human action recognition.
Okutama ActionOkutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection
Mmaction2OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark