Publications

FXPAL publishes in top scientific conferences and journals.

2002

The Elusive Ubiquitous Information System and m-Links

Publication Details
  • Fuji Xerox Technical Report, No. 14, 2002
  • Jun 25, 2002

Abstract

Close
A basic objective of Weiser's Ubiquitous Computing vision is ubiquitous information access: being able to utilize any content or service (e.g., all the rich media content and services on the WWW), using devices that are always "at hand" (embedded in environments or portable), over a network with universal coverage and adequate bandwidth. Although much progress has been made, the ideal remains elusive. This paper examines the inter-relations among three dimensions of ubiquitous information systems: (1) ubiquitous content; (2) ubiquitous devices; and (3) ubiquitous networking. We use the space defined by these dimensions to reflect on the tradeoffs designers make and to chart some past and current information systems. Given this background, we present m-Links (mobile links), a new system that takes aim at the elusive ideal of ubiquitous information. Our approach builds on wireless web phone technologies because of their trend towards ubiquitous devices and networking (the second and third dimensions). Yet such very small devices sacrifice usability as rich media Internet terminals (the first dimension). To offset this limitation, we propose a new information access model for very small devices that supports a much wider range of content and services than previously possible. We have built this system with an emphasis on open systems extensibility and describe its design and implementation.

Going Back in Hypertext

Publication Details
  • Proceedings of ACM Hypertext 2002
  • Jun 11, 2002

Abstract

Close
Hypertext interfaces typically involve navigation, the act (and interaction) of moving from one piece of information to another. Navigation can be exploratory, or it may involve backtracking to some previously-visited node. While backtracking interfaces are common, they may not reflect differences in readers' purposes and mental models. This paper draws on some empirical evidence regarding navigation between and within documents to suggest improvements on traditional hypertext navigation, and proposes a time-based view of backtracking.
Publication Details
  • Journal of Library Administration, 35:1-2, 99-123, Haworth
  • Jun 7, 2002

Abstract

Close
In the emerging world of electronic publishing how we create, distribute, and read books will be in a large part determined by an underlying framework of content standards that establishes the range of technological opportunities and constraints for publishing and reading systems. But efforts to develop content standards based on sound engineering models must skillfully negotiate competing and sometimes apparently irreconcilable objectives if they are to produce results relevant to the rapidly changing course of technology. The Open eBook Forum's Publication Structure, an XML-based specification for electronic books, is an example of the sort of timely and innovative problem solving required for successful real-world standards development. As a result of this effort, the electronic book industry will not only happen sooner and on a larger scale than it would have otherwise, but the electronic books it produces will be more functional, more interoperable, and more accessible to all readers. Public interest participants have a critical role in this process.
Publication Details
  • CHI 2002
  • Apr 22, 2002

Abstract

Close
Shared text input is a technique we implemented into a note taking system for facilitating text entry on small devices. Instead of writing out words on the tedious text entry interfaces found on handheld computers, users can quickly reuse words and phrases already entered by others. Sharing notes during a meeting also increases awareness among note takers. We found that filtering the text to share was appropriate to deal with a variety of design issues such as screen real estate, scalability, privacy, reciprocity, and predictability of text location
Publication Details
  • CHI 2002
  • Apr 22, 2002

Abstract

Close
In this paper, we describe an evaluation of the Palette, a presentation tool that was reported at CHI '99. The Palette allows presenters to quickly access digital presentations using physical cards that have unique barcodes printed on them. The Palette has been in use in our lab for over three years, and has been released as a product in Japan. Our evaluation consists of an analysis of usage logs, an expert walkthrough review, and observations and interviews with users, non-users and the system administrator. The findings reveal benefits and drawbacks of the technology, and offers design ideas for further work on tangible tools of this kind.
Publication Details
  • International Journal of Human-Computer Studies, 56, pp. 75-107
  • Feb 1, 2002

Abstract

Close
We describe our experiences with the design, implementation, deployment, and evaluation of a Portholes tool which provides group and collaboration awareness through the Web. The research objective was to explore how such a system would improve communication and facilitate a shared understanding among distributed development groups. During the deployment of our Portholes system, we conducted a naturalistic study by soliciting user feedback and evolving the system in response. Many of the initial reactions of potential users indicated that our system projected the wrong image so that we designed a new version that provided explicit cues about being in public and who is looking back to suggest a social rather than information interface. We implemented the new design as a Java applet and evaluated design choices with a preference study. Our experiences with different Portholes versions and user reactions to them provide insights for designing awareness tools beyond Portholes systems. Our approach is for the studies to guide and to provide feedback for the design and technical development of our system.
2001
Publication Details
  • In Workshop on Identifying Objects Across Variations in Lighting: Psychophysics & Computation, Proc. IEEE Intl. Conf. on Computer Vision & Pattern Recognition 2001.
  • Dec 12, 2001

