Text, as one of the most influential inventions of humanity, has played an important role in human life, so far from ancient times. The rich and precise information embod- ied in text is very useful in a wide range of vision-based ap- plications, therefore text detection and recognition in natu- ral scenes have become important and active research topics in computer vision and document analysis. Especially in re- cent years, the community has seen a surge of research efforts and substantial progresses in these fields, though a variety of challenges （e.g. noise, blur, distortion, occlusion and varia- tion） still remain. The purposes of this survey are three-fold： 1） introduce up-to-date works, 2） identify state-of-the-art al- gorithms, and 3） predict potential research directions in the future. Moreover, this paper provides comprehensive links to publicly available resources, including benchmark datasets, source codes, and online demos. In summary, this literature review can serve as a good reference for researchers in the areas of scene text detection and recognition.
On June 17, 2013, MilkyWay-2 （Tianhe-2） supercomputer was crowned as the fastest supercomputer in the world on the 41th TOP500 list. This paper provides an overview of the MilkyWay-2 project and describes the design of hardware and software systems. The key architecture features of MilkyWay-2 are highlighted, including neo-heterogeneous compute nodes integrating commodity- off-the-shelf processors and accelerators that share similar instruction set architecture, powerful networks that employ proprietary interconnection chips to support the massively parallel message-passing communications, proprietary 16- core processor designed for scientific computing, efficient software stacks that provide high performance file system, emerging programming model for heterogeneous systems, and intelligent system administration. We perform extensive evaluation with wide-ranging applications from LINPACK and Graph500 benchmarks to massively parallel software deployed in the system.
This paper presents a novel tracking algorithm which integrates two complementary trackers. Firstly, an improved Bayesian tracker(B-tracker) with adaptive learning rate is presented. The classification score of B-tracker reflects tracking reliability, and a low score usually results from large appearance change. Therefore, if the score is low, we decrease the learning rate to update the classifier fast so that B-tracker can adapt to the variation and vice versa. In this way, B-tracker is more suitable than its traditional version to solve appearance change problem. Secondly, we present an improved incremental subspace learning method tracker(S-tracker). We propose to calculate projected coordinates using maximum posterior probability, which results in a more accurate reconstruction error than traditional subspace learning tracker. Instead of updating at every time, we present a stop-strategy to deal with occlusion problem. Finally, we present an integrated framework(BAST), in which the pair of trackers run in parallel and return two candidate target states separately. For each candidate state, we define a tracking reliability metrics to measure whether the candidate state is reliable or not, and the reliable candidate state will be chosen as the target state at the end of each frame. Experimental results on challenging sequences show that the proposed approach is very robust and effective in comparison to the state-of-the-art trackers.
There is a trend that, virtually everyone, ranging from big Web companies to traditional enterprisers to physical science researchers to social scientists, is either already experiencing or anticipating unprecedented growth in the amount of data available in their world, as well as new opportunities and great untapped value. This paper reviews big data challenges from a data management respective. In particular, we discuss big data diversity, big data reduction, big data integration and cleaning, big data indexing and query, and finally big data analysis and mining. Our survey gives a brief overview about big-data-oriented research and problems.
This paper investigates human mobility patterns in an urban taxi transportation system. This work focuses on predicting human mobility from discovering patterns of in the number of passenger pick-ups quantity （PUQ） from urban hotspots. This paper proposes an improved ARIMA based prediction method to forecast the spatial-temporal variation of passengers in a hotspot. Evaluation with a large-scale real- world data set of 4 000 taxis＇ GPS traces over one year shows a prediction error of only 5.8%. We also explore the applica- tion of the pl~di~fioti approach to help drivers find their next passetlgerS, The sinatllation results using historical real-world data demonstrate that, with our guidance, drivers can reduce the time taken and distance travelled, to find their next pas- senger＋ by 37.1% and 6.4% respectively,
DBSCAN （density-based spatial clustering of ap- plications with noise） is an important spatial clustering tech- nique that is widely adopted in numerous applications. As the size of datasets is extremely large nowadays, parallel process- ing of complex data analysis such as DBSCAN becomes in- dispensable. However, there are three major drawbacks in the existing parallel DBSCAN algorithms. First, they fail to prop- erly balance the load among parallel tasks, especially when data are heavily skewed. Second, the scalability of these al- gorithms is limited because not all the critical sub-procedures are parallelized. Third, most of them are not primarily de- signed for shared-nothing environments, which makes them less portable to emerging parallel processing paradigms. In this paper, we present MR-DBSCAN, a scalable DBSCAN algorithm using MapReduce. In our algorithm, all the crit- ical sub-procedures are fully parallelized. As such, there is no performance bottleneck caused by sequential process- ing. Most importantly, we propose a novel data partitioning method based on computation cost estimation. The objective is to achieve desirable load balancing even in the context of heavily skewed data. Besides, We conduct our evaluation us- ing real large datasets with up to 1.2 billion points. The ex- periment results well confirm the efficiency and scalability of MR-DBSCAN.
Recent years have witnessed the rapid growth of social multimedia data available over the Internet. The age of huge amount of media collection provides users facihties to share and access data, while it also demands the revolution of data management techniques, since the exponential growth of social multimedia requires more scalable, effective and ro- bust technologies to manage and index them. The event is one of the most important cues to recall people＇s past memory. The reminder value of an event makes it extremely helpful in organizing data. The study of event based analysis on so- cial multimedia data has drawn intensive attention in research community. In this article, we provide a comprehensive sur- vey on event based analysis over social multimedia data, in- cluding event enrichment, detection, and categorization. We introduce each paradigm and summarize related research ef- forts. In addition, we also suggest the emerging trends in this research area.
