ACM Transactions on

Intelligent Systems and Technology (TIST)

Latest Articles

Crowdsourcing Without a Crowd

We present an incremental Bayesian model that resolves key issues of crowd size and data quality for consensus labeling. We evaluate our method using data collected from a real-world citizen science program, BeeWatch, which invites members of the public in the United Kingdom to classify (label)... (more)

A Crowd-Powered System for Fashion Similarity Search

Driven by the needs of customers and industry, online fashion search and analytics are recently... (more)

Rapid Low-Cost Virtual Human Bootstrapping via the Crowd

Virtual human interactions provide an important avenue for training as emergent opportunities arise. In response to a new training need, we propose a... (more)

Incentives for Effort in Crowdsourcing Using the Peer Truth Serum

Crowdsourcing is widely proposed as a method to solve a large variety of judgment tasks, such as classifying website content, peer grading in online... (more)


Crowdsourcing is increasingly being adopted to solve simple tasks such as image labeling and object tagging, as well as more complex tasks, where crowd workers collaborate in processes with interdependent steps. For the whole range of complexity, research has yielded numerous patterns for coordinating crowd workers in order to optimize crowd... (more)

Crowdsourcing Empathetic Intelligence

Unobtrusive recognition of the user's mood is an essential capability for affect-adaptive systems. Mood is a subtle, long-term affective state, often misrecognized even by humans. The challenge to train a machine to recognize it from, for example, a video of the user, is significant, and already begins with the lack of ground truth for supervised... (more)


Crowdsourcing implies user collaboration and engagement, which fosters a renewal of city governance processes. In this article, we address a subset of crowdsourcing, named citizen-sourcing, where citizens interact with authorities collaboratively and actively. Many systems have experimented citizen-sourcing in city governance processes; however,... (more)

Leveraging Human Computations to Improve Schematization of Spatial Relations from Imagery

The process of generating schematic maps of salient objects from a set of pictures of an indoor environment is challenging. It has been an active area... (more)

A Game-Theory Approach for Effective Crowdsource-Based Relevance Assessment

Despite the ever-increasing popularity of crowdsourcing (CS) in both industry and academia, procedures that ensure quality in its results are still... (more)

Crowdsourcing Human Annotation on Web Page Structure

Parsing the semantic structure of a web page is a key component of web information extraction. Successful extraction algorithms usually require... (more)


New options for ACM authors to manage rights and permissions for their work

ACM introduces a new publishing license agreement, an updated copyright transfer agreement, and a new author-pays option which allows for perpetual open access through the ACM Digital Library. For more information, visit the ACM Author Rights webpage.


About TIST

ACM Transactions on Intelligent Systems and Technology (ACM TIST, Impact Factor: 2.4) is a scholarly journal that publishes the highest quality papers on intelligent systems, applicable algorithms and technology with a multi-disciplinary perspective. An intelligent system is one that uses artificial intelligence (AI) techniques to offer important services (e.g., as a component of a larger system) to allow integrated systems to perceive, reason, learn, and act intelligently in the real world. READ MORE

Forthcoming Articles
Soft Confidence-Weighted Learning

Online learning plays a very important role in many big data mining problems, because it enjoys very high efficiency. In literature, many first order online learning algorithms by using first order information such as, gradient, are proposed to solve online classification tasks. Recently, some second order online learning algorithms are proposed for classification tasks, which can uses some second order information, such as, the correlation between the features to improve the learning efficiency. Among them, Confidence-Weighted (CW) learning algorithms are very effective, which assume that the classification model satisfies a Gaussian distribution, so that the model can be effectively updated using the second order information of the data stream. Despite being studied actively, these CW algorithms cannot handle non-separable datasets and nosy datasets very well. Although, other methods, such as Adaptive Regularization of Weight (AROW), are proposed to alleviate this problem, they do not have the adaptive margin property of CW. In this paper, we propose a family of Soft Confidence Weighted (SCW) learning algorithms for both binary classification and multi-class classification tasks, which is the first family of online classification algorithms that enjoys four salient properties simultaneously: (i) large margin training, (ii) confidence weighting, (iii) capability to handle non-separable data, and (iv) adaptive margin. Our experimental results show that the proposed SCW algorithms significantly outperform the original CW algorithm. When comparing with a variety of state-of-the-art algorithms (including AROW, NAROW and NHERD), we found that SCW in general achieves better or at least comparable predictive performance, but enjoys considerably better efficiency advantage (i.e., using smaller number of updates and lower time cost). To facilitate future research, we release all the datasets and source code to public at~\url{}.

Learning User Attributes via Mobile Social Multimedia Analytics

Learning user attributes from mobile social media is a fundamental basis for many applications, such as the personalized and targeting services. A large and growing body of literatures has investigated the user attributes learning problem. However, far too little attention has been paid to jointly consider the dual-heterogeneities of user attributes learning by harvesting multiple social media sources. In particular, user attributes are complementarily and comprehensively characterized by multiple social media sources, including footprints from Foursqare, daily updates from Twitter, professional careers from Linkedin and photo posts from Instagram; On the other hand, attributes are inter-correlated in a complex way rather than independent to each other, and highly related attributes may share similar feature sets. Towards this end, we proposed a unified model to jointly regularize the source consistency and graph-constrained relatedness among tasks. As a byproduct, it is able to learn the attribute-specific and attribute-sharing features via graph-guided fused lasso penalty. Besides, we have theoretically demonstrated its optimization. Extensive evaluations on real-world dataset thoroughly demonstrated the effectiveness of our proposed model.

Joint Structured Sparsity Regularized Multi-view Dimension Reduction for Video-based Facial Expression Recognition

Video-based facial expression recognition (FER) has recently received increased attention as a result of its widespread application. Using only one type of feature to describe facial expression in video sequences is often inadequate, because the available information is very complex. With the emergence of different features to represent different properties of facial expressions in videos, an appropriate combination of these features becomes an important yet challenging problem. Considering that the dimensionality of these features is usually high, we thus introduce multi-view dimension reduction (MVDR) to video-based FER. In MVDR, it is critical to explore the relationships between and within different feature views. To achieve this goal, we propose a novel framework for MVDR by enforcing joint structured sparsity at both inter- and intra-view levels. In this way, correlations on and between the feature spaces of different views tends to be well-exploited. In addition, a transformation matrix is learned for each view to discover the patterns contained in the original features, so that the different views are comparable in finding a common representation. The model can not only be performed in an unsupervised manner, but also easily extended to semi-supervised setting by incorporating some domain knowledge. An alternating algorithm is developed for problem optimization, and each sub-problem can be efficiently solved. Experiments on two challenging video-based FER datasets demonstrate the effectiveness of the proposed framework.

SMARTS: Scalable Microscopic Adaptive Road Traffic Simulator

Microscopic traffic simulators are important tools for studying transportation systems as they describe the evolution of traffic to the highest level of detail. A major challenge to microscopic simulators is the slow simulation speed due to the complexity of traffic models. We develop SMARTS, a distributed microscopic traffic simulator that can achieve a significant improvement in simulation speed by utilizing network-connected computing nodes in parallel. The simulator implements an innovative spatial workload balancing strategy that helps to minimize computation workload and communication cost at the same time. SMARTS can perform fast large-scale simulations. For example, a simulation performed by 30 computing nodes runs 1.14 times faster than real time when there are one million vehicles in an area the size of Melbourne. SMARTS supports a number of driver models and traffic rules, such as car-following model and lane-changing model, which can be driver dependent. It can simulate multiple vehicle types, including bus and tram. The simulator is equipped with a wide range of features that help to customize, calibrate and monitor simulations. Users can build traffic scenarios such as simulating the spike of traffic towards a specified area. Simulations are accurate and confirm with real traffic behaviours. For example, it achieves 79.1% accuracy in predicting traffic on a 10-kilometre freeway 90 minutes into the future. The simulator can be used for predictive traffic advisories as well as traffic management decisions as simulations complete well ahead of real time. SMARTS can be easily deployed to different operating systems as it is developed with the standard Java libraries.

Getting Closer to the Essence of Music: The Con Espressione Manifesto

This text offers a personal and very subjective view on the current situation of Music Information Research (MIR). Motivated by the desire to build systems with a somewhat deeper understanding of music than the ones we currently have, I try to sketch a number of challenges for the next decade of MIR research, grouped around six simple truths about music that are probably generally agreed on, but often ignored in everyday research.

Rating Effects on Social News Posts and Comments

At a time when information seekers first turn to digital sources for news and opinion, it is critical that we understand the role that social media plays in human behavior. This is especially true when information consumers also act as information producers and editors through their online activity. In order to better understand the effects that editorial ratings have on online human behavior, we report the results of a two large-scale in-vivo experiments in social media. We find that small, random rating manipulations on social media posts and comments created significant changes in downstream ratings resulting in significantly different final outcomes. We found positive herding effects for positive treatments on posts, increasing the final rating by 11.02% on average, but not for positive treatments on comments. Contrary to the results of related work, we found negative herding effects for negative treatments on posts and comments, decreasing the final ratings on average, of posts by 5.15% and of comments by 37.4%. Compared to the control group, the probability of reaching a high rating (>=2000) for posts is increased by 24.6% when posts receive the positive treatment and for comments is decreased by 46.6% when comments receive the negative treatment.

Recognizing Parkinsonian Gait Pattern by Exploiting Fine-grained Movement Function Features

Parkinsons Disease (PD) is one of the typical movement disorder diseases among elderly people, which has a serious impact on their daily lives. In this paper, we propose a novel computation framework to recognize gait patterns in patients with PD. The key idea of our approach is to distinguish gait patterns in PD patients from healthy individuals by accurately extracting gait features which capture all the three aspects of movement functions, i.e., stability, symmetry and harmony. The proposed framework contains three steps: gait phase discrimination, feature extraction and selection, and pattern classification. In the first step, we put forward a sliding window based method to discriminate four gait phases from plantar pressure data. Based on the gait phases, we extract and select gait features which characterize stability, symmetry and harmony of movement functions. Finally, we recognize PD gait patterns by applying a hybrid classification model. We evaluate the framework using an open dataset that contains real plantar pressure data of 93 PD patients and 72 healthy individuals. Experimental results demonstrate that our framework significantly outperforms the four baseline approaches.

Driving profiles computation and monitoring for car insurance CRM

Customer segmentation is one of the most traditional and valued tasks in customer relationship management (CRM). In this paper, we explore the problem in the context of the car insurance industry, where the mobility behavior of customers plays a key role: different mobility needs, driving habits and skills imply also different requirements (level of coverage provided by the insurance) and risks (of accidents). In the present work, we describe a methodology to extract several indicators describing the driving profile of customers, and provide a clustering-oriented instantiation of the segmentation problem, based on such indicators. Then, we consider the availability of a continuous flow of fresh mobility data sent by the circulating vehicles, aiming at keeping our segments constantly up-to-date. We tackle a major scalability issue that emerges in this context when the number of customers is large, namely the communication bottleneck, by proposing and implementing a sophisticated distributed monitoring solution (called SaDiC), which reduces the communications between vehicles and company servers to the essential. We validate the framework on a large database of real mobility data, coming from GPS devices of private cars. Finally, we analyze the privacy risks that the proposed approach might involve for the users, providing and evaluating a countermeasure based on data perturbation.

Measuring Similarity Similarly: LDA and Human Perception

Several intelligent technologies designed to improve navigability in and digestibility of text corpora use topic modeling such as the state-of-the-art Latent Dirichlet Allocation (LDA). This model and variants on it provide lower-dimensional document representations used in visualizations and in computing similarity between documents. This paper contributes a method for validating such algorithms against human perceptions of similarity, especially applicable to contexts where the algorithm is intended to support navigability between similar documents via dynamically generated hyperlinks. Such validation enables researchers to ground their methods in context of intended use instead of relying on assumptions of fit. In addition to the methodology, this paper presents the results of an evaluation using a corpus of short documents and the LDA algorithm. We also present some analysis of potential causes of differences between cases where this model matches human perceptions of similarity more or less well.