Abstract

Close
In this paper, we document an extension to traditional pattern-theoretic object templates to jointly accommodate variations in object pose and in the radiant appearance of the object surface. We first review classical object templates accommodating pose variation. We then develop an efficient subspace representation for the object radiance indexed on the surface of the three dimensional object template. We integrate the low-dimensional representation for the object radiance, or signature, into the pattern-theoretic template, and present the results of orientation estimation experiments. The experiments demonstrate both estimation performance fluctuations under varying illumination conditions and performance degradations associated with unknown scene illumination. We also present a Bayesian approach for estimation accommodating illumination variability.

Work/place: mobile technologies and arenas of activity

Publication Details
  • ACM SIGGROUP Bulletin, Volume 22, Issue 3, Pp3-9, Publisher ACM Press, New York, NY, USA
  • Dec 8, 2001

Abstract

Close
The increasing number of wireless, portable devices has led inevitably to lyrical rhetorics of business cost-cutting and increased efficiency as workers can be productive while on the and offices become streamlined areas of efficient activity. In this short paper, we raise a number if issues that have been appearing in common discourses the (most) modern office, and the impact of wireless technologies thereupon. We also present an overview of a workshop held at ECSCW in Bonn in September of 2001 on this topic, giving an overview of the comments and discussions that took place at the workshop.

Framing Mobile Collaborations and Mobile Technologies.

Publication Details
  • In B. Brown, N. Green, R. Harper (Eds.) Wireless World: Social and Interactional Aspects of Wireless Technology, London, UK: Springer-Verlag.
  • Dec 1, 2001

Abstract

Close
Recent years have seen a marked increase in the production and promotion of portable, wireless communication devices: mobile phones with internet access, wireless PDAs such as the Palm VII and smart pagers such as RIM's 850 and 950. Some claim the presence of such devices in the hands, bags and pockets of so many people heralds a new world of work in which people can be reached and information accessed "anywhere, anytime". Whether or not access to information in itself can promote new working practices, individuals whose lives revolve around movement between work sites have been singled out as an obvious market for such portable wireless communication devices. Using these devices such “mobile workers” can be in touch with colleagues, collaborators and clients "24/7", and still sustain non-work social relationships due, apparently, to their constant connectedness whilst mobile. In this chapter we have two goals. The first is to address the design of mobile technologies. This second is to illustrate our design approach, wherein we consider local practices of technology use, but also the broader cultural context in which technologies are designed, produced, bought, sold, used and redesigned. Our ultimate design aim is to build upon existing practices, but also to consider possibilities for the development of innovative technologies that enable new, complementary, practices.
Publication Details
  • In Proceedings of the International Conference on Image Processing, Thessaloniki, Greece. October 7-10, 2001.
  • Oct 7, 2001

Abstract

Close
In this paper, we present a novel framework for analyzing video using self-similarity. Video scenes are located by analyzing inter-frame similarity matrices. The approach is flexible to the choice of similarity measure and is robust and data-independent because the data is used to model itself. We present the approach and its application to scene boundary detection. This is shown to dramatically outperform a conventional scene-boundary detector that uses a histogram-based measure of frame difference.
Publication Details
  • Proceedings of ACM Multimedia 2001, Ottawa, Canada, Oct. 5, 2001.
  • Oct 5, 2001

Abstract

Close
Given rapid improvements in storage devices, network infrastructure and streaming-media technologies, a large number of corporations and universities are recording lectures and making them available online for anytime, anywhere access. However, producing high-quality lecture videos is still labor intensive and expensive. Fortunately, recent technology advances are making it feasible to build automated camera management systems to capture lectures. In this paper we report our design of such a system, including system configuration, audio-visual tracking techniques, software architecture, and user study. Motivated by different roles in a professional video production team, we have developed a multi-cinematographer single-director camera management system. The system performs lecturer tracking, audience tracking, and video editing all fully automatically, and offers quality close to that of human-operated systems.
Publication Details
  • Proc. ACM Multimedia 2001, Ottawa,CA, Oct. 2001.
  • Sep 30, 2001

