hzhang57

dense_flow

Tools to extract dense optical flow from videos, based on OpenCV

TrajectoryNet-1

Deep-Learning-Tricks

Enumerate diverse machine learning training tricks.

dense-flow

Dense Optical Flow extraction rewritten from https://github.com/wanglimin/dense_flow

dense_flow-1

dense flow(yjxiong) for opencv-3.1

FCIS

Fully Convolutional Instance-aware Semantic Segmentation

hdrnet

An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017

heatmap

Python package to combine image and heatmap

kinetics-i3d

Convolutional neural network model for video classification trained on the Kinetics dataset.

NBA-Player-Movements

🏀 Visualization of NBA games from raw SportVU data logs

PennAction

Penn Action Dataset, with human body joints for all frames!

pyflow

Fast, accurate and easy to run dense optical flow with python wrapper

Python-optical-flow-tracking

Using Optical Flow for Detection Motion object.

ResNeXt

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

RNN-TrajModel

The source of the IJCAI2017 paper "Modeling Trajectory with Recurrent Neural Networks"

st-resnet

Code release for "Spatiotemporal Residual Networks for Video Action Recognition", NIPS16 & "Spatiotemporal Multiplier Networks for Video Action Recognition", CVPR17.

STWalk

Implementation of "STWalk: Learning Trajectory Representations in Temporal Graphs"

TCNActionRecognition

Skeleton based action recognition models with TCN variants for learning interpretable representation.

TraClusAlgorithm

This is an implementation for TraClus algorithm in Java. A GUI was added.

trajectory

Trajectory Outlier Detection Library

trajectory2vec

code for "Trajectory clustering via deep representation learning"

TrajectoryClustering

This application written in Python is capable of fully automatic clustering of 2D trajectory data.

TrajectoryTracking

Trajectory Tracking Project