Towards Music Structural Segmentation Across Genres: Features, Structural Hypotheses and Annotation Principles

This article provides insights into how different audio features and segmentation methods embrace different music genres. By incorporating a newly composed corpus with Chinese traditional Jingju music into the music structural segmentation study, we propose to extend this research topic outside a Western context across genres. The investigated harmonic-percussive separation technique in the feature extraction process has introduced significant improvement for the segmentation. A systematic evaluation is carried out to examine the effectiveness of commonly used audio features and segmentation methods for several music categories. Results show that investigated features capture the structural patterns of different music genres in different ways. Well acknowledged feature types and structural hypotheses for Western pop music may have weak assumptions for the Chinese traditional genre. To summarise, in the scenario of music structural analysis, the selection of audio features, the design of segmentation paradigms as well as the associated signal processing techniques, the music types and the annotation principles should not be isolated in order to achieve successful segmentation.

Privacy-Preserving Verifiable Incentive Mechanisms for Crowd Sensing Applications

Understanding the Relationship between Human Behavior and Susceptibility to Cyber-Attacks: A Data-Driven Approach

While human users are often considered to be the weakest link in security systems, the risks associated with typical day-to-day computing habits are not well understood. Using Symantec's WINE platform, we conduct a detailed study of 1.6 million machines over an 8-month period in order to learn the relationship between user behavior and cyber attacks against their personal computers.We classify users into 4 categories (gamers, professionals, software developers, others plus a fifth category comprising everyone) and identify a total of 7 independent variables to study: (i) number of binaries (executables) on a machine, (ii) fraction of low-prevalence binaries on a machine, (iii) fraction of high-prevalence binaries on a machine, (iv) fraction of unique binaries on a machine, (v) fraction of downloaded binaries on a machine, (vi) fraction of unsigned binaries on a machine and (vii) travel history of the machine based on number of ISPs from whom the machine connected to the Internet. For each of the 35 possible combinations (5 categories times 7 independent variables), we studied the relationship between each of these 7 independent variables and one dependent variable, namely the number of attempted malware attacks detected by Symantec on the machine. Our results show that the first variable is closely linked to number of attacks for software developers, while the next 5 are linked to the number of attacks for all user categories. Surprisingly, our results show that software developers are more at risk of engaging in risky cyber-behavior than other categories.

SNAP: A General Purpose Network Analysis and Graph Mining Library

Large networks are becoming a widely used abstraction for studying complex systems in a broad set of disciplines, ranging from social network analysis to molecular biology and neuroscience. Despite an increasing need to analyze and manipulate large networks, only a limited number of tools are available for this task. Here, we describe Stanford Network Analysis Platform (SNAP), a general-purpose, high-performance system that provides easy to use, high-level operations for analysis and manipulation of large networks. We present SNAP functionality, describe its implementational details, and give performance benchmarks. SNAP has been developed for single big-memory machines and it balances the trade-off between maximum performance, compact in-memory graph representation, and the ability to handle dynamic graphs where nodes and edges are being added or removed over time. It can process massive networks with hundreds of millions of nodes and billions of edges. SNAP offers over 140 different graph algorithms that can efficiently manipulate large graphs, calculate structural properties, generate regular and random graphs, and handle attributes on nodes and edges. Besides being able to handle large graphs, an additional strength of SNAP is that networks and their attributes are fully dynamic, they can be modified during the computation at low cost. SNAP is provided as an open source library in C++ as well as a module in Python. We also describe the Stanford Large Network Dataset, a set of social and information real-world networks and datasets, which we make publicly available. The collection is a complementary resource to our SNAP software and is widely used for development and benchmarking of graph analytics algorithms.

Dystemo: Distant Supervision Method for Multi-Category Emotion Recognition in Tweets

Emotion recognition in text has become an important research objective. It involves building classifiers capable of detecting a full range of human emotions. The accuracy of such classifiers depends not only on their precision but also on how fine-grained the underlying emotion model is. The more complete the model, the more accurately the resultant classifier can approximate how people feel. This paper proposes a distant supervision methodDystemofor producing emotion classifiers using a 20-category emotion model. The success of this method depends largely on a novel classifierBalanced Weighted Voting (BWV)designed to overcome the imbalance in emotion distribution in the initial dataset. We demonstrate Dystemo with BWV using Twitter data about sports events. Through a series of carefully designed experiments, we confirm that applying this method improves emotion recognition quality up to 191%. We also study how different initial classifiers can lead to dissimilar performance of the final classifiers, how applying different rebalancing techniques has effects, and how to include neutral tweets. This investigation could serve as a design framework for those interested in building distant learning classifiers in a variety of domains, e.g. analyzing reactions to product launches, monitoring emotions at sports events, or discerning opinions in political debates.

Multi-Modular Text Normalization of Dutch User-Generated Content

As social media constitute a valuable source for data analysis for a wide range of applications, the need for handling such data arises. However, the non-standard language used on social media poses problems for Natural Language Processing (NLP) tools as these are typically trained on standard language mate- rial. We propose a text normalization approach to tackle this problem. More specifically, we investigate the usefulness of a multi-modular approach to account for the diversity of normalization issues encountered in user-generated content. We consider three different types of user-generated content written in Dutch (SNS, SMS and tweets) and provide a detailed analysis of the performance of the different modules and the over- all system. We also apply an extrinsic evaluation by evaluating the performance of a part-of-speech (POS) tagger, lemmatizer and named-entity recognizer (NER) before and after normalization.As social media constitute a valuable source for data analysis for a wide range of applications, the need for handling such data arises. However, the non-standard language used on social media poses problems for Natural Language Processing (NLP) tools as these are typically trained on standard language mate- rial. We propose a text normalization approach to tackle this problem. More specifically, we investigate the usefulness of a multi-modular approach to account for the diversity of normalization issues encountered in user-generated content. We consider three different types of user-generated content written in Dutch (SNS, SMS and tweets) and provide a detailed analysis of the performance of the different modules and the over- all system. We also apply an extrinsic evaluation by evaluating the performance of a part-of-speech (POS) tagger, lemmatizer and named-entity recognizer (NER) before and after normalization.

Harnessing Music related Visual Stereotypes for Music Information Retrieval

Over decades music labels have shaped easily identifiable genres to improve recognition value and subsequently market sales of new music acts.Referring to print magazines and later to music television as important distribution channels, the visual representation thus played and still plays a significant role in music marketing. Visual stereotypes developed over decades which enable us to quickly identify referenced music only by sight without listening. Despite of the richness of music related visual information provided by daily life such as music videos, album covers as well as T-shirts, advertisements and magazines, research towards harnessing this information to advance existing or approach new problems of music retrieval or recommendation is scarce or missing. In this paper we presents our research on visual music computing which aims to extract stereotypical music related visual information from music videos. To provide comprehensive and reproducible results we present the Music Video Dataset - a thoroughly assembled suite of datasets where each sub-set is dedicates to a certain Music Information Retrieval (MIR) task or evaluation scenario. Based on this dataset we provide evaluations of conventional low-level image processing features as well as affect-related features to provide an overview of the expressiveness of fundamental visual properties such as color, illumination and contrasts. Based on this we introduce a high-level approach to facilitate visual stereotypes based on visual concept detection. This approach decomposes the semantic content of music video frames into concrete concepts such as Guitars, Cars, Tools, etc. defined in a wide visual vocabulary. Concepts of this vocabulary are detected using convolutional neural networks and their frequency distributions are analyzed towards their performance in predicting the music genre of a video.

Learning Contextualized Music Semantics from Tags via a Siamese Neural Network

Music information retrievals (MIR) face a challenge of modelling contextualized musical concepts. In this paper, we propose a novel Siamese neural network to fight off this challenge. By means of tag features and probabilistic topic models, our Siamese network captures contextualized music semantics from tags via unsupervised learning, which leads to a distributed semantics space and a potential solution to the out of vocabulary (OOV) problem which has yet to be sufficiently addressed so far. We have conducted simulations on three public music tag collections, CAL500, MagTag5K and Million Song Dataset, and have compared our approach to a number of the state-of-the-art semantics learning approaches. Comparative results suggest that ours outperforms previous approaches in terms of the semantic priming and the tag completion tasks.

Topic-aware Physical Activity Propagation with Temporal Dynamics in a Health Social Network

Modeling physical activity propagation, such as the activity level and intensity, is the key to prevent the cascades of obesity, and help spread wellness and healthy behavior in a social network. However, there has been lacking of scientific and quantitative study to elucidate how social communication may deliver physical activity interventions. In this work we introduce a novel model named Topic Aware Community-level Physical Activity Propagation (TaCPP) to analyze physical activity propagation and social influence at different granularities (i.e., individual level and community level). Given a social network, the TaCPP model first integrates the correlations between the content of social communication and social influences. Then a hierarchical approach is utilized to detect a set of communities and their reciprocal influence strength of physical activities. The experimental evaluation shows not only the effectiveness of our approach but also the correlation of the detected communities with various health outcome measures. Our promising results pave a way for knowledge discovery in health social networks.

Mining Search and Browse Logs for Web Search: A Survey

Tensors for Data Mining and Data Fusion: Models, Applications, and Scalable Algorithms

Tensors and tensor decompositions are very powerful and versatile tools that can model a wide variety of heterogeneous, multi-aspect data. As a result, tensor decompositions, which extract useful latent information out of multi-aspect data tensors, have witnessed increasing popularity and adoption by the data mining community. In this survey, we present some of the most widely used tensor decompositions, providing the key insights behind them, and summarizing them from a practitioners point of view. We then overview a very broad spectrum of applications where tensors have been instrumental in achieving state of the art performance, ranging from social network analysis to brain data analysis, and from web mining to healthcare. Subsequently, we present recent algorithmic advances in scaling tensor decompositions up to todays big data scale, outlining the existing systems and summarizing the key ideas behind them. Finally, we conclude with a list of challenges and open problems that outline exciting future research directions.

A Joyful Ode to Automatic Orchestration

After long decades of research in computer music, music generation is now finally becoming a reality. The ability to produce automatically music of human-level quality, whatever this means, by algorithms able to understand sufficiently well the various problems underlying music generation. In this paper I report on a specific experiment in music generation resulting from a commission of the European Commision: the re-orchestration of Ode to Joy, the European anthem, in seven styles, using algorithms developped in the Flow Machines project and in a very limited time frame. I stress out the benefits of having had such a unifying goal, and the interesting new problems it raised in the way, both concerning symbolic and audio music generation.

Sound and Music Recommendation with Knowledge Graphs

The Web has moved, slowly but steady, from a collection of documents towards a collection of structured data. Knowledge graphs have then emerged as a way of representing the knowledge encoded in such data as well as a tool to reason on them in order to extract new and implicit information. Knowledge graphs are currently used, e.g., to explain search results, to explore knowledge spaces, to semantically enrich textual documents or to feed knowledge intensive applications such as recommender systems. In this work we describe how to create a knowledge graph to supply a hybrid recommendation engine with information that builds on top of the collection of sounds freely available in Freesound, a popular site for sharing sound samples which count more than 4 million registered users and about 250,000 uploaded sounds. Tags and textual sound descriptions, added by contributors at the time of the upload of a sound, are exploited to extract and link entities to external graphs such as WordNet and DBpedia which are in turn used to semantically enrich the initial data. The extracted data are eventually merged with a domain specific tagging ontology to form a richer knowledge graph of entities and labelled relationships. By means of the knowledge graph we build, recommendations are computed using a feature combination hybrid approach. Two explicit graph feature mappings are formulated to obtain meaningful item feature representations able to catch the knowledge embedded in the graph. Those content features are further combined with additional collaborative information deriving from implicit user feedback. An extensive evaluation on historical data shows significant improvements with respect to state of the art collaborative algorithms. In addition, we show how the semantic expansion of the initial sound descriptions help in achieving much better recommendation quality in terms of aggregated diversity and novelty.

