Action-LocalizationAction-Localization, Atomic Visual Actions (AVA) Dataset
Stars: ✭ 22 (-82.95%)
DepthKit-for-MaxA patch for using DepthKit volumetric videos in Max/MSP/Jitter
Stars: ✭ 21 (-83.72%)
ailia-modelsThe collection of pre-trained, state-of-the-art AI models for ailia SDK
Stars: ✭ 1,102 (+754.26%)
ARehabARehab is a free software for physical rehab, aided by augmented reality technologies and user tracking systems, such as Microsoft Kinect v2.
Stars: ✭ 20 (-84.5%)
gspca-kinect2Kinect2 Sensor Device Driver for Linux
Stars: ✭ 25 (-80.62%)
sanThe official PyTorch implementation of "Context Matters: Self-Attention for sign Language Recognition"
Stars: ✭ 17 (-86.82%)
MiCT-Net-PyTorchVideo Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone
Stars: ✭ 48 (-62.79%)
gzsl-odOut-of-Distribution Detection for Generalized Zero-Shot Action Recognition
Stars: ✭ 47 (-63.57%)
OpenDepthSensorOpen library to support Kinect V1 & V2 & Azure, RealSense and OpenNI-compatible sensors.
Stars: ✭ 61 (-52.71%)
sparsepropTemporal action proposals
Stars: ✭ 46 (-64.34%)
Openpose-based-GUI-for-Realtime-Pose-Estimate-and-Action-RecognitionGUI based on the python api of openpose in windows using cuda10 and cudnn7. Support body , hand, face keypoints estimation and data saving. Realtime gesture recognition is realized through two-layer neural network based on the skeleton collected from the gui.
Stars: ✭ 69 (-46.51%)
Dataset-REPAIRREPresentAtion bIas Removal (REPAIR) of datasets
Stars: ✭ 49 (-62.02%)
AzureKinectSampleSample Program for Azure Kinect Sensor SDK and Azure Kinect Body Tracking SDK
Stars: ✭ 55 (-57.36%)
Two-Stream-CNNTwo Stream CNN implemented in Keras using in skeleton-based action recognition with dataset NTU RGB+D
Stars: ✭ 75 (-41.86%)
MUSES[CVPR 2021] Multi-shot Temporal Event Localization: a Benchmark
Stars: ✭ 51 (-60.47%)
cpnetLearning Video Representations from Correspondence Proposals (CVPR 2019 Oral)
Stars: ✭ 93 (-27.91%)
bLVNet-TAMThe official Codes for NeurIPS 2019 paper. Quanfu Fan, Ricarhd Chen, Hilde Kuehne, Marco Pistoia, David Cox, "More Is Less: Learning Efficient Video Representations by Temporal Aggregation Modules"
Stars: ✭ 54 (-58.14%)
pose2actionexperiments on classifying actions using poses
Stars: ✭ 24 (-81.4%)
Vridge.KinectUsing the Kinect sensor with RIftcat/Vridge has head and hands trackers.
Stars: ✭ 18 (-86.05%)
temporal-sslVideo Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.
Stars: ✭ 46 (-64.34%)
TCEThis repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).
Stars: ✭ 51 (-60.47%)
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 (-51.94%)
TA3N[ICCV 2019 Oral] TA3N: https://github.com/cmhungsteve/TA3N (Most updated repo)
Stars: ✭ 45 (-65.12%)
adascan-publicCode for AdaScan: Adaptive Scan Pooling (CVPR 2017)
Stars: ✭ 43 (-66.67%)
MTL-AQAWhat and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment [CVPR 2019]
Stars: ✭ 38 (-70.54%)
KinectXbox360-UE4kinect Xbox 360 sdk 1.8 Plugin for Unreal Engine 4
Stars: ✭ 43 (-66.67%)
DepthKit-A-Frame🎥 An A-Frame component for rendering DepthKit volumetric videos in WebVR
Stars: ✭ 34 (-73.64%)
torch-lrcnAn implementation of the LRCN in Torch
Stars: ✭ 85 (-34.11%)
ViCC[WACV'22] Code repository for the paper "Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting", https://arxiv.org/abs/2106.10137.