Abstract

Close
We describe a system called FlyAbout which uses spatially indexed panoramic video for virtual reality applications. Panoramic video is captured by moving a 360° camera along continuous paths. Users can interactively replay the video with the ability to view any interesting object or choose a particular direction. Spatially indexed video gives the ability to travel along paths or roads with a map-like interface. At junctions, or intersection points, users can chose which path to follow as well as which direction to look, allowing interaction not available with conventional video. Combining the spatial index with a spatial database of maps or objects allows users to navigate to specific locations or interactively inspect particular objects.
Publication Details
  • Proc. International Conference on Computer Music (ICMC), Habana, Cuba, September 2001.
  • Sep 12, 2001

Abstract

Close
This paper presents a novel approach to visualizing the time structure of musical waveforms. The acoustic similarity between any two instants of an audio recording is displayed in a static 2D representation, which makes structural and rhythmic characteristics visible. Unlike practically all prior work, this method characterizes self-similarity rather than specific audio attributes such as pitch or spectral features. Examples are presented for classical and popular music.
Publication Details
  • IEEE Computer, 34(9), pp. 61-67
  • Sep 1, 2001

Abstract

Close

To meet the diverse needs of business, education, and personal video users, the authors developed three visual interfaces that help identify potentially useful or relevant video segments. In such interfaces, keyframes-still images automatically extracted from video footage-can distinguish videos, summarize them, and provide access points. Well-chosen keyframes enhance a listing's visual appeal and help users select videos. Keyframe selection can vary depending on the application's requirements: A visual summary of a video-captured meeting may require only a few highlight keyframes, a video editing system might need a keyframe for every clip, while a browsing interface requires an even distribution of keyframes over the video's full length. The authors conducted user studies for each of their three interfaces, gathering input for subsequent interface improvements. The studies revealed that finding a similarity measure for collecting video clips into groups that more closely match human perception poses a challenge. Another challenge is to further improve the video-segmentation algorithm used for selecting keyframes. A new version will provide users with more information and control without sacrificing the interface's ease of use.

Recording the Region of Interest from FlyCam Panoramic Video

Publication Details
  • Proc. International Conference on Image Processing, Thessaloniki, Greece, September 2001.
  • Sep 1, 2001

Abstract

Close
A novel method for region of interest tracking and recording video is presented. The proposed method is based on the FlyCam system, which produces high resolution and wide-angle video sequences by stitching the video frames from multiple stationary cameras. The method integrates tracking and recording processes, and targets applications such as classroom lectures and video conferencing. First, the region of interest (which typically covers the speaker) is tracked using a Kalman filter. Then, the Kalman filter estimation results are used for virtual camera control and to record the video. The system has no physical camera motion and the virtual camera parameters are readily available for video indexing. The proposed system has been implemented for real time recording of lectures and presentations.

The Beat Spectrum: A New Approach to Rhythm Analysis

Publication Details
  • In Proceedings of the International Conference on Multimedia and Expo 2001 (ICME), Tokyo, Japan. August 22-25, 2001.
  • Aug 25, 2001

Abstract

Close
We introduce the beat spectrum, a new method of automatically characterizing the rhythm and tempo of music and audio. The beat spectrum is a measure of acoustic self-similarity as a function of time lag. Highly structured or repetitive music will have strong beat spectrum peaks at the repetition times. This reveals both tempo and the relative strength of particular beats, and therefore can distinguish between different kinds of rhythms at the same tempo. We also introduce the beat spectrogram which graphically illustrates rhythm variation over time. Unlike previous approaches to tempo analysis, the beat spectrum does not depend on particular attributes such as energy or frequency, and thus will work for any music or audio in any genre. We present tempo estimation results for a variety of musical genres, which are accurate to within 1%. This approach has a variety of applications, including music retrieval by similarity and automatically generating music videos.
Publication Details
  • In Proceedings of Conference on Modeling and Design of Wireless Networks (ITCOM2001), Denver, Colorado, August 23-24 August 2001.
  • Aug 23, 2001

Abstract

Close
This paper reports our design, and implementation of an automatic lecture-room camera-management system. The motivation for building this system is to facilitate online lecture access and reduce the expense of producing high quality lecture videos. The goal of this project is a camera-management system that can perform as a human video-production team. To achieve this goal, our system collects audio/video signals available in the lecture room and uses the multimodal information to direct our video cameras to interesting events. Compared to previous work--which has tended to be technology centric--we started with interviews with professional video producers and used their knowledge and expertise to create video production rules. We then targeted technology components that allowed us to implement a substantial portion of these rules, including the design of a virtual video director, a speaker cinematographer, and an audience cinematographer. The complete system is installed in parallel with a human-operated video production system in a middle-sized corporate lecture room, and used for broadcasting lectures through the web. The systemí*s performance was compared to that of a human operator via a user study. Results suggest that our system's quality is close to that of a human-controlled system.

