zs's repositories
action_recognition
This repository is used to classify actions in videos to different classes. It has been tested on KTH and hollywood datasets.
BossSensor
Hide screen when boss is approaching.
caffe-yolo
YOLO (Real-Time Object Detection) in caffe
Corel5K
这是Corel5K图像集,共包含科雷尔(Corel)公司收集整理的5000幅图片,故名:Corel5K,童鞋们可用于科学图像实验:分类、检索等。Corel5k数据集是图像实验的事实标准数据集。请勿用于商业用途。私底下学习交流使用。 Corel图像库是科雷尔(Corel)公司收集整理的较为丰富的图像库涵盖多个主题。Corel图像库由若干个CD组成,每个CD包含100张大小相等的图像,可以转换成多种格式。每张CD代表一个语义主题,例如有公共汽车、恐龙、海滩等。 Corel5k自从被提出用于图像标注实验后,已经成为图像实验的标准数据集,被广泛应用于标注算法性能的比较。Corel5k由50张CD组成,包含50个语义主题。 Corel5k图像库通常被分成三个部分: 4000张图像作为训练集,500张图像作为验证集用来估计模型参数,其余500张作为测试集评价算法性能。使用验证集寻找到最优模型参数后4000张训练集和500张验证集混合起来组成新的训练集。 该图像库中的每张图片被标注1~5个标注词,训练集中总共有374个标注词,在测试集中总共使用了263个标注词。 童鞋们自己去提取相关低层视觉特征:Rgb Lab Hsv Sift Gist HOG等等。 童鞋们完成 svm knn adaboost 逻辑回归 随机森林 mimlsvm mimlknn mimlboost 自定义算法 等等多类与多标签实验吧。Go, ...
Deep-Compression-AlexNet
Deep Compression on AlexNet
dense_flow
OpenCV Implementation of different optical flow algorithms
Feature-Extraction
An example of extracting image features from VGG network on Caffe
gstreamer
Sample Code which I build
human-detector
Human Detection using HOG-Linear SVM in Python
libGraph
first project for test
multipathnet
A Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)
OpenCV-demo
This project contain some OpenCV demo that we use frequently.
Places205-VGGNet
Places205-VGGNet models for scene recognition
py_img_seg_eval
Evaluation metrics for image segmentation inspired by paper Fully Convolutional Networks for Semantic Segmentation
ROLO
ROLO is short for Recurrent YOLO, aimed at simultaneous object detection and tracking
shell
Shell Programming: some useful code and tutorial
torch-pastalog
A Torch interface for pastalog - simple, realtime visualization of neural network training performance
twostreamfusion
Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.
Video-Feature-Extraction
All steps of PCM including predictive encoding, feature extraction, quantization, lossless encoding using LZW and Arithmetic encoding, as well as decoding for a video with the help of OpenCV library using Python.
video-modeling
Optical flow prediction
VideoFeatureExtraction
various ways to extract features from video The Red Balloon
work
just for test