Stars: ✭ 33 (-74.42%)
KinectUtilThis project solves the problem of mismatching between rgb camera and depth camera of Kinect camera. And we can get higher quality point cloud model than Kinect itself. We solve the problem by first using both DLT and Zhangzhengyou‘s checkerboard to calibrate the camera, and then applying the calibrated parameters to project and re-project from…
Stars: ✭ 28 (-78.29%)
conv3d-video-action-recognitionMy experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves result…
Stars: ✭ 50 (-61.24%)
video repres mascode for CVPR-2019 paper: Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
Stars: ✭ 63 (-51.16%)
MSAFOffical implementation of paper "MSAF: Multimodal Split Attention Fusion"
Stars: ✭ 47 (-63.57%)
Pose2vecA Repository for maintaining various human skeleton preprocessing steps in numpy and tensorflow along with tensorflow model to learn pose embeddings.
Stars: ✭ 25 (-80.62%)
VideoTransformer-pytorchPyTorch implementation of a collections of scalable Video Transformer Benchmarks.
Stars: ✭ 159 (+23.26%)
DLCV2018SPRINGDeep Learning for Computer Vision (CommE 5052) in NTU
Stars: ✭ 38 (-70.54%)
Three-KinectronA Three.js plugin for rendering Kinectron feeds
Stars: ✭ 28 (-78.29%)
pushup-counter-appCount pushups from video/webcam. Tech stack: Keypoint detection, BlazePose, action recognition.
Stars: ✭ 48 (-62.79%)
C3D-tensorflowAction recognition with C3D network implemented in tensorflow
Stars: ✭ 34 (-73.64%)
UAV-Human[CVPR2021] UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
Stars: ✭ 122 (-5.43%)
OpenISSOpenISS -- a unified multimodal motion data delivery framework.
Stars: ✭ 22 (-82.95%)
TadTREnd-to-end Temporal Action Detection with Transformer. [Under review for a journal publication]
Stars: ✭ 55 (-57.36%)
temporal-binding-networkImplementation of "EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition, ICCV, 2019" in PyTorch
Stars: ✭ 95 (-26.36%)
KinectToVRKinectToVR EX (Official)
Stars: ✭ 163 (+26.36%)
Kinect2ToolboxCode for CVPR 2015 Paper Understanding Tools: Task-Oriented Object Modeling, Learning and Recognition.
Stars: ✭ 45 (-65.12%)
TCFPN-ISBATemporal Convolutional Feature Pyramid Network (TCFPN) & Iterative Soft Boundary Assignment (ISBA), CVPR '18
Stars: ✭ 40 (-68.99%)
tfvaegan[ECCV 2020] Official Pytorch implementation for "Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification". SOTA results for ZSL and GZSL
Stars: ✭ 107 (-17.05%)
GST-videoICCV 19 Grouped Spatial-Temporal Aggretation for Efficient Action Recognition
Stars: ✭ 40 (-68.99%)
ntu-xNTU-X, which is an extended version of popular NTU dataset
Stars: ✭ 55 (-57.36%)
Robust-Deep-Learning-PipelineDeep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data. Human Activity Recognition Challenge. Springer SIST (2020)
Stars: ✭ 20 (-84.5%)
synse-zslOfficial PyTorch code for the ICIP 2021 paper 'Syntactically Guided Generative Embeddings For Zero Shot Skeleton Action Recognition'
Stars: ✭ 14 (-89.15%)
dynamic-images-for-action-recognitionA public Python implementation for generating Dynamic Images introduced in 'Dynamic Image Networks for Action Recognition' by Bilen et al.
Stars: ✭ 27 (-79.07%)