Conventional and Unconventional Crowdsourcing Approaches to Make Search Smarter

Despite technological advances, algorithmic search systems still have difficulty with complex or subtle information needs. For example, scenarios requiring deep semantic interpretation are a challenge for computers. People, on the other hand, are well-suited to solving such problems. As a result, there is an opportunity for humans and computers to collaborate during the course of a search in a way that takes advantage of the unique abilities of each. While search tools that rely on human intervention will never be able to respond as quickly as current search engines do, recent research suggests that there are scenarios where a search engine could take more time if it resulted in a much better experience. This paper explores how crowdsourcing can be used to augment key stages of the search pipeline. We first explore a conventional approach where people are used to replace or augment traditional retrieval components such as query expansion and relevance scoring. We find that using crowd workers increases robustness against failure for query expansion and improves overall precision for results filtering, but that the gains are limited and unlikely to make up for the extra time required. We then introduce more unconventional approaches, where crowd workers provide rich query understanding and result processing, that lead to more notable gains. Our results confirm that crowdsourcing can positively impact the search experience, but suggest that significant changes to the search process may be required for crowdsourcing to fulfill its potential in search systems.

Using Crowdsourcing for Scientic Analysis of Tomographic Images

In this paper we present a novel application domain for human computing, and specifically for crowdsourcing, that can help in understanding particle tracking problems. Through an interdisciplinary inquiry, we built a crowdsourcing system designed to detect tracer particles in tomographic images, and applied it to the problem of bulk solid flow in silos. As images from silo sensing systems cannot be properly analyzed using computational methods, it requires human intelligence. However, limited availability of experts, as well as their high cost, motivates employing additional non-experts. We report on the results of a study that assesses the task completion time and accuracy of employing non-expert workers to process large data sets of rich images in order to generate useful data that might inform further research. We prove the feasibility of this approach by comparing results from the user study with data generated from a computational algorithm, showing the crowd provides superior quality, is more flexible, and is economical. This system can help analyze and understand the physics of flow phenomena to better inform the future design of silos, and is generalized enough to be applicable to other domains.

Intelligent Process Adaptation in the SmartPM System

Using Scalable Data Mining for Predicting Flight Delays

Flight delays are frequent all over the world (about 20% of airline flights arrive more than 15 minutes late) and they are estimated to have an annual cost of several tens of billion dollars. This scenario makes the prediction of flight delays a primary issue for airlines and travelers. The main goal of this work is to implement a predictor of the arrival delay of a scheduled flight due to weather conditions. The predicted arrival delay takes into consideration both implicit flight information (origin airport, destination airport, scheduled departure and arrival time) and weather forecast at origin airport and destination airport according to the flight timetable. Airline flights and weather observations datasets have been analyzed and mined using parallel algorithms implemented as MapReduce programs executed on a Cloud platform. The results show a high accuracy in predicting delays above a given threshold. For instance, with a delay threshold of 60 minutes we achieve 85.8% accuracy and 86.9% recall on delayed flights. Furthermore, the experimental results demonstrate the predictor scalability that can be achieved performing data preparation and mining tasks as MapReduce applications on the Cloud.

Personalized Microtopic Recommendation on Microblogs

Microblogging services such as Twitter and Sina Weibo allow users to create tags enclosed in a pair of # which are called microtopics. Each microtopic has a designate page, and can be directly visited or commented on. Microtopic recommendation can facilitate users to efciently acquire information by summarizing trending online topics and feeding comments with high quality. However, it is non-trivial to recommend microtopics to the users of microblogs to satisfy their information needs. In this paper, we investigate the task of personalized microtopic recommendation which exhibits two characteristics. First, the users tend not to give explicit ratings to the microtopics. Second, there exists rich information about users and microtopics, for example, users published content and biographical information. To address the above two characteristics, we propose a joint probabilistic latent factor model to integrate rich information into user adoption matrix factorization. Our model benets in collaborative ltering, content analysis and feature regression. Using two real-world datasets, we evaluate our model with different kinds of content and contextual information. Experimental results show that our model signicantly outperforms a few competitive baseline methods, especially in the circumstance that users have few adoption behaviors.

CSM: A Cloud Service Marketplace for Complex Service Acquisition

Cloud service marketplace (CSM) is an exploratory project aiming to provide an AppStore for Services. It is an intelligent online marketplace that facilitates services discovery and acquisition for enterprise customers. Traditional service discovery and acquisition is time-consuming. In the era of OneClick Checkout and pay-as-you-go service plans, users expect services to be purchased online efficiently and conveniently. However, as services are complex and different from software apps, currently prevailing AppStore based on keyword search are inadequate for services. In CSM, exploring and configuring services is an iterative process. Customers provide their requirements in natural language and interact with the system through questioning and answering. Learning from the input, the system can incrementally clarify users intention, narrow down the candidate services and profile the configuration information for the candidates at the same time. CSMs backend is built around the Services Knowledge Graph (SKG) and leverages data mining technologies to enable the semantic understanding of the customers requirements. To quantitatively assess the value of CSM, empirical evaluation on real and synthetic datasets and case studies are given to demonstrate the efficacy and effectiveness of the proposed system. Currently, CSM has been internally used by the business consultants of IBM.

A Semantic Framework for Intelligent Match-making for Clinical Trial Eligibility Criteria

Introduction to the Special Issue on Crowd in Intelligent Systems

Differential Flattening: A Novel Framework for Community Detection in Multi-Layer Graphs

A multi-layer graph consists of multiple layers of weighted graphs, where the multiple layers represent the different aspects of relationships. Considering multiple aspects (i.e., layers) together is essential to achieve a comprehensive and consolidated view. In this paper, we propose a novel framework of differential flattening, which facilitates the analysis of multi-layer graphs, and apply this framework to community detection. Differential flattening merges multiple graphs into a single graph such that the graph structure with the maximum clustering coefficient is obtained from the single graph. It has two distinct features compared with existing approaches. First, dealing with multiple layers is done independently of a specific community detection algorithm whereas previous approaches rely on a specific algorithm. Thus, any algorithm for a single graph becomes applicable to multi-layer graphs. Second, the contribution of each layer to the single graph is determined automatically for the maximum clustering coefficient. Since differential flattening is formulated by an optimization problem, the optimal solution is easily obtained by well-known algorithms such as interior point methods. Extensive experiments were conducted using the LFR benchmark networks as well as the DBLP, 20 Newsgroups, and MIT Reality Mining networks. The results show that our approach of differential flattening leads to discovery of higher-quality communities than baseline approaches and the state-of-the-art algorithms.

Optimal Scheduling of Cybersecurity Analysts for Minimizing Risk

Cybersecurity threats are on the rise with evermore digitization of the nformation that many day-to-day systems depend upon. The demand for cybersecurity analysts outpaces supply, which calls for optimal management of the analyst resource. Therefore, a key component of the cybersecurity defense system is the optimal scheduling of its analysts. Sensor data is analyzed by automatic processing systems, and alerts are generated. A portion of these alerts is considered to be {\it significant}, which requires thorough examination by a cybersecurity analyst. Risk, in this paper, is defined as the percentage of unanalyzed or not thoroughly analyzed alerts among the {\it significant} alerts by analysts. The paper presents a generalized optimization model for scheduling cybersecurity analysts to minimize risk (a.k.a maximize {\it significant} alert coverage by analysts) and maintain risk under a pre-determined upper bound. The paper tests the optimization model and its scalability on a set of given sensors with varying analyst experiences, alert generation rates, system constraints, and system requirements. Results indicate that the optimization model is scalable, and is capable of identifying both the right mix of analyst expertise in an organization and the sensor-to-analyst allocation in order to maintain risk below a given upper bound. Several meta-principles are presented, which are derived from the optimization model, and they further serve as guiding principles for hiring and scheduling cybersecurity analysts. The simulation studies (validation) of the optimization model outputs indicate that risk varies non-linearly with analyst/sensor ratio, and for a given analyst/sensor ratio, the risk is independent of the number of sensors in the system.

Dynamic Scheduling of Cybersecurity Analysts for Minimizing Risk Using Reinforcement Learning

An important component of the cyber-defense mechanism is the adequate staffing levels of its cybersecurity analyst workforce and their optimal assignment to sensors for investigating the dynamic alert traffic. The ever-increasing cybersecurity threats faced by today's digital systems require a strong cyber-defense mechanism that is both reactive in its response to mitigate the known risk, and proactive in being prepared for handling the unknown risks. In order to be proactive for handling the unknown risks, the above workforce must be scheduled dynamically so that the system is adaptive to meet the day-to-day stochastic demands on its workforce (both size and expertise mix). The stochastic demands on the workforce stem from the varying alert generation and their significance rate, which causes an uncertainty for the cybersecurity analyst scheduler that is attempting to schedule analysts for work and allocate sensors to analysts. Sensor data is analyzed by automatic processing systems, and alerts are generated. A portion of these alerts is categorized to be {\it significant}, which requires thorough examination by cybersecurity analyst. Risk, in this paper, is defined as the percentage of {\it significant} alerts that are not thoroughly analyzed by analysts. In order to minimize risk, it is imperative that the cyber-defense system accurately estimates the future significant alert generation rate, and dynamically schedules its workforce to meet the stochastic workload demand to analyze them. The paper presents a reinforcement learning-based stochastic dynamic programming optimization model for dynamically scheduling cybersecurity analysts to minimize risk (a.k.a maximize {\it significant} alert coverage by analysts) and maintain risk under a pre-determined upper bound. The paper tests the dynamic optimization model and compares the results to an integer programming model that optimizes the static staffing needs based on a daily-average alert generation rate with no estimation of future workload (static workforce model). Results indicate that the learning-based optimization model, through a dynamic (on-call) workforce in addition to the static workforce, is capable of reducing risk better than the static model, is scalable and capable of identifying the quantity and the right mix of analyst expertise in an organization, and is able to determine their dynamic (on-call) schedule and their sensor-to-analyst allocation in order to maintain risk below a given upper bound. Several meta-principles are presented, which are derived from the optimization model, and they further serve as guiding principles for hiring and scheduling cybersecurity analysts.

A Survey of Appearance Models in Visual Object Tracking

A Spatial-Temporal Topic Model for the Semantic Annotation of POIs in LBSNs

Semantic tags of Points of Interest (POIs) are a crucial prerequisite for location search, recommendation services, or data cleaning. However, most of POIs in location based social networks (LBSNs) are either tag-missing or tag-incomplete. This paper aims to develop semantic annotation techniques to automatically infer tags for POIs. We first analyze two LBSN datasets and observe that there are two types of tags, category-related ones and sentimental ones, which have unique characteristics. Category-related tags are hierarchical while sentimental ones are category-aware. All existing related work has adopted classification methods to predict high-level category-related tags in the hierarchy, but they cannot apply to infer either low-level category tags or sentimental ones. In light of this, we propose a latent-class probabilistic generative model, namely Spatial-Temporal Topic Model (STM), to infer personal interests, the temporal and spatial patterns of topics/semantics embedded in users' check-in activities, the interdependence between category-topic and sentiment-topic, and the correlation between sentimental tags and rating scores from users' check-in and rating behaviors. Then, these learnt knowledge is utilized to automatically annotate all POIs with both category-related and sentimental tags in a unified way. We conduct extensive experiments to evaluate the performance of the proposed STM on a real large-scale dataset. The experimental results show the superiority of our proposed STM, and we also observe that the real challenge of inferring category-related tags for POIs lies in the low-level ones of the hierarchy, and the challenge of predicting sentimental tags are those with neutral ratings.

