StepSTEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)
Stars: ✭ 196 (+33.33%)
HakeHAKE: Human Activity Knowledge Engine (CVPR'18/19/20, NeurIPS'20)
Stars: ✭ 132 (-10.2%)
M PactA one stop shop for all of your activity recognition needs.
Stars: ✭ 85 (-42.18%)
Tsn PytorchTemporal Segment Networks (TSN) in PyTorch
Stars: ✭ 895 (+508.84%)
MTL-AQAWhat and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment [CVPR 2019]
Stars: ✭ 38 (-74.15%)
Mmaction2OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Stars: ✭ 684 (+365.31%)
TimeceptionTimeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)
Stars: ✭ 153 (+4.08%)
ActionvladActionVLAD for video action classification (CVPR 2017)
Stars: ✭ 217 (+47.62%)
I3d finetuneTensorFlow code for finetuning I3D model on UCF101.
Stars: ✭ 128 (-12.93%)
C3d KerasC3D for Keras + TensorFlow
Stars: ✭ 171 (+16.33%)
DIN-Group-Activity-Recognition-BenchmarkA 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.
Stars: ✭ 26 (-82.31%)
Squeeze-and-Recursion-Temporal-GatesCode 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".
Stars: ✭ 62 (-57.82%)
Movienet ToolsTools for movie and video research
Stars: ✭ 113 (-23.13%)
Hake ActionAs a part of the HAKE project, includes the reproduced SOTA models and the corresponding HAKE-enhanced versions (CVPR2020).
Stars: ✭ 72 (-51.02%)
glimpse cloudsPytorch implementation of the paper "Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points", F. Baradel, C. Wolf, J. Mille , G.W. Taylor, CVPR 2018
Stars: ✭ 30 (-79.59%)
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
Stars: ✭ 172 (+17.01%)
DEAR[ICCV 2021 Oral] Deep Evidential Action Recognition
Stars: ✭ 36 (-75.51%)
Tdn[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition
Stars: ✭ 72 (-51.02%)
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
Stars: ✭ 218 (+48.3%)
Robust-Deep-Learning-PipelineDeep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data. Human Activity Recognition Challenge. Springer SIST (2020)
Stars: ✭ 20 (-86.39%)
MmactionAn open-source toolbox for action understanding based on PyTorch
Stars: ✭ 1,711 (+1063.95%)
TddTrajectory-pooled Deep-Convolutional Descriptors
Stars: ✭ 99 (-32.65%)
Fight detectionReal time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition
Stars: ✭ 65 (-55.78%)
T3dTemporal 3D ConvNet
Stars: ✭ 97 (-34.01%)
Resgcnv1ResGCN: an efficient baseline for skeleton-based human action recognition.
Stars: ✭ 50 (-65.99%)
3d Resnets3D ResNets for Action Recognition
Stars: ✭ 95 (-35.37%)
Okutama ActionOkutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection
Stars: ✭ 36 (-75.51%)
Video Dataset Loading PytorchGeneric PyTorch Dataset Implementation for Loading, Preprocessing and Augmenting Video Datasets
Stars: ✭ 92 (-37.41%)
Hcn Prototypeloss PytorchHierarchical Co-occurrence Network with Prototype Loss for Few-shot Learning (PyTorch)
Stars: ✭ 17 (-88.44%)
Two Stream Action RecognitionUsing two stream architecture to implement a classic action recognition method on UCF101 dataset
Stars: ✭ 705 (+379.59%)
Temporal Shift Module[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
Stars: ✭ 1,282 (+772.11%)
MultiverseDataset, 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.
Stars: ✭ 131 (-10.88%)
Video ClassificationTutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Stars: ✭ 543 (+269.39%)
SenseEnhance your application with the ability to see and interact with humans using any RGB camera.
Stars: ✭ 522 (+255.1%)
Gluon CvGluon CV Toolkit
Stars: ✭ 5,001 (+3302.04%)
Vidvrd HelperTo keep updates with VRU Grand Challenge, please use https://github.com/NExTplusplus/VidVRD-helper
Stars: ✭ 81 (-44.9%)
Two Stream PytorchPyTorch implementation of two-stream networks for video action recognition
Stars: ✭ 428 (+191.16%)
Keras Kinetics I3dkeras implementation of inflated 3d from Quo Vardis paper + weights
Stars: ✭ 116 (-21.09%)
Realtime Action RecognitionApply 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 !!!)
Stars: ✭ 417 (+183.67%)
DapsThis repo allocate DAPs code of our ECCV 2016 publication
Stars: ✭ 74 (-49.66%)
Action RecognitionExploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.
Stars: ✭ 129 (-12.24%)
ModelfeastPytorch model zoo for human, include all kinds of 2D CNN, 3D CNN, and CRNN
Stars: ✭ 116 (-21.09%)