GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → XiaoCode-er → Two-Stream-CNN

XiaoCode-er / Two-Stream-CNN

Licence: other
Two Stream CNN implemented in Keras using in skeleton-based action recognition with dataset NTU RGB+D

Programming Languages

python
139335 projects - #7 most used programming language

Labels

kerasaction-recognitionskeleton-data

Projects that are alternatives of or similar to Two-Stream-CNN

bLVNet-TAM
The 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 (-28%)
Mutual labels:  action-recognition
ailia-models
The collection of pre-trained, state-of-the-art AI models for ailia SDK
Stars: ✭ 1,102 (+1369.33%)
Mutual labels:  action-recognition
gzsl-od
Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
Stars: ✭ 47 (-37.33%)
Mutual labels:  action-recognition
MUSES
[CVPR 2021] Multi-shot Temporal Event Localization: a Benchmark
Stars: ✭ 51 (-32%)
Mutual labels:  action-recognition
Action-Localization
Action-Localization, Atomic Visual Actions (AVA) Dataset
Stars: ✭ 22 (-70.67%)
Mutual labels:  action-recognition
Squeeze-and-Recursion-Temporal-Gates
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".
Stars: ✭ 62 (-17.33%)
Mutual labels:  action-recognition
MiCT-Net-PyTorch
Video Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone
Stars: ✭ 48 (-36%)
Mutual labels:  action-recognition
pushup-counter-app
Count pushups from video/webcam. Tech stack: Keypoint detection, BlazePose, action recognition.
Stars: ✭ 48 (-36%)
Mutual labels:  action-recognition
Openpose-based-GUI-for-Realtime-Pose-Estimate-and-Action-Recognition
GUI 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 (-8%)
Mutual labels:  action-recognition
TCE
This repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).
Stars: ✭ 51 (-32%)
Mutual labels:  action-recognition
MSAF
Offical implementation of paper "MSAF: Multimodal Split Attention Fusion"
Stars: ✭ 47 (-37.33%)
Mutual labels:  action-recognition
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 (-56%)
Mutual labels:  action-recognition
dynamic-images-for-action-recognition
A public Python implementation for generating Dynamic Images introduced in 'Dynamic Image Networks for Action Recognition' by Bilen et al.
Stars: ✭ 27 (-64%)
Mutual labels:  action-recognition
VideoTransformer-pytorch
PyTorch implementation of a collections of scalable Video Transformer Benchmarks.
Stars: ✭ 159 (+112%)
Mutual labels:  action-recognition
UAV-Human
[CVPR2021] UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
Stars: ✭ 122 (+62.67%)
Mutual labels:  action-recognition
C3D-tensorflow
Action recognition with C3D network implemented in tensorflow
Stars: ✭ 34 (-54.67%)
Mutual labels:  action-recognition
MTL-AQA
What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment [CVPR 2019]
Stars: ✭ 38 (-49.33%)
Mutual labels:  action-recognition
Pose2vec
A Repository for maintaining various human skeleton preprocessing steps in numpy and tensorflow along with tensorflow model to learn pose embeddings.
Stars: ✭ 25 (-66.67%)
Mutual labels:  action-recognition
pose2action
experiments on classifying actions using poses
Stars: ✭ 24 (-68%)
Mutual labels:  action-recognition
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 (+42.67%)
Mutual labels:  action-recognition
View All Similar Projects ➔

Two-Stream-CNN implement in Keras

Two Stream CNN is proposed in SKELETON-BASED ACTION RECOGNITION WITH CONVOLUTIONAL NEURAL NETWORKS, which is used for skeleton-based action recognition. It maps a skeleton sequence to an image( coordinates x,y,z to image R,G,B ). And they specially designed skeleton transformer module to rearrange and select important skeleton joints automatically.

Requirments

  • Python3
  • Keras
  • h5py
  • matplotlib
  • numpy

Network Architecture

The network mainly consists of four modules which are Skeleton Transformer, ConvNet, Feature Fusion and Classification. The inputs of two stream are raw data(x, y, z) and frame difference respectively. As show below : Two Stream CNN

Usage

  1. function/data_generator.py : generate the inputs numpy array of two stream

  2. layers/transformer : the layer of Skeleton Transformer implement in Keras

  3. network/ : the fold has four flies with different feature fusion way

Result

model accuracy(cs)
base line 83.2%
my model 80.7%

Introduce attention mechanism to Skeleton Transformer module. Then, the accurancy can reach at 82.1%.

Contact

If you have any questions, please feel free to contact me.
Duohan Liang ([email protected])

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].