The impact of text browsing on text retrieval performance

Publication Details
  • Information Processing and Management 37 (3) pp. 507-520
  • Aug 21, 2001

Abstract

Close
The results from a series of three experiments that used Text Retrieval Conference (TREC) data and TREC search topics are compared. These experiments each involved three novel user interfaces (one per experiment). User interfaces that made it easier for users to view text were found to improve recall in all three experiments. A distinction was found between a cluster of subjects (a majority of whom were search experts) who tended to read fewer documents more carefully (readers, or exclusives) and subjects who skimmed through more documents without reading them as carefully (skimmers, or inclusives). Skimmers were found to have significantly better recall overall. A major outcome from our experiments at TREC and with the TREC data, is that hypertext interfaces to information retrieval (IR) tasks tend to increase recall. Our interpretation of this pattern of results across the three experiments is that increased interaction with the text (more pages viewed) generally improves recall. Findings from one of the experiments indicated that viewing a greater diversity of text on a single screen (i.e., not just more text per se, but more articles available at once) may also improve recall. In an experiment where a traditional (type-in) query interface was contrasted with a condition where queries were marked up on the text, the improvement in recall due to viewing more text was more pronounced with search novices. Our results demonstrate that markup and hypertext interfaces to text retrieval systems can benefit recall and can also benefit novices. The challenge now will be to find modified versions of hypertext interfaces that can improve precision, as well as recall and that can work with users who prefer to use different types of search strategy or have different types of training and experience.

m-Links: An Infrastructure for Very Small Internet Devices

Publication Details
  • The 7th Annual International Conference on Mobile Computing and Networking (MOBICOM 2001), Rome, Italy, July 16-21 2001, ACM Press, 2001, pp. 122-131.
  • Jul 16, 2001

Abstract

Close
In this paper we describe the Mobile Link (m-Links) infrastructure for utilizing existing World Wide Web content and services on wireless phones and other very small Internet terminals. Very small devices, typically with 3-20 lines of text, provide portability and other functionality while sacrificing usability as Internet terminals. In order to provide access on such limited hardware we propose a small device web navigation model that is more appropriate than the desktop computers web browsing model. We introduce a middleware proxy, the Navigation Engine, to facilitate the navigation model by concisely displaying the Webs link (i.e., URL) structure. Because not all Web information is appropriately "linked," the Navigation Engine incorporates data-detectors to extract bits of useful information such as phone numbers and addresses. In order to maximize program-data composibility, multiple network-based services (similar to browser plug-ins) are keyed to a links attributes such as its MIME type. We have built this system with an emphasis on user extensibility and we describe the design and implementation as well as a basic set of middleware services that we have found to be particularly important.
Publication Details
  • Proceedings of the INNS-IEEE International Joint Conference on Neural Networks, vol. 3, pp. 2176 - 2181, Washington DC., July 14-19, 2001.
  • Jul 14, 2001

Abstract

Close
The goal of this project is to teach a computer-robot system to understand human speech through natural human-computer interaction. To achieve this goal, we develop an interactive and incremental learning algorithm based on entropy-guided learning vector quantisation (LVQ) and memory association. Supported by this algorithm, the robot has the potential to learn unlimited sounds progressively. Experimental results of a multilingual short-speech learning task are given after the presentation of the learning system. Further investigation of this learning system will include human-computer interactions that involve more modalities, and applications that use the proposed idea to train home appliances.
Publication Details
  • The Eighth IFIP TC.13 Conference On Human-Computer Interaction (INTERACT 2001). Tokyo, Japan, July 9-13, 2001.
  • Jul 9, 2001