When Location Meets Social Multimedia: A Survey on Vision-based Recognition and Mining for Geo-Social Multimedia Analytics

Analyzing User Behavior across Social Sharing Environments

Bridging the Air Gap between Isolated Networks and Mobile Phones in a Practical Cyber-Attack

Information is the most critical asset of modern organizations, and accordingly it is one of the resources most coveted by adversaries. When highly sensitive data is involved, an organization may resort to air gap isolation in which there is no networking connection between the inner network and the external world. While infiltrating an air gapped network has been proven feasible in recent years (e.g., Stuxnet), data exfiltration from an air gapped network is still considered to be one of the most challenging phases of an advanced cyber-attack. In this paper we present "AirHopper", a bifurcated malware that bridges the air gap between an isolated network and nearby infected mobile phones using FM signals. While it is known that software can intentionally create radio emissions from a video display unit, this is the first time that mobile phones are considered in an attack model as the intended receivers of maliciously crafted radio signals. We examine the attack model and its limitations and discuss implementation considerations such as stealth and modulation methods. We test AirHopper on an existing workplace at a typical office building and demonstrate how textual and binary data can be exfiltrated from physically isolated computers to mobile phones at a distance of 1-7 meters, with an effective bandwidth of 13-60 BPS (Bytes per second).

Multiagent Resource Allocation for Dynamic Task Arrivals with Preemption

In this paper we present a distributed algorithm for allocating resources to tasks in multiagent systems, one which adapts well to dynamic task arrivals where new work arises at short notice. Our algorithm is designed to leverage preemption if it is available, revoking resource allocations to tasks in progress if new opportunities arise which those resources are better suited to handle. Our multi-agent model assigns a task agent to each task which must be completed and a proxy agent to each resource which is available. Preemption occurs when a task agent approaches a proxy agent with a sufficiently compelling need that the proxy agent determines the newcomer derives more benefit from the proxy agent's resource than the task agent currently using that resource. Task agents reason about which resources to request based on a learning of churn and congestion. We compare to a well-established multi-agent resource allocation framework which permits preemption under more conservative assumptions, and show through simulation that our model allows for improved allocations through more permissive preemption. In all, we offer a novel approach for multiagent resource allocation that is able to cope well with dynamic task arrivals.

SPRank: Semantic Path-based Ranking for Top-N Recommendations using Linked Open Data

In most real world scenarios the ultimate goal of recommender system (RS) applications is to suggest a short ranked list of items, namely Top-N recommendations, supposed to be the most appealing for the end user. Often, the problem of computing Top-N recommendations is mainly tackled with a two steps approach. The system focuses first on predicting the unknown ratings which are eventually used to generated a ranked recommendation list. Actually, the Top-N recommendation task can be directly seen as a ranking problem where the main goal is not to accurately predict ratings but directly find the best ranked list of items to recommend. In this paper, we present SPRank, a novel hybrid recommendation algorithm able to compute Top-N recommendations exploiting freely available knowledge in the Web of Data. In particular we employ DBpedia, a well-known encyclopedic knowledge base in the Linked Open Data cloud, to extract semantic path-based features and to eventually compute Top-N recommendations in a Learning to Rank fashion. Experiments with three datasets related to different domains (books, music and movies) prove the effectiveness of our approach compared to state-of-the-art recommendation algorithms.

Enhanced Knowledge-Leverage Based TSK Fuzzy System Modeling for Inductive Transfer Learning

The knowledge-leverage based TakagiSugenoKang fuzzy system (KL-TSK-FS) modeling method has shown the promising performance for fuzzy modeling tasks where transfer learning is required. However, the knowledge-leverage mechanism of KL-TSK-FS can be further improved. This is because available training data in a current scene are not utilized for the learning of antecedent and the knowledge transfer mechanism from a reference scene to the current scene is still too simple for the learning of consequent parameters when a TakagiSugenoKang fuzzy system (TSK FS) mode is trained in the current scene. The proposed method, i.e., enhanced KL-TSK-FS (EKL-TSK-FS) has two knowledge-leverage strategies for enhancing the parameter learning of the TSK FS model for the current scene using available information from the reference scene. One strategy is used for the learning of antecedent parameters while the other is for consequent parameters. It is demonstrated that the proposed EKL-TSK-FS has higher transfer learning abilities than KL-TSK-FS.

A Unified Point-of-interest Recommendation Framework in Location-based Social Networks

Location-based social networks (LBSNs), such as Gowalla, Facebook, Foursquare, Brightkite, etc., have attracted millions of users to share their social friendship and their locations via check-ins in the past few years. Plenty of valuable information is accumulated based on the check-in behaviors, which makes it possible to learn users moving patterns as well as their preferences. In LBSNs, point-of-interest (POI) recommendation is one of the most significant tasks since it can help targeted users explore their surroundings as well as help third-party developers provide personalized services. Matrix factorization is a promising method for this task since it can capture users preferences to locations and is widely adopted in traditional recommender systems such as movie recommendation. However, the sparsity of the check-in data makes it difficult to capture users preferences accurately. Geographical influence can help alleviate this problem and have a large impact on the final recommendation result. By studying users moving patterns, we find that users tend to check in around several centers and different users have different numbers of centers. Based on this, we propose a Multi-center Gaussian Model (MGM) to capture this pattern via modeling the probability of a users check-in on a location. Moreover, users are usually more interested in the top 20 or even top 10 recommended POIs, which makes personalized ranking important in this task. From previous work, directly optimizing for pairwise ranking like Bayesian Personalized Ranking (BPR) achieves better performance in the top-k recommendation than directly using matrix matrix factorization that aims to minimize the point- wise rating error. To consider users preferences, geographical influence and personalized ranking, we propose a unified POI recommendation framework, which unifies all of them together. Specifically, we first fuse MGM with matrix factorization methods and further with BPR using two different approaches. We conduct experiments on Gowalla and Foursquare datasets, which are two large-scale real world LBSNs datasets publicly available online. The results on both datasets show that our unified POI recommendation framework can produce better performance.

CIM: Community-based Influence Maximization in Social Networks

Tempo Driven Audio-to-Score Alignment using Spectral Decomposition and Online Dynamic Time Warping

In this paper, we present an online score following framework designed to deal with automatic accompaniment. The proposed framework is based on spectral factorization and online Dynamic Time Warping (DTW) and has two separated stages: preprocessing and alignment. In the first one, we convert the score into a reference audio signal using a MIDI synthesizer software and we analyze the provided information in order to obtain the spectral patterns (i.e. basis functions) associated to each combination of concurrent notes in the score. These spectral patterns are learned from the synthetic MIDI signal using a method based on Non-negative Matrix Factorization (NMF) with Beta-divergence where the gains are initialized as the ground-truth transcription inferred from the MIDI. On the second stage, a non-iterative signal decomposition method with fixed spectral patterns per combination of notes is used over the magnitude spectrogram of the input signal resulting in a distortion matrix that can be interpreted as the cost of the matching for each combination of notes at each frame. Finally, the relation between the performance and the musical score times is obtained using a strategy based on online DTW, where the optimal path is biased by the speed of interpretation. Our system has been evaluated and compared to other systems, yielding reliable results and performance.

A Machine Learning Approach to College Drinking Prediction and Risk Factor Identification

A Risk-Scoring Feedback Model for Webpages and Web Users based on Browsing Behavior

It has been claimed that many security breaches are often caused by vulnerable (naïve) employees within the organization [1]. Thus, the weakest link in security is often not the technology itself but rather the people who use it [2]. In this paper, we propose a machine learning scheme for detecting risky webpages and risky browsing behavior, performed by naïve users in the organization. The scheme analyzes the interaction between two modules: one represents naïve users, while the other represents risky webpages. It implements a feedback loop between these modules such that if a webpage is exposed to a lot of traffic from risky users, its "risk score" increases, while in a similar manner, as the user is exposed to risky webpages (with a high "risk score"), his own "risk score" increases. The proposed scheme is tested on a real-world dataset of HTTP logs provided by a large American toolbar company. The results suggest that a feedback learning process involving webpages and users can improve the scoring accuracy and lead to the detection of unknown malicious webpages.


Publication Years 2010-2016
Publication Count 396
Citation Count 3875
Available for Download 396
Downloads (6 weeks) 4678
Downloads (12 Months) 45904
Downloads (cumulative) 320002
Average downloads per article 808
Average citations per article 10
First Name Last Name Award
Benjamin B Bederson ACM Distinguished Member (2011)
Andrei Broder ACM Paris Kanellakis Theory and Practice Award (2012)
Carlos A. Castillo ACM Senior Member (2014)
Charles L A Clarke ACM Distinguished Member (2015)
Ingemar J. Cox ACM Distinguished Member (2011)
Deborah Estrin ACM-W Athena Lecturer Award (2006)
Maria L Gini ACM Distinguished Member (2006)
Xian-Sheng Hua ACM Distinguished Member (2015)
ACM Senior Member (2009)
Chih-Jen Lin ACM Distinguished Member (2011)
ACM Senior Member (2010)
C.L. Liu ACM Karl V. Karlstrom Outstanding Educator Award (1989)
Jeffrey Nichols ACM Senior Member (2013)
Judea Pearl ACM A. M. Turing Award (2011)
ACM AAAI Allen Newell Award (2003)
Jian Pei ACM Senior Member (2007)
Yong Rui ACM Distinguished Member (2009)
ACM Senior Member (2006)
Stefan Savage ACM-Infosys Foundation Award in the Computing Sciences (2015)
Yoav Shoham ACM AAAI Allen Newell Award (2012)
Gita Reese Sukthankar ACM Senior Member (2013)
Moshe Tennenholtz ACM AAAI Allen Newell Award (2012)
Feiyue Wang ACM Distinguished Member (2007)
Xing Xie ACM Senior Member (2010)
Qiang Yang ACM Distinguished Member (2011)
Franco Zambonelli ACM Distinguished Member (2012)
ACM Senior Member (2009)
Yu Zheng ACM Senior Member (2011)
Michelle Zhou ACM Distinguished Member (2009)
ACM Senior Member (2007)
Michelle Zhou ACM Distinguished Member (2009)
ACM Senior Member (2007)

