sdimple-chf's repositories
video_face_detect
视频流中人脸识别检测:从《都挺好》第一集视频中检测出现的人脸数并合并相同人的脸,统计露脸人数。
FCHD-Fully-Convolutional-Head-Detector
Code for FCHD - A fast and accurate head detector
rgcnn
Neural Recommender System from "Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks"
DeepLearningTutorials-1
Deep Learning与PyTorch入门实战视频教程
SPM_toolkit
Neural network toolkit for sentence pair modeling.
Age-and-Gender
同时识别年龄与性别
deep-learning-with-keras-notebooks
Jupyter notebooks for using & learning Keras
CASE
code for Truth Discovery by Claim and Source Embedding
atics_i
First module assignment for Advanced Topics In Computer Science course held at the "Roma Tre" University of Rome.
Tweets-Clustering-using-k-means
By clustering similar tweets together, we can generate a more concise and organized representation of the raw tweets, which will be very useful for many Twitter-based applications (e.g., truth discovery, trend analysis, search ranking, etc.)
Twitter-Truth-Discovery
Implemented a maximum likelihood algorithm in python which performs credibility analysis on clusters of similar tweets gathered from the Tweepy Twitter API
self-training-scikit-learn-PySpark
Semi-supervised method is a class of supervised learning techniques applied on a data with small amount of labeled and large amount of unlabeled data. Here, self-training method is applied to efficiently label unlabeled data. Effect of different parameters (probability threshold, unlabeled data ratio) are investigated versus the cost of human labeling. The model is developed in both sequential (with python) and distributed (with PySpark) systems. At the end, accuracy of the developed model is compared with label propagation model from Scikit-learn package.
graph-based-recommendation-system
building a recommendation system using graph search methodologies. We will be comparing these different approaches and closely observe the limitations of each.
Tweets-Clustering-KMeans
Implemented K-MEANS algorithm in Python using Jaccard distance as distance metric and analyzed various twitter based applications that involve truth discovery, trend analysis, search ranking.
KDEm
This repository includes data and code for the algorithm of Kernel Density Estimation from Multiple Sources (KDEm) proposed in a KDD'16 paper
Twitter-Truth-Discovery-1
Accurately ascertain both the correctness of each tweet and the reliability of each Twitter user.
truthfinder
TruthFinder.org website