Abstract

Close
The two most commonly used techniques for evaluating the fit between application design and use - namely, usability testing and beta testing with user feedback - suffer from a number of limitations that restrict evaluation scale (in the case of usability tests) and data quality (in the case of beta tests). They also fail to provide developers with an adequate basis for: (1) assessing the impact of suspected problems on users at large, and (2) deciding where to focus development and evaluation resources to maximize the benefit for users at large. This paper describes an agent-based approach for collecting usage data and user feedback over the Internet that addresses these limitations to provide developers with a complementary source of usage- and usability-related information. Contributions include: a theory to motivate and guide data collection, an architecture capable of supporting very large scale data collection, and real-word experience suggesting the proposed approach is complementary to existing practice.
Publication Details
  • In Proceedings of Human-Computer Interaction (INTERACT '01), IOS Press, Tokyo, Japan, pp. 464-471
  • Jul 9, 2001

Abstract

Close
Hitchcock is a system to simplify the process of editing video. Its key features are the use of automatic analysis to find the best quality video clips, an algorithm to cluster those clips into meaningful piles, and an intuitive user interface for combining the desired clips into a final video. We conducted a user study to determine how the automatic clip creation and pile navigation support users in the editing process. The study showed that users liked the ease-of-use afforded by automation, but occasionally had problems navigating and overriding the automated editing decisions. These findings demonstrate the need for a proper balance between automation and user control. Thus, we built a new version of Hitchcock that retains the automatic editing features, but provides additional controls for navigation and for allowing users to modify the system decisions.

Designing e-Books for Legal Research.

Publication Details
  • In Proceedings of JCDL 2001 (Roanoke, VA, June 23-27). ACM Press. pp. 41-48.
  • Jun 23, 2001

Abstract

Close
In this paper we report the findings from a field study of legal research in a first-tier law school and on the resulting redesign of XLibris, a next-generation e-book. We first characterize a work setting in which we expected an e-book to be a useful interface for reading and otherwise using a mix of physical and digital library materials, and explore what kinds of reading-related functionality would bring value to this setting. We do this by describing important aspects of legal research in a heterogeneous information environment, including mobility, reading, annotation, link following and writing practices, and their general implications for design. We then discuss how our work with a user community and an evolving e-book prototype allowed us to examine tandem issues of usability and utility, and to redesign an existing e-book user interface to suit the needs of law students. The study caused us to move away from the notion of a stand-alone reading device and toward the concept of a document laptop, a platform that would provide wireless access to information resources, as well as support a fuller spectrum of reading-related activities.
Publication Details
  • Proceedings of ACM CHI2001, vol. 3, pp. 442 - 449, Seattle, Washington, USA, March 31 - April 5, 2001.
  • Apr 5, 2001

Abstract

Close
Given rapid improvements in network infrastructure and streaming-media technologies, a large number of corporations and universities are recording lectures and making them available online for anytime, anywhere access. However, producing high-quality lecture videos is still labor intensive and expensive. Fortunately, recent technology advances are making it feasible to build automated camera management systems to capture lectures. In this paper we report on our design, implementation and study of such a system. Compared to previous work-which has tended to be technology centric-we started with interviews with professional video producers and used their knowledge and expertise to create video production rules. We then targeted technology components that allowed us to implement a substantial portion of these rules, including the design of a virtual video director. The system's performance was compared to that of a human operator via a user study. Results suggest that our system's quality in close to that of a human-controlled system. In fact most remote audience members could not tell if the video was produced by a computer or a person.

Quiet Calls: Talking Silently on Mobile Phones

Publication Details
  • In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 174-181, ACM Press, March 31-April 5, 2001, Seattle, WA.
  • Mar 30, 2001
Publication Details
  • In Proceedings of the Thirty-fourth Annual Hawaii International Conference on System Sciences (HICSS), Big Island, Hawaii. January 7-12, 2001.
  • Feb 7, 2001

Abstract

Close
This paper describes a new system for panoramic two-way video communication. Digitally combining images from an array of inexpensive video cameras results in a wide-field panoramic camera, from inexpensive off-the-shelf hardware. This system can aid distance learning in several ways, by both presenting a better view of the instructor and teaching materials to the students, and by enabling better audience feedback to the instructor. Because the camera is fixed with respect to the background, simple motion analysis can be used to track objects and people of interest. Electronically selecting a region of this results in a rapidly steerable "virtual camera." We present system details and a prototype distance-learning scenario using multiple panoramic cameras.
Publication Details
  • WebNet 2001 World Conference on the WWW and Internet, Orlando, FL
  • Jan 17, 2001

Abstract

Close
As more information is made available online, users collect information in personal information spaces like bookmarks and emails. While most users feel that organizing these collections is crucial to improve access, studies have shown that this activity is time consuming and highly cognitive. Automatic classification has been used but by relying on the full text of the documents, they do not generate personalized classifications. Our approach is to give users the ability to annotate their documents as they first access them. This annotation tool is unobtrusive and welcome by most users who generally miss this facility when dealing with digital documents. Our experiments show that these annotations can be used to generate personalized classifications of annotated Web pages.