First Name Last Name Paper Counts
Dacheng Tao 6
Enhong CHEN 6
Xing Xie 6
Tatseng Chua 5
Yu Zheng 5
Xiansheng Hua 5
Jinhui Tang 5
Shuicheng Yan 5
Nicholasjing Yuan 4
Changsheng Xu 4
Qiang Yang 4
Michelle Zhou 4
Xuan Song 3
Steven Hoi 3
Philip Yu 3
Ryosuke Shibasaki 3
Christopherchuen Yang 3
Wen Gao 3
Xue Li 3
Hui Xiong 3
Rongrong Ji 3
Xiaowei Shao 3
Huanhuan Cao 3
Rebecca Castano 3
Qi Tian 3
Wenchih Peng 3
Tao Li 3
Charles Ling 2
Mohan Kankanhalli 2
Zhengjun Zha 2
Yue Gao 2
Yoshinobu Kawahara 2
Chihjen Lin 2
Diane Cook 2
Defu Lian 2
Elena Baralis 2
Tania Cerquitelli 2
Robin Cohen 2
Sungwook Yoon 2
Mahmud Hossain 2
Vincent Tseng 2
Sihong Xie 2
Zhiwen Yu 2
Hongxun Yao 2
Paulo Shakarian 2
Hongyuan Zha 2
Haggai Roitman 2
Liyan Zhang 2
Alex Rogers 2
Alberto Del Bimbo 2
Jian Pei 2
Amin Javari 2
Yongdong Zhang 2
Alexander Artikis 2
Ido Guy 2
Iván Cantador 2
Venkatramanan Subrahmanian 2
Maria Sapino 2
Guirong Xue 2
Bohao Chen 2
Yixin Chen 2
Fuzheng Zhang 2
Nathan Eagle 2
Manish Marwah 2
Daxin Jiang 2
Xuning Tang 2
Francesco Bonchi 2
Meir Kalech 2
Shoude Lin 2
Jia Zeng 2
Katia Sycara 2
Rino Falcone 2
Jinshi Cui 2
Tao Mei 2
Yuval Elovici 2
Dana Nau 2
Hanqing Lu 2
Ling Guan 2
Michael Fire 2
Neil Yorke-Smith 2
Laiwan Chan 2
Meng Wang 2
Ratnesh Sharma 2
Fabio Gasparetti 2
Alessandro Micarelli 2
Munindar Singh 2
Gita Sukthankar 2
Zhiyuan Cheng 2
John Dickerson 2
Alvin Chin 2
Irwin King 2
David Carmel 2
Jun Ma 2
Jiuyong Li 2
Yuichi Motai 2
Masaki Aono 2
Jeffrey Nichols 2
Bingbing Ni 2
David Thompson 2
Alejandro Bellogín 2
Benno Stein 2
Zhi Geng 2
Kun Zhang 2
Bernhard Schölkopf 2
Ramesh Jain 2
Naren Ramakrishnan 2
Lior Rokach 2
Kiri Wagstaff 2
Li Chen 2
Alan Said 2
Martin Potthast 2
Sarit Kraus 2
Shihchia Huang 2
Huijing Zhao 2
Xindong Wu 2
Wangchien Lee 2
Subbarao Kambhampati 2
Shulamit Reches 2
Jalal Mahmud 2
Jamal Bentahar 2
Kyumin Lee 2
James Caverlee 2
Thomas Dietterich 2
Ya'akov Gal 2
Quanshi Zhang 2
Shuaiqiang Wang 2
Qingzhong Liu 2
Jiawei Han 2
Luan Tang 2
Claudio Biancalana 2
Giuseppe Sansonetti 2
Mahdi Jalili 2
Anlei Dong 2
Luca Cagliero 2
Daqing Zhang 2
Yue Shi 2
Martha Larson 2
Alan Hanjalic 2
Jilei Tian 2
Timothy Norman 1
Olivier Colot 1
Qun Jin 1
Huijing Zhao 1
Xiangfeng Luo 1
Enrico Pontelli 1
Lora Aroyo 1
Wangchien Lee 1
Alice Leung 1
Chenghua Lin 1
Paola Mello 1
Marta Arias 1
Ramon Xuriguera 1
Janyl Jumadinova 1
Ching Law 1
José García-Macías 1
Paolo Garza 1
Wangchien Lee 1
Zheng Song 1
Jian Ma 1
Zhaohui Wu 1
Leye Wang 1
J Gibson 1
Xing Xie 1
Chengkang Hsieh 1
John Jenkins 1
Feng Wu 1
Payam Barnaghi 1
Amit Sheth 1
Miyoung Kim 1
David Hayden 1
Markus Mühling 1
Yujin Zhang 1
Xianming Liu 1
Shiguang Shan 1
Myunghoon Suk 1
Shaohui Liu 1
Mary Pendleton Hoffer 1
Fernando Díez 1
Yoshiyuki Inagaki 1
Daniel Schuster 1
Benjamin Hung 1
Stephan Kolitz 1
Yakov Kronrod 1
Aurélien Max 1
Anne Vilnat 1
Tobias Höllerer 1
Dityan Yeung 1
Balakrishnan Prabhakaran 1
Yuchih Chen 1
Juan Recio-García 1
Nathannan Liu 1
Pranam Kolari 1
Yan Liu 1
Jianmin Wu 1
Xiaokang Yang 1
Lijun Zhu 1
Franco Zambonelli 1
Natalie Fridman 1
Kazumi Saito 1
Nitin Madnani 1
Svetlin Bostandjiev 1
Xiaoxiao Lian 1
Majid Ahmadabadi 1
Lars Haug 1
Jussara Almeida 1
Marcos Gonçalves 1
Tongliang Liu 1
Jinhui Tang 1
Daniel Roggen 1
Robert Jäschke 1
Le Wu 1
Simon Dooms 1
David Ben-Shimon 1
Guy Shani 1
Bracha Shapira 1
Thomas Huang 1
Wei Jin 1
Hala Mostafa 1
Steve Chien 1
Georgios Paltoglou 1
Vasileios Lampos 1
Ramendra Sahoo 1
Alejandro Jaimes 1
Fang Wu 1
William Bainbridge 1
Olivier Chapelle 1
Eren Manavoglu 1
Pablo Castells 1
Zhongxue Chen 1
Peter Briggs 1
Haifeng Wang 1
Quan Yuan 1
Yi Zhang 1
Hossein Hajimirsadeghi 1
Siegfried Handschuh 1
Jing Bai 1
Carolina Batista 1
Jiankang Deng 1
Dingqi Yang 1
Yuanzhuo Wang 1
Tie Luo 1
Guangming Guo 1
Luc Martens 1
Paolo Cremonesi 1
Yue Zhou 1
Tanzeem Choudhury 1
Guan Wang 1
Jiawei Han 1
Francisco Carrero 1
Linyun Fu 1
Zhenxing Wang 1
Wengkeen Wong 1
Huzaifa Zafar 1
Kenneth Whitebread 1
Scott DuVall 1
Aristidis Pappaioannou 1
Michal Feldman 1
Hengshu Zhu 1
Tieyan Liu 1
Marco Ribeiro 1
Anísio Lacerda 1
Adriano Veloso 1
Ümit Çatalyürek 1
Zhen Liao 1
Amos Azaria 1
Zhengdong Lu 1
Michael O’Mahony 1
Claudio Cioffi-Revilla 1
Hongan Wang 1
Hilal Khashan 1
Peter Prettenhofer 1
Shiwan Zhao 1
Fan Liu 1
Tatjen Cham 1
Qionghai Dai 1
Cristina Muntean 1
Ke Lu 1
Scott Spurlock 1
Ioannis Refanidis 1
Xiubo Geng 1
Xudong Zhang 1
Yan Song 1
Maria Gini 1
Yongsheng Dong 1
Xavier Serra 1
Yong Rui 1
Jun Wang 1
Jianmin Zheng 1
Guangming Shi 1
Ao Tang 1
Jie Huang 1
Yi Zhen 1
Wen Ji 1
Shanshan Huang 1
Peizhe Cheng 1
Seungchan Kim 1
Subbarao Kambhampati 1
Julie Porteous 1
Songchun Zhu 1
Peng Luo 1
Pingfeng Xu 1
Einat Minkov 1
George Baciu 1
Luis Leiva 1
Daniel Martín-Albo 1
Areej Malibari 1
Xin Jin 1
Yuanlong Shao 1
Nenghai Yu 1
Bolin Ding 1
Varun Mithal 1
Vipin Kumar 1
Marina Blanton 1
Shumei Sun 1
Miloš Hauskrecht 1
Silvia Chiusano 1
Atif Khan 1
Antonina Dattolo 1
Julita Vassileva 1
Taesup Moon 1
Yulan He 1
Layne Watson 1
Kathleen Carley 1
Hai Yang 1
Eric Lu 1
Qi Liu 1
Hsunping Hsieh 1
Chengte Li 1
Xinghai Sun 1
Wei Liu 1
Stephen Roberts 1
Denilson Barbosa 1
Richang Hong 1
Marco Gavanelli 1
Carlos Guestrin 1
Steven Klooster 1
Youxi Wu 1
Lin Lin 1
Elif Kürklü 1
Kalyan Subbu 1
Iyad Batal 1
Cristopher Yang 1
Riccardo Molinari 1
Amip Shah 1
Naren Ramakrishnan 1
Chuan Shi 1
Eui Shin 1
Derrall Heath 1
Patrick Butler 1
Liqiang Nie 1
Mitsuru Ishizuka 1
Helmut Prendinger 1
Jiaching Ying 1
Clemens Drews 1
Xiang Wu 1
Yicheng Song 1
Come Etienne 1
Bin Cheng 1
István Hegedűs 1
Levente Kocsis 1
András Benczúr 1
Wenyuan Dai 1
Alvaro Rosero 1
Linlin You 1
Tianyi Ma 1
Praveen Paritosh 1
Amit Chopra 1
Frank Dignum 1
Cristina Baroglio 1
Munindar Singh 1
Bo Xin 1
Kristen Venable 1
Petros Daras 1
Benjamin Lok 1
Gavin McArdle 1
Shikui Wei 1
Christopher Lambin 1
David Huynh 1
Andrew Jones 1
Radu Jurca 1
Zhoujun Li 1
Senzhang Wang 1
Abraham Bernstein 1
Jean Vandeborre 1
Hongbin Zha 1
Trancao Son 1
Guoliang Chen 1
Jaling Wu 1
Yunji Chen 1
Ling Li 1
Zhiwei Xu 1
Francesco Ricci 1
Yulan He 1
Fiona McNeill 1
Marco Montali 1
Hao Yan 1
Dario Antonelli 1
Disneyyan Lam 1
Md Ullah 1
Mingjin Zhang 1
Ron Hirschprung 1
Lotfi Romdhane 1
Yicheng Chen 1
Jiunlong Huang 1
Z Khalapyan 1
Cameron Ketcham 1
Krishnaprasad Thirunarayan 1
Jun Du 1
Adnan Ansar 1
Melissa Bunte 1
Xiaojin Zhu 1
Chengbo Zhang 1
Luheng He 1
Min Zhao 1
Isamu Okada 1
Enrique Chavarriaga 1
Bo Han 1
Shaodian Zhang 1
Lele Chang 1
Shijian Li 1
Haoyi Xiong 1
Shanchiehjay Yang 1
Nobuyuki Shimizu 1
Hiroshi Nakagawa 1
Ziqiang Shi 1
Tianshi Chen 1
Lena Tenenboim-Chekina 1
Rami Puzis 1
Mario Cataldi 1
Mehdi Elahi 1
Juan Pane 1
Alessandro Fiori 1
Xuemin Zhao 1
Naeem Mahoto 1
Jilin Chen 1
Yun Lu 1
Chang Liu 1
Naphtali Rishe 1
Eran Toch 1
Yueying He 1
Hao Fu 1
Aston Zhang 1
Asmaa Elbadrawy 1
S Nolen 1
Sumi Helal 1
Daniel Gaines 1
Robert Anderson 1
Michael Burl 1
Yantao Zheng 1
Deming Zhai 1
Stefano Berretti 1
Ronald Greeley 1
Norbert Schorghofer 1
Chunping Li 1
Lara Quijano-Sánchez 1
Shlomo Berkovsky 1
Paul Cook 1
Timothy Baldwin 1
Hongyuan Zha 1
Xiao Gu 1
Hao Wang 1
Hao Wang 1
Alberto Rosi 1
Markus Endler 1
John O’Donovan 1
Neil Yen 1
Weihong Qian 1
Xueying Li 1
Hadi Moradi 1
Shriram Revankar 1
John Salerno 1
Gal Kaminka 1
Andrea Apolloni 1
Asuman Ozdaglar 1
Herbert Gintis 1
Shiqi Zhao 1
Mirella Lapata 1
Alexander Quinn 1
Yang Song 1
Weijia Cai 1
Babak Araabi 1
Peipei Li 1
Wenbin Zhang 1
Christian Rohrdantz 1
Umeshwar Dayal 1
Daniel Keim 1
Xiaoyan Li 1
Zhaoyan Ming 1
Sajal Das 1
Stephan Doerfel 1
Paul Lukowicz 1
Xinlong Bao 1
Jane Hsu 1
Jeff Bilmes 1
Daqing Zhang 1
Matthai Philipose 1
Katayoun Farrahi 1
Amac Herdagdelen 1
Zhijun Yin 1
Xiaonan Li 1
Chengkai Li 1
Cong Yu 1
Christian KöRner 1
José Troyano 1
Li Ding 1
Prasad Tadepalli 1
Derek Green 1
Diana Spears 1
Santiago Ontañón 1
Jainarayan Radhakrishnan 1
Ashwin Ram 1
Umaa Rebbapragada 1
Damhnait Gleeson 1
Erel Uziel 1
Mike Thelwall 1
ShihHsien Tai 1
Siming Li 1
VinhTuan Thai 1
Lixin Shi 1
Ke Zhou 1
Dingquan Wang 1
Ahamad Khader 1
K Subramanian 1
Xueming Wang 1
Alberto Calatroni 1
Xueqi Cheng 1
Jennifer Moody 1
Lirong Xia 1
Jamie Ward 1
Hans Gellersen 1
Danny Wyatt 1
James Kitts 1
Bing Liu 1
Quanquan Gu 1
Fabian Loose 1
Paolo Rosso 1
Tad Hogg 1
Darren Appling 1
Elizabeth Whitaker 1
Deborah McGuinness 1
Antons Rebguns 1
Gerald DeJong 1
Reid MacTavish 1
Jinhong Guo 1
Sergej Sizov 1
Anusua Trivedi 1
Piyush Rai 1
Nello Cristianini 1
Carlos Castillo 1
Chunnan Hsu 1
Hao Ma 1
Justin Ma 1
Geoffrey Voelker 1
Moshe Tennenholtz 1
Rebecca Goolsby 1
Kamer Kaya 1
Panagiotis Adamopoulos 1
Alexander Tuzhilin 1
Zinovi Rabinovich 1
Claudia Goldman 1
Guozhong Dai 1
Elizabeth Salmon 1
Xiatian Zhang 1
Stefan Savage 1
J Carr 1
Huan Liu 1
Kuifei Yu 1
Charles Clarke 1
Tao Qin 1
Jun Wang 1
Nívio Ziviani 1
Yiyang Yang 1
Maurice Coyle 1
Xiaolong Zhang 1
Feng Tian 1
Zhanyi Liu 1
Wentao Zheng 1
Andrei Broder 1
Rongyao Fu 1
Yoav Shoham 1
Wenkui Ding 1
Shaojie Zhuo 1
Daniel Hennes 1
Ling Zhong 1
You Yang 1
Richard Souvenir 1
Abdulmotaleb Saddik 1
Gao Cong 1
Kevin Curran 1
Froduald Kabanza 1
Marcello Cirillo 1
Lars Karlsson 1
Amy Fire 1
Xiaogang Dong 1
Jianhua Guo 1
Peng Ding 1
Jiji Zhang 1
Thucduy Le 1
Nicholas Jennings 1
Weisheng Chin 1
Yong Zhuang 1
Zhao Zhang 1
Chenglin Liu 1
Rong Jin 1
Jameson Toole 1
Andreas Krause 1
Perukrishnen Vytelingum 1
Nicholas Jennings 1
Pauline Berry 1
Juan Castilla-Rubio 1
Wei Ding 1
Mitchell Ai-Chang 1
Howard Tennen 1
Aaron Steele 1
Sukjin Lee 1
Saranya Krishnamoorthy 1
Yubin Park 1
Pasquale Lops 1
Christopher Yang 1
Simon Pool 1
Juanzi Li 1
Emil Stefanov 1
Elaine Shi 1
Dan Ventura 1
Yiliang Zhao 1
Wei Jiang 1
Ali Hurson 1
Yunchao Wei 1
Guangchan Liu 1
Mohammad Hossain 1
Ghulam Muhammad 1
Huaming Rao 1
Advaith Siddharthan 1
Richard Comont 1
Elaine O'mahony 1
Amit Chopra 1
Munindar Singh 1
Robert Morris 1
Xiaoming Zhang 1
Jasminko Novak 1
Mark Melenhorst 1
Dimitrios Michalopoulos 1
Michael Borish 1
