Augmented Reality is increasingly explored as the new medium for two-way remote collaboration applications to guide the participants more effectively and efficiently via visual instructions. As users strive for more natural interaction and automation in augmented reality applications, new visual recognition techniques are needed to enhance the user experience. Although simple object recognition is often used in augmented reality towards this goal, most collaboration tasks are too complex for such recognition algorithms to suffice. In this paper, we propose a fine-grained visual recognition approach for mobile augmented reality, which leverages RGB video frames and sparse depth feature points identified in real-time, as well as camera pose data to detect various visual states of an object. We demonstrate the value of our approach through a mobile application designed for hardware support, which automatically detects the state of an object to present the right set of information in the right context.

While existing visual recognition approaches, which rely on 2D images to train their underlying models, work well for object classification, recognizing the changing state of a 3D object requires addressing several additional challenges. This paper proposes an active visual recognition approach to this problem, leveraging camera pose data available on mobile devices. With this approach, the state of a 3D object, which captures its appearance changes, can be recognized in real time. Our novel approach selects informative video frames filtered by 6-DOF camera poses to train a deep learning model to recognize object state. We validate our approach through a prototype for Augmented Reality-assisted hardware maintenance.

This paper presents our initial efforts towards building a cognitive analytics framework for change management. We propose a novel predictive algorithm for change risk calculation based on historical change failures, server failures, change triggered incidents as well as expert user input. Our predictive algorithm provides significant improvement over traditional risk assessments in proactively capturing problematic changes when tested with real client account data.

IT service providers are faced with a dilemma when trying to ensure proper function and effective operation of their clients' infrastructure. On one hand, frequent changes to the IT infrastructure are required to ensure smooth operation; on the other hand, studies show that changes are responsible for 80% of all incidents that result in client outages. This paper proposes a novel methodology for investigating the role of change in incident prevention. We provide a detailed analysis of the change-incident space, offer algorithms on linking incidents to changes that caused them, and show how such data can be effectively used to build predictive models for incident prevention. We conclude by presenting our methodology applied to a real-world dataset and use cases.

It is common knowledge in the IT service domain that changes to the system configuration are responsible for a major portion of incidents that result in client outages. However, it is typically very difficult to establish a relationship between changes and incidents as proper documentation takes lower priority at change creation time, as well as during incident management, in order to deal with the tremendous time pressure to quickly implement changes and resolve incidents. As a result, it is often not possible to leverage historical data to perform retrospective analysis to identify any emerging trends linking changes to incidents, or to build predictive models for proactive incident prevention at change creation time. In this paper, we present an approach for establishing causality between changes and incidents through an ensemble of statistics, data classification, and natural language processing techniques. We demonstrate our approach with a real world example.

Recent years have seen a major increase in the application of predictive analytics to the service delivery domain as more and more service providers rely on such analytics for proactive risk management. At the pre-contract stage, identifying potential project risks accurately is of vital importance since it allows service providers to avoid profit erosion through proactive risk management. This paper describes a data-driven approach to project failure prediction of complex information technology (IT) projects. We introduce a novel theoretical framework of Latent Trait Analysis (LTA), whose original form was first developed in psychometrics. We take as the input questionnaire data of risk assessment reviews in the quality assurance (QA) process of IT projects before contract signing, and attempt to predict the project health in the delivery phase after contract signing. The idea is to explicitly capture the human cognitive process through LTA, and estimate the latent project failure tendency hidden behind the questionnaire answers collected by QA experts. Using real QA data of an IT service provider, we demonstrate that our approach outperforms existing approaches in project failure prediction while providing practical information on the usefulness of individual question items.

This paper describes a novel approach for identifying IT outsourcing contract renewal risk ahead of contract expiration by taking into account not only client satisfaction survey results (in the form of numeric scores), but also client interview transcripts (in the form of unstructured text). By using machine learning techniques, the interview transcripts are automatically processed to identify important topics of interest along with an associated sentiment for each topic. The output of the sentiment analysis is then used as an input (in addition to client satisfaction survey scores) to classify contract renewal risk. We show that, by using sentiment analysis to transform unstructured textual information into structured input, the classification accuracy of non-renewing contracts, in particular, is substantially enhanced. Moreover, the topics with negative sentiments can shed light on the root causes of problems leading to contract non-renewal.

This application track paper describes the Change Risk Expert (CRE) tool, which is designed to help reduce change failure rates. CRE assists Change Requesters to adequately plan changes by semi- automatically classifying change tickets, by informing about past failure rates and reasons, by systematically managing change risks, and by providing standard change implementation plans.

Consumers are increasingly relying on Web-based social content, such as product reviews, prior to making to a purchase. Recent surveys in the retail industry confirm that social content is indeed the #1 aid in a buying decision. Currently, accessing or adding to this valuable Web-based social content repository is mostly limited to computers far removed from the site of the shopping experience itself. We present a mobile augmented reality application, which extends such social content from the computer monitor into the physical world through mobile phones, providing consumers with in situ information on products right when and where they need to make buying decisions.

In many technical support systems, live support agents help end-users resolve issues with computer software/hardware and appliances/gadgets in the real world. The dominant mode of communication in such systems is still the telephone, while instant messaging, video communication, and remote take-over have emerged as additional modalities in recent years. In contrast to these, 3D avatar based visual co-presence offers a unique combination of gestural interaction, shared reality, agent multitasking, and anonymity. Our paper argues that such 3D co-presence is viable in computer chat/remote help sessions, as well as real world support over camera equipped devices, offering an attractive alternative and enhancement to today's support modalities.

We present a set of techniques that enable mobile users to visualize and navigate complex hypermedia structures embedded in the real world, through augmented reality or virtual reality. Situating hypermedia in the 3D physical environment makes it possible to represent information about users' surroundings in context. However, it requires addressing a new set of problems beyond those of visualizing hypermedia on a 2D display: Nodes and links can potentially be distributed across large distances, and may be occluded by other objects, both real and virtual. Our techniques address these issues by enabling mobile users to select and manipulate portions of the hypermedia structure by tilting, lifting and shifting them, to view more clearly links and nodes that would otherwise be occluded or ambiguously connected.

We present a set of mobile augmented reality interaction techniques for authoring situated media: multimedia and hypermedia that are embedded within the physical environment. Our techniques are designed for use with a tracked hand-held tablet display with an attached camera, and rely on "freezing" the frame for later editing.

Several researchers have pointed out and begun to demonstrate that it is now possible to digitize an entire lifetime of experiences into a pocket-sized storage device, and thus to create a rich and portable electronic chronicle of an individual's life and activities. This possibility has brought with it a host of significant challenges: How can the creation of these electronic chronicles be natural and effortless? How should these chronicles be organized? What kinds of navigation and search tools unleash the potential of the chronicled data allowing the user to receive and retrieve the information most relevant to their context at any time? How can such chronicles impact business organizations? How can people in organizations share chronicles and effectively combine chronicled data from different individuals in collaborative settings? Our research is beginning to address these issues with a focus on the business organizational setting. In this paper we introduce PICASSO, our work on pervasive chronicle creation and exploitation in enterprise applications. PICASSO enables the capture of rich user context (including PC/PDA interactions, audio, video, images, and location) and provides tools that enable users to search, navigate, share, and merge personal events, both from desktop computers and from mobile devices