Identifying Materials of Photographic Images and Photorealistic Computer Generated Graphics Based on Deep CNNs

Currently,some photorealistic computer graphics are very similar to photographic images.Photorealistic computer generated graphics can be forged as photographic images,causing serious security problems.The aim of this work is to use a deep neural network to detect photographic images(PI)versus computer generated graphics(CG).In existing approaches,image feature classification is computationally intensive and fails to achieve realtime analysis.This paper presents an effective approach to automatically identify PI and CG based on deep convolutional neural networks(DCNNs).Compared with some existing methods,the proposed method achieves real-time forensic tasks by deepening the network structure.Experimental results show that this approach can effectively identify PI and CG with average detection accuracy of 98%.

Analyzing Cross-domain Transportation Big Data of New York City with Semi-supervised and Active Learning

The majority of big data analytics applied to transportation datasets suffer from being too domain-specific,that is,they draw conclusions for a dataset based on analytics on the same dataset.This makes models trained from one domain(e.g.taxi data)applies badly to a different domain(e.g.Uber data).To achieve accurate analyses on a new domain,substantial amounts of data must be available,which limits practical applications.To remedy this,we propose to use semi-supervised and active learning of big data to accomplish the domain adaptation task:Selectively choosing a small amount of datapoints from a new domain while achieving comparable performances to using all the datapoints.We choose the New York City(NYC)transportation data of taxi and Uber as our dataset,simulating different domains with 90%as the source data domain for training and the remaining 10%as the target data domain for evaluation.We propose semi-supervised and active learning strategies and apply it to the source domain for selecting datapoints.Experimental results show that our adaptation achieves a comparable performance of using all datapoints while using only a fraction of them,substantially reducing the amount of data required.Our approach has two major advantages:It can make accurate analytics and predictions when big datasets are not available,and even if big datasets are available,our approach chooses the most informative datapoints out of the dataset,making the process much more efficient without having to process huge amounts of data.

Geek Talents:Who are the Top Experts on GitHub and Stack Overflow?

In the field of Computer Science,software developers need to use a wide array of social collaborative platforms for learning and cooperating.The most popular ones are GitHub and Stack Overflow.Existing platforms only support search queries to extract relevant repository information from GitHub,or questions and answers from Stack Overflow.This ignores the valuable coder-related part-who are the top experts(geek talents)in a specific area?This information is important to companies,open source projects,and to those who want to learn from an expert role model.Thus,how to find the right developers is quite a crucial yet challenging problem.Most of the current works mainly focus on recommending experts in a particular software engineering task and ignore the relationship between developers within different projects.In this paper,we propose a novel technique that automatically identifies geek talents from GitHub,Stack Overflow,and across both communities.The results show that our work performs well at recommending proper developers in diverse areas.