Matteo Venanzi 1
Mohamed Daoudi 1
Liangtien Chia 1
Timothy Shih 1
Yo Ehara 1
Khoi Nguyen 1
Feiyue Wang 1
Pakkin Wong 1
Ruoyun Huang 1
Zhihua Zhou 1
Emilio Ferrara 1
Geert Houben 1
Neil Rubens 1
Thomas Porta 1
Myungcheol Doo 1
Ling Liu 1
Wei Gao 1
Federico Chesani 1
Luigi Grimaudo 1
Prithviraj Dasgupta 1
Jianhui Ye 1
Anshul Sawant 1
MohammadTaghi Hajiaghayi 1
Hiroyuki Yoshida 1
Valeria Soto-Mendoza 1
Jesús Favela 1
Maythe Rojas 1
François Poulet 1
Xiaoshuai Sun 1
Pengfei Xu 1
Shengping Zhang 1
Julian Panetta 1
Timothy Rogers 1
Weishi Zhang 1
Pablo Castells 1
Yi Chang 1
Li Song 1
Karl Aberer 1
Daqing Zhang 1
Lingyin Wei 1
Thomas Springer 1
Hiroshi Motoda 1
Haifeng Wang 1
Bonnie Dorr 1
Taesun Moon 1
Houda Bouamor 1
Arthur Asuncion 1
Kasim Candan 1
Xuegang Hu 1
Christos Anagnostopoulos 1
Hong Zhou 1
Steven Skiena 1
Bernhard Pfahringer 1
Jie Tang 1
Philippe De Wilde 1
Rodrygo Santos 1
Gerhard Tröster, 1
Zhifeng Li 1
Qi Liu 1
Jiaul Paik 1
Daniel Gatica-Perez 1
Markus Strohmaier 1
Dominik Benz 1
Elad Yom-Tov 1
Haofen Wang 1
Ethan Trewhitt 1
Chongjie Zhang 1
Phillip DiBona 1
Martin Hofmann 1
Vivekanand Gopalkrishnan 1
Szuhao Huang 1
Shanghong Lai 1
Thomas Tran 1
Zhiyuan Liu 1
Marina Spivak 1
Lawrence Saul 1
Wei Chen 1
RubéN Lara 1
Dell Zhang 1
Edleno Moura 1
Erik Saule 1
Hang Li 1
Evangelos Milios 1
Inderjit Dhillon 1
Vanja Josifovski 1
Lance Riedel 1
William Groves 1
Frederic Font 1
Yinting Wang 1
Jiadong Zhang 1
Tao Guan 1
Liya Duan 1
Chongyu Chen 1
Meng Wang 1
Haiyan Li 1
Nan Dong 1
Fanchieh Cheng 1
Fabrizio Silvestri 1
Guodong Guo 1
Haiwei Dong 1
Kartik Talamadupula 1
Alessandro Saffiotti 1
Daniel Neill 1
Hong Liu 1
Steven Reece 1
Hoda Sepehri Rad 1
Vincentwenchen Zheng 1
Andrew Sung 1
Mengyu Qiao 1
Jiebo Luo 1
Karen Haigh 1
Jaegil Lee 1
Roland Kays 1
Joshua Plotkin 1
Shyam Boriah 1
Christopher Potter 1
Zhenyu Lu 1
Qiusha Zhu 1
Xi Li 1
Zhongfei Zhang 1
Anton Hengel 1
Brandon Gozick 1
Chewlim Tan 1
Nitesh Chawla 1
Elisabeth Weiss 1
Hannes Wolf 1
Yugyung Lee 1
Deendayal Dinakarpandian 1
Klaus Herrmann 1
Jiang Bian 1
Rong Yan 1
Xiangyu Wang 1
Chang Tan 1
Sashi Gurung 1
Oukhellou Latifa 1
Yashar Moshfeghi 1
Peng Dai 1
Nicoletta Fornara 1
Michael Wooldridge 1
Goran Radanovic 1
Viviana Patti 1
Lingjing Hu 1
Cristiano Castelfranchi 1
Yiqun Hu 1
Liu Wenyin 1
Jiqing Han 1
Tieran Zheng 1
Ofrit Lesser 1
Luigi Caro 1
Jiawei Han 1
John Debenham 1
Liubin Wang 1
Alen Docef 1
Ana Martínez-García 1
Md Seddiqui 1
Huibo Wang 1
Erik Edrosa 1
Guande Qi 1
Dingkun Ma 1
Nithya Ramanathan 1
D George 1
Aijun Bai 1
Ying Xu 1
Randy Goebel 1
Mark Beattie 1
Alice Chan 1
Benjamin Bornstein 1
Michele Judd 1
Homer Chen 1
Xilin Chen 1
Yohan Jin 1
Xin Sun 1
Pietro Pala 1
Junming Xu 1
Guiguang Ding 1
Yushi Lin 1
Dietmar Jannach 1
Hitoshi Yamamoto 1
Xiaohua Liu 1
Ming Zhou 1
Ruiqiang Zhang 1
Keyi Shen 1
Yiping Han 1
Pavel Serdyukov 1
Christine Parent 1
Kouzou Ohara 1
Yuval Marton 1
Trevor Cohn 1
Chang Hu 1
Katrin Erk 1
Steven Burrows 1
David Newman 1
Padhraic Smyth 1
Kostas Kolomvatsos 1
Stathes Hadjiefthymiades 1
Albert Bifet 1
Weinan Zhang 1
Fabiano BeléM 1
Jintao Ye 1
Dihong Gong 1
Hweepink Tan 1
Domonkos Tikk 1
Marco Baroni 1
Benno Stein 1
Steffen Becker 1
Denis Helic 1
Roman Kern 1
Charles Parker 1
Ugur Kuter 1
Daniel Corkill 1
Daniel Tran 1
Robert Pappalardo 1
Vasant Dhar 1
Yuzhou Zhang 1
Edward Chang 1
Gilles Gasso 1
Rómer Rosales 1
Bo Liu 1
Itamar Hata 1
Si Liu 1
Ping Tan 1
Chiyin Chow 1
Ingemar Cox 1
Houqiang Li 1
Qiang Chen 1
Jinfeng Zhuang 1
Marek Lipczak 1
Vishvas Vasuki 1
Berkant Savas 1
Lei Tang 1
Juan Rogers 1
Yingying Jiang 1
Michele Gelfand 1
Jingdong Wang 1
Sheng Li 1
Evgeniy Gabrilovich 1
Joan Serrà 1
Bowei Chen 1
Jianfei Cai 1
Yang Yang 1
Bruce Elder 1
Ranieri Baraglia 1
Wenbin Chen 1
Chunyan Miao 1
Fan Liu 1
Zhen Hai 1
Paul McKevitt 1
Marc Cavazza 1
Fred Charles 1
Éric Beaudry 1
Elias Bareinboim 1
Hua Chen 1
Xiaohua Zhou 1
Jixue Liu 1
Miaojing Shi 1
Gem Stapleton 1
Beryl Plimmer 1
Bernadette Bouchon-Meunier 1
Kyle Feuz 1
Chidansh Bhatt 1
Guojun Qi 1
Jie Yu 1
Yimin Zhang 1
Fusun Yaman 1
Debprakash Patnaik 1
Zhenhui Li 1
Sarvapali Ramchurn 1
Melinda Gervasio 1
Sudhakar Reddy 1
Michael Iatauro 1
Ashish Garg 1
Yu Zhu 1
Meiyu Huang 1
Jonathan Doherty 1
Zhou Jin 1
Takashi Washio 1
Peter Rodgers 1
Sahar Changuel 1
Yuan Zhou 1
Lei Wu 1
Jia Liu 1
Paolo Cagnoli 1
Massimiliano Cattafi 1
Bart Peintner 1
Tomasz Stepinski 1
Chunhua Shen 1
Ram Dantu 1
Gregory Cooper 1
Vincenzo D'Elia 1
Kurt Rothermel 1
Yicheng Chen 1
Matthijs Leeuwen 1
Yi Chang 1
Jinpeng Wang 1
Di Fu 1
Neilzhenqiang Gong 1
Dawn Song 1
Marjan Momtazpour 1
Jason Hong 1
Licia Capra 1
Ouri Wolfson 1
Eoghan Furey 1
Aonghus Lawlor 1
Dan Lin 1
Juan Cao 1
Byron Gao 1
Jiashi Feng 1
Teng Li 1
Waitat Fu 1
Matteo Baldoni 1
Boi Faltings 1
Robin Cohen 1
Theodoros Semertzidis 1
Martin Bockle 1
Patrick De Boer 1
Nicolas Labroche 1
Alina Huldtgren 1
Ingrid Heynderickx 1
Jeremiah Folsom-Kovarik 1
Lourenço Bandeira 1
Ricardo Ricardo 1
Tianyu Cao 1
Ari Jónsson 1
Anthony Dick 1
Jiangwen Sun 1
Parisa Rashidi 1
Joydeep Ghosh 1
William Cushing 1
Philip Hendrix 1
John Yen 1
Ameet Talwalkar 1
Ling Huang 1
David Norton 1
Mohammad Bozchalui 1
Jaewon Yang 1
Xingyu Gao 1
Yao Zhao 1
Arpad Berta 1
Chen Luo 1
Mingxuan Yuan 1
Shihwen Huang 1
Nirwan Sharma 1
Frank Dignum 1
Elisabetta Erriquez 1
Scott Gerard 1
Jie Zhang 1
Michael Strintzis 1
Christina Katsimerou 1
Chris Burnett 1
Sae Schatz 1
Hedi Tabia 1
Takashi Ninomiya 1
Qing Li 1
Vien Tran 1
You Xu 1
Weixiong Zhang 1
Chingyung Lin 1
Claudio Schifanella 1
Josh Ying 1
Wenchih Peng 1
Nardine Osman 1
Daniel Sui 1
VS Subrahmanian 1
Zhihui Jin 1
Yang Gao 1
Giulia Bruno 1
Zhengxiang Wang 1
Shunxuan Wang 1
Qi Guo 1
Fabian Abel 1
Wil Van Der Aalst 1
Argimiro Arratia 1
Tao Li 1
Haiyin Shen 1
Yi Wang 1
Zhenlong Sun 1
Patricia Serrano-Alvarado 1
John Champaign 1
Kyumin Lee 1
Hongtai Li 1
Oded Maimon 1
Wangsheng Zhang 1
Brent Longstaff 1
Joshua Selsky 1
Xiaoping Chen 1
Pramod Anantharam 1
Osmar Zaïane 1
Eunju Kim 1
Chris Nugent 1
Jiming Liu 1
Tara Estlin 1
Steve Chien 1
Bernd Freisleben 1
Ning Zhang 1
Lingyu Duan 1
Steffen Rendle 1
Yuchun Shen 1
Fatih Gedikli 1
Guillermo Jiménez-Díaz 1
Hongbin Zha 1
Furu Wei 1
Ya Zhang 1
Zhixian Yan 1
Dipanjan Chakraborty 1
Zhengzheng Pan 1
Bill Dolan 1
Idan Szpektor 1
Philip Resnik 1
Benjamin Bederson 1
Brynjar Gretarsson 1
Shixia Liu 1
Huadong Ma 1
Wei Peng 1
Silvia Chiusano 1
Haodong Yang 1
Yudong Guang 1
Mohamed Bouguessa 1
Bo Zhang 1
Gang Pan 1
Hua Lu 1
David Wilkie 1
George Karypis 1
Jinha Kang 1
Deborah Estrin 1
Bin Guo 1
Alfredo Milani 1
Yihsuan Yang 1
Ralph Ewerth 1
Lingfang Li 1
Hong Chang 1
Ashok Ramadass 1
Belén Díaz-Agudo 1
Ernesto De Luca 1
Wolfgang Nejdl 1
Fernando Diaz 1
Stefano Spaccapietra 1
Bin Xu 1
Diane Cook 1
Marco Mamei 1
Achla Marathe 1
Masahiro Kimura 1
Olivia Buzek 1
Shimei Pan 1
Luigi Di Caro 1
Chengbin Zeng 1
Huamin Qu 1
Ming Hao 1
Eibe Frank 1
Azhar Ibrahim 1
Ibrahim Venkat 1
Changxing Ding 1
Zechao Li 1
Jing Liu 1
Michael Hardegger 1
Qiang Li 1
Yantao Jia 1
Xiaolong Jin 1
Chiachun Lian 1
Wanrong Jih 1
Kristina Lerman 1
Xiaoqinshelley Zhang 1
Tong Sun 1
Weiwei Cui 1
Pierre Rouille 1
Geoffrey Holmes 1
Yuhang Zhao 1
Bingqing Qu 1
Gerd Stumme 1
David Glass 1
Toon De Pessemier 1
Michelle Zhou 1
Liangliang Cao 1
José Cortizo 1
Yong Yu 1
Janardhan Doppa 1
Bhavesh Shrestha 1
Victor Lesser 1
Daniel McFarlane 1
Yosi Mass 1
Hal Daumé 1
Richong Zhang 1
Wenjun Zhou 1
Chihchung Chang 1
Dana Nau 1
Bernardo Huberman 1
Onur Küçüktunç 1
Zhiguo Gong 1
Atesmachew Hailegiorgis 1
Aris Anagnostopoulos 1
Zhenmin Tang 1
Mingli Song 1
Jiajun Bu 1
Ah Tsoi 1
Stevende Jong 1
Yuesong Wang 1
Matthew Kyan 1
Guoyu Sun 1
Paisarn Muneesawang 1
Franco Nardini 1
Yufei Wang 1
Nadia Figueroa 1
Kuiyu Chang 1
Daniel Bryce 1
Michael Verdicchio 1
Paul Schermerhorn 1
Matthias Scheutz 1
Abder Benaskeur 1
James Michaelis 1
James Hendler 1
Geoffrey Levine 1
Zhexuan Song 1
Lukas Mandrake 1
Bin Li 1
Yong Ge 1
Maosong Sun 1
Aristides Gionis 1
Michael Lyu 1
Léon Bottou 1
Patrick Roos 1
Raju Balakrishnan 1
Rushi Bhatt 1
Azin Ashkan 1
Leong U 1
Nagarajan Natarajan 1
Barry Smyth 1
Kevin Mcnally 1
Xufei Wang 1
Huan Liu 1
Hua Wu 1
Thuc Vu 1
Karl Tuyls 1
Yiqiang Chen 1
J Benton 1
Seth Flaxman 1
Furui Liu 1
Zhikun Wang 1
Chao Sun 1
Judea Pearl 1
Lin Liu 1
Bingyu Sun 1
Réjean Plamondon 1
Yuriy Pepyolyshev 1
Aidan Delaney 1
Dhaval Patel 1
Mingbo Zhao 1
Deng Cai 1
Jianke Zhu 1
Xiaofeng Tong 1
Tao Wang 1
Jeremy Frank 1
Chao Chen 1
Meiling Shyu 1
Hang Li 1
Jian Su 1
Chandan Reddy 1
Hamed Valizadegan 1
Alex Smola 1
Na Shan 1
Hadrien Hours 1
Ernst Biersack 1
Patrick Loiseau 1
Saisai Ma 1
Tianzhu Zhang 1
Chao Xu 1
Marina Demeshko 1
Siddhartha Ghosh 1
Yuchin Juan 1
Carla Gomes 1
Michela Milano 1
Ming Ji 1
Yintao Yu 1
Matthew Boyce 1
Michael Steinbach 1
Yang Mu 1
Weiming Hu 1
Bin Chen 1
Jinbo Bi 1
Yu Wu 1
Stephen Armeli 1
Thomas Hoens 1
Wenyuan Zhu 1
Bo Long 1
Lihong Li 1
Waynexin Zhao 1
Bin Wu 1
Jure Leskovec 1
Alena Neviarouskaya 1
Wenning Kuo 1
Alexei Pozdnoukhov 1
Jintao Li 1
Jiankai Sun 1
Zhenfeng Zhu 1
Yanhui Xiao 1
Quan Fang 1
Márk Jelasity 1
Joemon Jose 1
Gianmario Motta 1
Anne Robinson 1
Chris Mellish 1
Rene Van Der Wal 1
Elisa Marengo 1
Yizhou Wang 1
Matthew Johnson 1
Joris Albeda 1
Davide Susta 1
John Doucette 1
Federica Cena 1
Suhyin Lee 1
Nan Li 1
Xiaoming Li 1
Xiangnan Kong 1
Qi He 1
Haizheng Zhang 1
Lester Mackey 1
Kenneth Joseph 1
Rui Zhang 1
Kaixu Liu 1
Shuguang Han 1
Marco Colombetti 1
Pınar Yolum 1
Wiebe Hoek 1
James Lindsey 1
Michalis Lazaridis 1
Isabel Micheel 1
Judith Redi 1
Michele Piunti 1
Cristina Conati 1
Qiang Lu 1
Jyhren Shieh 1
Pasquale De Meo 1
Kamfai Wong 1
Carles Sierra 1
Fabrizio Maggi 1
Yanfang Ye 1
Lifeng Wang 1
Edgar Chávez 1
Chiharold Liu 1
Wendong Wang 1
Daqing Zhang 1
Jie Zhu 1
Hongsuda Tangmunarunkit 1
Juan Cruz 1
Cécile Bothorel 1
J Ooms 1
Faisal Alquaddoomi 1
Runhe Huang 1
Jitao Sang 1
Clement Leung 1
Yuanxi Li 1
David Thompson 1
Qingming Huang 1

