hopeliu20160622

3d-pose-2d-keypoints

3d Human Pose Estimation from 2d Keypoints

AA-remotesensing-artificial-structures

Master's thesis development code

Activity-Recognition-skeleton-datasets

Skeleton data extracted from Kinect Activity Recognition Dataset

age_gender_classification

Multi-task learning,using CNN model to classify age and gender

AI4Animation

Bringing Characters to Life with Computer Brains in Unity

apollo

An open autonomous driving platform

articulated-animation

Code for Motion Representations for Articulated Animation paper

asen

attribute-aware-attention

Code for paper: Attribute-Aware Attention Model for Fine-grained Representation Learning

Robust-Motion-In-betweening-with-Conditioning

hopeliu20160622/3d-pose-2d-keypoints

3d Human Pose Estimation from 2d Keypoints

hopeliu20160622/age_gender_classification

Multi-task learning,using CNN model to classify age and gender

hopeliu20160622/awesome-deep-learning

A curated list of awesome Deep Learning tutorials, projects and communities.

hopeliu20160622/awesome-very-deep-learning

A curated list of papers and code about very deep neural networks

hopeliu20160622/Character_Animation

A Re-implementation of the paper "A Deep Learning Framework for Character Motion Synthesis and Editing"

hopeliu20160622/Cleaned-Traffic-Light-Datasets

Aggregated and cleaned various datasets on traffic light (TL) detection, including ApolloScape, Bosch Small TL Dataset, WPI TL Dataset, and LISA TL Dataset. Copyrights belong to the owners of the respective datasets.

hopeliu20160622/deep-learning-traffic-lights

Code and files of the deep learning model used to win the Nexar Traffic Light Recognition challenge

hopeliu20160622/deep-learning-traffic-lights-1

Keras solution for recognizing traffic light from dash camera

hopeliu20160622/DropoutUncertaintyExps

Experiments used in "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning"

hopeliu20160622/dtw-features-cnn

Introducing Local Distance-based Features to Temporal Convolutional Neural Networks (ICFHR 2018)

hopeliu20160622/Finetuning-Tensorflow

Fine tuning MobileNet for hand gestures recognition using tensorflow.

hopeliu20160622/furniture

Galvanize capstone project - Furniture seeker

hopeliu20160622/Furniture-Classification

iMaterialist Challenge (Furniture) at FGVC5, Kaggle Competition

hopeliu20160622/hopeliu20160622.github.io

hopeliu20160622/ITSDC-Udacity-Traffic-Light-Classifier

Udacity's Intro to Self driving Car ND Classification Project

hopeliu20160622/kaggle_dstl_submission

Code for a winning model (3 out of 419) in a Dstl Satellite Imagery Feature Detection challenge

hopeliu20160622/LeetCode-1

正确的姿势，学习的态度来刷 LeetCode：高效的代码、简洁的注释、精炼的总结。

hopeliu20160622/MobileNetV2

A Tensorflow implementation of MobileNet V2

hopeliu20160622/MobileNetV2-pytorch

Impementation of MobileNetV2 in pytorch

hopeliu20160622/MS-TLD

In order to solve tracking failures caused by objects deformation, occlusion and fast motion, a novel algorithm called MS-TLD which under the Tracking-Learning-Detection framework is proposed. The algorithm reconstructs a new tracker with the scale-adaptive mean-shift method. By introducing color histogram features and scale-adaptive, the new tracker can track objects with deformation and fast moving. We establish a new tracking-detection feedback strategy—the inter-correction between tracker and detector. Therefore, the new algorithm has better robustness when objects are occluded. We use TB-50 standard dataset to verify and evaluate our method. The experimental results show that the proposed algorithm can overcome the tracking failures caused by objects with deformation, occlusion, fast motion, as well as background clutters, and has better tracking accuracy and robustness compared with TLD and other 3 classic algorithms.

hopeliu20160622/pytorch-multi-label-classifier

A pytorch implemented classifier for Multiple-Label classification

hopeliu20160622/QuaterNet

Proposes neural networks that can generate animation of virtual characters for different actions.

hopeliu20160622/Remote-Sensing-Indices-Derivation-Tool

Calculate spectral remote sensing indices from satellite imagery

hopeliu20160622/Sketch-Based-Image-Retrieval

hopeliu20160622/Traffic-Signals-Detect-Chinese

Train a model to detect Chinese traffic signs and signals with tensorflow object detection API

hopeliu20160622/transferlearning-tutorial

《迁移学习简明手册》LaTex源码

hopeliu20160622/TrustScore

To Trust Or Not To Trust A Classifier. A measure of uncertainty for any trained (possibly black-box) classifier which is more effective than the classifier's own implied confidence (e.g. softmax probability for a neural network).