WANG XIN's repositories
video-nonlocal-net
Non-local Neural Networks for Video Classification
abd_ver1.0
this is a program
anomaly-event-detection
An implementation of paper Detecting anomalous events in videos by learning deep representations of appearance and motion on python, opencv and tensorflow. This paper uses the stacked denoising autoencoder for the the feature training on the appearance and motion flow features as input for different window size and using multiple SVM as a single classifier this is work under progress.
crowd-counting-MCNN
A very ugly unofficial implementation of CVPR2016 paper Single-Image Crowd Counting via Multi Column Convolutional Neural Network using tensorflow and keras
crowd-counting-scnn
This project is an implementation of the crowd counting model proposed in our CVPR 2017 paper - Switching Convolutional Neural Network(SCNN) for Crowd Counting. SCNN is an adaptation of the fully-convolutional neural network and uses an expert CNN that chooses the best crowd density CNN regressor for parts of the scene from a bag of regressors. This helps it tackle intra-scene crowd density variation and obtain SOTA results
csc411proj
Abnormal Behaviour Detection
dataset
The Open Images dataset
drn
Dilated Residual Networks
Frame-level-anomalies-in-videos
Frame level anomaly detection on videos using auto-encoders
graph-cnn.pytorch
Pytorch Implementation for Graph Convolutional Neural Networks
MachineLearning
Machine Learning in Action（机器学习实战-笔记）
My-TensorFlow-tutorials
This repo contains all of my TensorFlow tutorials
newHOJ3D
Histogram data analysis using data from 'View Invariant Human Action Recognition Using Histograms of 3D Joints'
Observation-Learning
Programs related to the project: Seeing to Learn
Pedestrian-Attributes
People Attributes Recognition, deep learning
Person-Attribute-Recognition-MarketDuke
A baseline model ( pytorch implementation ) for person attribute recognition task, training and testing on Market1501-attribute and DukeMTMC-reID-attribute dataset.
Person-Reidentification-System
Person Re-identification System based on Deep Residual Network with GUI.
pytorch-cifar
95.16% on CIFAR10 with PyTorch
SaCNN-CrowdCounting-Tencent_Youtu
Crowd Counting Via Scale-adaptive Convolutional Neural Network
temporal-segment-networks
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
tensorflow-mnist-tutorial
Sample code for "Tensorflow and deep learning, without a PhD" presentation and code lab.
tf-faster-rcnn
Tensorflow Faster RCNN for Object Detection
tf-pose-estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
tvnet
End-to-End Learning of Motion Representation for Video Understanding
videopred
Common Video Prediction Architectures