cmc370's repositories
Spatial-Temporal-Networks
Spatial Temporal_Networks_In Mental-Retardation-Recognition
Action_Recognition_Keras
This project is about the implementation of a hybrid CNN-LSTM architecture to classify different classes of videos.
C3D-Tensorflow-slim
A simple Tensorflow code for C3D
ESS_MS_G3D
Skeleton-Based Assessment of Severe Mental Retardation
PyTorch-Networks
Pytorch implementation of cnn network
Pytorch-Video-Classification
Make video classification on UCF101 using CNN and RNN based on Pytorch framework.
two-stream-action-recognition
Using two stream architecture to implement a classic action recognition method on UCF101 dataset
video-action-recognition
视频动作识别，基于C3D网络构建
3D-ConvNets-for-Action-Recognition
3D ConvNets for Action Recognition with Keras (3d ResNet, 3d DenseNet, 3d Inception, C3D, 3d dense resnet)
Action_recognition
This is an implementation of action recognition algorithm based on scene using CNN+LSTM
AlphaPose
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
daily-paper-computer-vision
记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文
MVision
机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶
qpu_code
Quaternion Product Units for Deep Learning on 3D Rotation Groups
spikingjelly
SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.
twostreamfusion
Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.
video-classification
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
video-dataset-preprocess
code about preprocessing and dataloaders for video dataset including UCF101 and HMDB51 based on PyTorch
visual-chatgpt
Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models