Affiliation Paper Counts
Ryukoku University 1
University of Connecticut Health Center 1
University of Lausanne 1
Federal University of Amazonas 1
University of Macedonia 1
Demokritos National Centre for Scientific Research 1
Anhui University 1
National Taitung University Taiwan 1
University of Sheffield 1
Ehime University 1
University of Haifa 1
University of Perugia 1
Joint Institute for Nuclear Research, Dubna 1
Instituto Superior Tecnico 1
University of Auckland 1
Bogazici University 1
University of Houston 1
University of Pennsylvania 1
University of Koblenz-Landau 1
Guangdong University of Technology 1
Northwestern University 1
Smithsonian National Museum of Natural History 1
Hebrew University of Jerusalem 1
Duke University 1
Vrije Universiteit Amsterdam 1
Hong Kong Polytechnic University 1
Birkbeck University of London 1
Educational Testing Service 1
IBM Almaden Research Center 1
Wayne State University 1
Northeast Normal University China 1
Central European University 1
Harvard University 1
University of Arizona 1
Rissho University 1
The University of British Columbia 1
Dartmouth College 1
Hohai University 1
The University of Western Ontario 1
Citigroup 1
Lingnan University 1
King's College London 1
Center for Mathematics and Computer Science - Amsterdam 1
University of Messina 1
University of Shizuoka 1
Open University 1
Aoyama Gakuin University 1
United States National Science Foundation 1
Ionian University 1
University of Passau 1
Eastman Kodak Company 1
University of Saskatchewan 1
University of Washington 1
General Electric Company 1
New York State Museum 1
Beijing Institute of Technology 1
Charles Stark Draper Lab Inc 1
University of Sussex 1
Defence Research and Development Canada 1
Nankai University 1
Washington State University Pullman 1
Office of Naval Research 1
Singapore Management University 1
Polytechnic School of Montreal 1
Netherlands Organisation for Applied Scientific Research - TNO 1
Binghamton University State University of New York 1
American University 1
Massachusetts General Hospital and Harvard Medical School 1
University of Surrey 1
Nanjing University of Aeronautics and Astronautics 1
Aalborg University 1
Naresuan University 1
University of Bari 1
Politecnico di Milano 1
Shanghai University 1
Soka University 1
Ecole Centrale Paris 1
National University of Defense Technology China 1
University of Fribourg 1
National Central University Taiwan 1
Dublin City University 1
Catholic University of Leuven 1
The University of North Carolina at Chapel Hill 1
University of Cincinnati 1
University of Udine 1
Institute of Intelligent Machines Chinese Academy of Sciences 1
Capital Medical University China 1
United States Military Academy 1
University of Quebec in Montreal 1
Berlin University of Applied Sciences 1
Fairleigh Dickinson University 1
Research Organization of Information and Systems National Institute of Informatics 1
University of Hawaii System 1
University of Southern California 1
European Space Agency - ESA 1
Institute of Applied Physics and Computational Mathematics 1
Columbia University 1
Texas State University-San Marcos 1
Ecole des Mines de Paris 1
Hosei University 1
Rutgers University 1
Boeing Corporation 1
Santa Fe Institute 1
Michigan State University 1
University of Western Australia 1
Indian Institute of Technology Roorkee 1
Korea Advanced Institute of Science & Technology 1
North Dakota State University 1
University of Electro-Communications 1
University of Roma La Sapienza 1
Pontifical Catholic University of Rio de Janeiro 1
University of Jyvaskyla 1
University of Chittagong 1
Nanjing University 1
University of Seville 1
Mehran University of Engineering & Technology 1
University of Sousse 1
Nanjing University of Information Science and Technology 1
Know-Center, Graz 1
Institute for Cancer Research and Treatment, Candiolo 1
Reykjavik University 1
Macau University of Science and Technology 1
Google Switzerland GmbH 1
Intel Research Laboratories 1
Nanyang Technological University School of Computer Engineering 1
Florida Institute for Human & Machine Cognition 1
Fujitsu America, Inc. 1
Shandong University of Finance 1
Shandong Academy of Sciences 1
Laboratoire d'Informatique de Nantes-Atlantique 1
Liverpool Hope University 1
Qatar Foundation 1
Shenzhen University 2
University of Texas at Arlington 2
King Abdulaziz University 2
University of Lugano 2
University of Missouri-Kansas City 2
University of Wolverhampton 2
University of Texas at El Paso 2
University of Brighton 2
Utrecht University 2
National University of Ireland, Galway 2
University of Massachusetts Dartmouth 2
Universite des Sciences et Technologies de Lille 2
University of Kent 2
Technical University of Berlin 2
University of Zurich 2
King Saud University 2
Telecom Bretagne 2
Aston University 2
Aristotle University of Thessaloniki 2
University of Southern California, Information Sciences Institute 2
Dalhousie University 2
National Tsing Hua University 2
Xiamen University 2
George Mason University 2
Technical University of Dresden 2
Tamkang University 2
University of Nebraska at Omaha 2
University of Bristol 2
Communication University of China 2
Ecole d' Ingenieurs Telecom Lille 1 2
University of Central Florida 2
Waseda University 2
Lancaster University 2
University of Massachusetts Boston 2
University of Ferrara 2
Sam Houston State University 2
Xidian University 2
University of Oxford 2
University of Edinburgh 2
Jerusalem College of Technology 2
Hungarian Academy of Sciences 2
New Mexico Institute of Mining and Technology 2
University of Athens 2
Universite de Rennes 1 2
University of California System 2
NEC Corporation 2
Universitat Pompeu Fabra 2
University of Dortmund 2
Intel Corporation 2
American University of Beirut 2
Universite Paris-Est 2
Telecom & Management SudParis 2
SRI International 3
Universiti Sains Malaysia 3
Universite Pierre et Marie Curie 3
University of Glasgow 3
University of Texas at San Antonio 3
University College Dublin 3
Tel Aviv University 3
Brigham Young University 3
The University of North Carolina at Charlotte 3
Universitat Politecnica de Catalunya 3
Orebro University 3
University of Wyoming 3
University of Texas at Dallas 3
Washington State University 3
Free University of Bozen-Bolzano 3
Universidad Politecnica de Valencia 3
Changchun University of Technology 3
BBN Technologies 3
Philipps-Universitat Marburg 3
Beihang University 3
Georgia Tech Research Institute 3
University of Washington Seattle 3
University of Stuttgart 3
IBM Thomas J. Watson Research Center 3
Kassel University 3
Wright State University 3
Simon Fraser University 3
CSIC - Instituto de Investigacion en Inteligencia Artificial 3
Xerox Corporation 3
Graz University of Technology 3
New York University 3
Massachusetts Institute of Technology 3
University of Macau 3
University of Connecticut 3
University of North Texas 3
Universite Paris-Sud XI 3
University of Utah 3
University of Konstanz 3
University of Teesside 3
Huazhong University of Science and Technology 3
Center For Research And Technology - Hellas 3
Stony Brook University 3
University of Szeged 3
University of Bologna 3
EURECOM Ecole d'Ingenieurs & Centre de Recherche en Systemes de Communication 3
University of California, San Diego 3
Utah State University 3
University of Wisconsin Madison 3
Ghent University 3
Intel Corp., China 3
Istituto di Scienza e Tecnologie dell'Informazione A. Faedo 3
Rutgers University-Newark Campus 4
New Mexico State University Las Cruces 4
Institute for Infocomm Research, A-Star, Singapore 4
Bar-Ilan University 4
Hefei University of Technology 4
Toyohashi University of Technology 4
Ohio State University 4
Northwestern Polytechnical University China 4
University of Waikato 4
University of Vermont 4
University of Adelaide 4
Stanford University 4
University of Florida 4
University of Pavia 4
University of Trento 4
University of Liverpool 4
Indiana University 4
West Virginia University 4
University of Notre Dame 4
University of Florence 4
University of Tehran 4
Swiss Federal Institute of Technology, Zurich 4
National University of Ireland, Maynooth 4
Microsoft 4
University of Melbourne 4
Complutense University of Madrid 4
Sharif University of Technology 4
University of Ottawa, Canada 4
University of California, Santa Barbara 4
University of Miami 4
Eindhoven University of Technology 4
Cornell Tech 4
Lockheed Martin 5
North Carolina State University 5
Google Inc. 5
University of California, Irvine 5
Soochow University 5
Istituto Di Scienze E Tecnologie Della Cognizione, Rome 5
City University of Hong Kong 5
University of Massachusetts Amherst 5
National Cheng Kung University 5
University of Pittsburgh 5
University College London 5
Beijing Jiaotong University 5
Osaka University 5
Missouri University of Science and Technology 5
Rensselaer Polytechnic Institute 5
TELECOM ParisTech 5
Max Planck Institute for Intelligent Systems 5
Shandong University 5
Yahoo Research Barcelona 5
Pennsylvania State University 6
Virginia Commonwealth University 6
Washington University in St. Louis 6
National Taipei University of Technology 6
Hong Kong Baptist University 6
NEC Laboratories America, Inc. 6
Texas A and M University 6
University of Southampton 6
Biblioteca CICESE 6
University of Alberta 6
Ryerson University 6
University of South Australia 6
Oregon State University 7
Institute of Automation Chinese Academy of Sciences 7
University of Ulster 7
Universidad Autonoma de Madrid 7
HP Labs 8
National Chiao Tung University Taiwan 8
Roma Tre University 8
Drexel University 8
University of Aberdeen 8
University of California, Berkeley 8
Virginia Tech 8
Swiss Federal Institute of Technology, Lausanne 8
Chinese University of Hong Kong 9
NASA Ames Research Center 9
Hong Kong University of Science and Technology 9
University of Texas at Austin 9
University of Waterloo 9
University of Illinois at Chicago 9
Bauhaus University Weimar 9
University of Minnesota Twin Cities 9
University of Turin 10
Beijing University of Posts and Telecommunications 10
Georgia Institute of Technology 10
Federal University of Minas Gerais 10
Nanjing University of Science and Technology 11
University of Technology Sydney 11
Nokia 11
Carnegie Mellon University 11
Zhejiang University 12
Delft University of Technology 12
Shanghai Jiaotong University 12
Polytechnic Institute of Turin 13
Florida International University 13
University of Tokyo 14
Tsinghua University 14
University of California, Los Angeles 14
Yahoo Research Labs 14
Nanyang Technological University 15
Ben-Gurion University of the Negev 15
Institute of Computing Technology Chinese Academy of Sciences 15
Arizona State University 16
Harbin Institute of Technology 17
Microsoft Research 17
University of Illinois at Urbana-Champaign 20
National Taiwan University 21
Microsoft Research Asia 21
Peking University 22
Jet Propulsion Laboratory 24
IBM Research 24
University of Maryland 25
National University of Singapore 27
Chinese Academy of Sciences 27
University of Science and Technology of China 32

