Rangozhang

VideoCaption

Video captioning using LSTM and CNN. This is the Visual Learning project done by Rui Zhang, Yujia Huang and Yu Zhang

Action_recognition_scripts_UCF101

Some scripts used for action recognition on UCF101 dataset

Socket_imageTransfer

image_sender & image_receiver

SparseBatchSfM

Implementation of a sparse batch reconstruction project by Yilin Yang, Yu Zhang

ActionRecognitionBaseline

Action Recognition Baseline with CNN+RNN

convexHull-shortestPath

Matlab code for convex hull and shortest path searching based on convex hull algorithm

Graph_cut

A simple implementation of graph cut algorithm with color and gradient constraints.

SurfaceNormalUsingFCN

Visual Learning, torch

datasources

Torch datasources

LearningtoLearnUsingRL

This is a workspace for meta-learning methods using Reinforcement learning

doc_helper

helpers for course materials

leatherPatternIdentification

This is a small implementation of leather pattern identification using simple SIFT and color information

LSTMTest

A toy model for testing LSTM

ImageClassification-Localization

Visual Learning, caffe

Twitch-plays-LSD-neural-net

caffe-lstm

LSTM implementation on Caffe

clouddream

Deepdreaming in the clouds: A Dockerized deepdream Guide

cnn-vis

Use CNNs to generate images

cockpit_demo

Cockpit project demo

deepdream

DeepLab-Context

LocalSlidePoisson

mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, and more

neuraltalk2

Efficient Image Captioning code in Torch, runs on GPU

rangozhang.github.io

Zhang, Yu 's blog

simple-neural-network

A simple Python script showing how the backpropagation algorithm works.