Recently, compressive tracking （CT） has been widely proposed for its efficiency, accuracy and robustness on many challenging sequences. Its appearance model employs non-adaptive random projections that preserve the structure of the image feature space. A very sparse measurement matrix is used to extract features by multiplying it with the feature vector of the image patch. An adaptive Bayes classifier is trained using both positive samples and negative samples to separate the target from background. On the CT frame- work, however, some features used for classification have weak discriminative abilities, which reduces the accuracy of the strong classifier. In this paper, we present an online compressive feature selection algorithm（CFS） based on the CT framework. It selects the features which have the largest margin when using them to classify positive samples and negative samples. For features that are not selected, we define a random learning rate to update them slowly, It makes those weak classifiers preserve more target information, which relieves the drift when the appearance of the target changes heavily. Therefore, the classifier trained with those discriminative features couples its score in many challenging sequences, which leads to a more robust tracker. Numerous experiments show that our tracker could achieve superior result beyond many state-of-the-art trackers.
String similarity search and join are two impor- tant operations in data cleaning and integration, which ex- tend traditional exact search and exact join operations in databases by tolerating the errors and inconsistencies in the data. They have many real-world applications, such as spell checking, duplicate detection, entity resolution, and webpage clustering. Although these two problems have been exten- sively studied in the recent decade, there is no thorough sur- vey. In this paper, we present a comprehensive survey on string similarity search and join. We first give the problem definitions and introduce widely-used similarity functions to quantify the similarity. We then present an extensive set of algorithms for siring similarity search and join. We also dis- cuss their variants, including approximate entity extraction, type-ahead search, and approximate substring matching. Fi- nally, we provide some open datasets and summarize some research challenges and open problems.
Robust face representation is imperative to highly accurate face recognition. In this work, we propose an open source face recognition method with deep representation named as VIPLFaceNet, which is a lO-layer deep convolu- tional neural network with seven convolutional layers and three fully-connected layers. Compared with the well-known AlexNet, our VIPLFaceNet takes only 20% training time and 60% testing time, but achieves 40% drop in error rate on the real-world face recognition benchmark LFW. Our VIPLFaceNet achieves 98.60% mean accuracy on LFW us- ing one single network. An open-source C＋＋ SDK based on VIPLFaceNet is released under BSD license. The SDK takes about 150ms to process one face image in a single thread on an i7 desktop CPU. VIPLFaceNet provides a state-of-the-art start point for both academic and industrial face recognition applications.
Dynamic consolidation of virtual machines （VMs） in a data center is an effective way to reduce the en- ergy consumption and improve physical resource utilization. Determining which VMs should be migrated from an over- loaded host directly influences the VM migration time and increases energy consumption for the whole data center, and can cause the service level of agreement （SLA）, delivered by providers and users, to be violated. So when designing a VM selection policy, we not only consider CPU utilization, but also define a variable that represents the degree of resource satisfaction to select the VMs. In addition, we propose a novel VM placement policy that prefers placing a migratable VM on a host that has the minimum correlation coefficient. The bigger correlation coefficient a host has, the greater the in- fluence will be on VMs located on that host after the migra- tion. Using CloudSim, we run simulations whose results let draw us to conclude that the policies we propose in this pa- per perform better than existing policies in terms of energy consumption, VM migration time, and SLA violation per- centage.
Time series classification is related to many dif- ferent domains, such as health informatics, finance, and bioinformatics. Due to its broad applications, researchers have developed many algorithms for this kind of tasks, e.g., multivariate time series classification. Among the classifi- cation algorithms, k-nearest neighbor （k-NN） classification （particularly 1-NN） combined with dynamic time warping （DTW） achieves the state of the art performance. The defi- ciency is that when the data set grows large, the time con- sumption of 1-NN with DTW will be very expensive. In con- trast to 1-NN with DTW, it is more efficient but less ef- fective for feature-based classification methods since their performance usually depends on the quality of hand-crafted features. In this paper, we aim to improve the performance of traditional feature-based approaches through the feature learning techniques. Specifically, we propose a novel deep learning framework, multi-channels deep convolutional neu- ral networks （MC-DCNN）, for multivariate time series classi- fication. This model first learns features from individual uni- variate time series in each channel, and combines information from all channels as feature representation at the final layer. Then, the learnt features are applied into a multilayer percep- tron （MLP） for classification. Finally, the extensive experi- ments on real-world data sets show that our model is not only more efficient than the state of the art but also competitive in accuracy. This study implies that feature learning is worth to be investigated for the problem of time series classification.
Remote photoplethysmography (rPPG) allows remote measurement of the heart rate using low-cost RGB imaging equipment. In this study, we review the development of the field of rPPG since its emergence in 2008. We also classify existing rPPG approaches and derive a framework that provides an overview of modular steps. Based on this framework, practitioners can use our classification to design algorithms for an rPPG approach that suits their specific needs. Researchers can use the reviewed and classified algorithms as a starting point to improve particular features of an rPPG algorithm.
Differential evolution (DE) is a kind of evolutionary algorithms, which is suitable for solving complex optimization problems. Mutation is a crucial step in DE that generates new solutions from old ones. It was argued and has been commonly adopted in DE that the solutions selected for mutation should have mutually different indices. This restrained condition, however, has not been verified either theoretically or empirically yet. In this paper, we empirically investigate the selection of solutions for mutation in DE. From the observation of the extensive experiments, we suggest that the restrained condition could be relaxed for some classical DE versions as well as some advanced DE variants. Moreover, relaxing the restrained condition may also be useful in designing better future DE algorithms.