ACM Transactions on Intelligent Systems and Technology (TIST) Archive


Volume 7 Issue 4, May 2016  Issue-in-Progress
Volume 7 Issue 3, April 2016 Regular Papers, Survey Papers and Special Issue on Recommender System Benchmarks
Volume 7 Issue 2, January 2016 Special Issue on Causal Discovery and Inference


Volume 7 Issue 1, October 2015
Volume 6 Issue 4, August 2015 Regular Papers and Special Section on Intelligent Healthcare Informatics
Volume 6 Issue 3, May 2015 Survey Paper, Regular Papers and Special Section on Participatory Sensing and Crowd Intelligence
Volume 6 Issue 2, May 2015 Special Section on Visual Understanding with RGB-D Sensors
Volume 6 Issue 1, April 2015
Volume 5 Issue 4, January 2015 Special Sections on Diversity and Discovery in Recommender Systems, Online Advertising and Regular Papers


Volume 5 Issue 3, September 2014 Special Section on Urban Computing
Volume 5 Issue 2, April 2014 Special Issue on Linking Social Granularity and Functions


Volume 5 Issue 1, December 2013 Special Section on Intelligent Mobile Knowledge Discovery and Management Systems and Special Issue on Social Web Mining
Volume 4 Issue 4, September 2013 Survey papers, special sections on the semantic adaptive social web, intelligent systems for health informatics, regular papers
Volume 4 Issue 3, June 2013 Special Sections on Paraphrasing; Intelligent Systems for Socially Aware Computing; Social Computing, Behavioral-Cultural Modeling, and Prediction
Volume 4 Issue 2, March 2013 Special section on agent communication, trust in multiagent systems, intelligent tutoring and coaching systems
Volume 4 Issue 1, January 2013 Special section on twitter and microblogging services, social recommender systems, and CAMRa2010: Movie recommendation in context


Volume 3 Issue 4, September 2012
Volume 3 Issue 3, May 2012
Volume 3 Issue 2, February 2012


Volume 3 Issue 1, October 2011
Volume 2 Issue 4, July 2011
Volume 2 Issue 3, April 2011
Volume 2 Issue 2, February 2011
Volume 2 Issue 1, January 2011


Volume 1 Issue 2, November 2010
Volume 1 Issue 1, October 2010
All ACM Journals | See Full Journal Index