Description and Narrative in Hypervideo

Publication Details
  • Proceedings of the Thirty-Fourth Annual Hawaii International Conference on System Sciences
  • Jan 3, 2001

Abstract

Close
While hypertext was originally conceived for the management of scientific and technical information, it has been embraced with great enthusiasm by several members of the literary community for the promises it offers towards new approaches to narrative. Experiments with hypertext-based interactive narrative were originally based solely on verbal text but have more recently extended to include digital video artifacts. The most accomplished of these experiments, HyperCafe, provided new insights into the nature of narrative and how it may be presented; but it also offered an opportunity to reconsider other text types. This paper is an investigation of the application of an approach similar to HyperCafe to a descriptive text. We discuss how the approach serves the needs of description and illustrate the discussion with a concrete example. We then conclude by considering the extent to which our experiences with description may be applied to our continuing interest in narrative.
2000
Publication Details
  • ACM Computing Surveys, Vol. 32 No. 4, December 2000.
  • Dec 1, 2000

Abstract

Close
Modern window-based user interface systems generate user interface events as natural products of their normal operation. Because such events can be automatically captured and because they indicate user behavior with respect to an application's user interface, they have long been regarded as a potentially fruitful source of information regarding application usage and usability. However, because user interface events are typically voluminos and rich in detail, automated support is generally required to extract information at a level of abstraction that is useful to investigators interested in analyzing application usage or evaluating usability. This survey examines computer-aided techniques used by HCI practitioners and researchers to extract usability-related information from user interface events. A framework is presented to help HCI practitioners and researchers categorize and compare the approaches that have been, or might fruitfully be, applied to this problem. Because many of the techniques in the research literature have not been evaluated in practice, this survey provides a conceptual evaluation to help identify some of the relative merits and drawbacks of the various classes of approaches. Ideas for future research in this area are also presented. This survey addresses the following questions: How might user interface events be used in evaluating usability? How are user interface events related to other forms of usability data? What are the key challenges faced by investigators wishing to exploit this data? What approaches have been brought to bear on this problem and how do they compare to one another? What are some of the important open research questions in this area?
Publication Details
  • Multimedia Modeling: Modeling Multimedia Information and Systems, Nagano, Japan
  • Nov 12, 2000

Abstract

Close
While hypermedia is usually presented as a way to offer content in a nonlinear manner, hypermedia structure tends to reinforce the assumption that reading is basically a linear process. Link structures provide a means by which the reader may choose different paths to traverse; but each of these paths is fundamentally linear, revealed through either a block of text or a well-defined chain of links. While there are experiences that get beyond such linear constraints, such as driving a car, it is very hard to capture this kind of non-linearity, characterized by multiple sources of stimuli competing for attention, in a hypermedia document. This paper presents a multi-channel document infrastructure that provides a means by which all such sources of attention are presented on a single "page" (i.e., a display with which the reader interacts) and move between background and foreground in response to the activities of the reader. The infrastructure thus controls the presentation of content with respect to four dimensions: visual, audio, interaction support, and rhythm.
Publication Details
  • In Proceedings of UIST '00, ACM Press, pp. 81-89, 2000.
  • Nov 4, 2000

Abstract

Close
Hitchcock is a system that allows users to easily create custom videos from raw video shot with a standard video camera. In contrast to other video editing systems, Hitchcock uses automatic analysis to determine the suitability of portions of the raw video. Unsuitable video typically has fast or erratic camera motion. Hitchcock first analyzes video to identify the type and amount of camera motion: fast pan, slow zoom, etc. Based on this analysis, a numerical "unsuitability" score is computed for each frame of the video. Combined with standard editing rules, this score is used to identify clips for inclusion in the final video and to select their start and end points. To create a custom video, the user drags keyframes corresponding to the desired clips into a storyboard. Users can lengthen or shorten the clip without specifying the start and end frames explicitly. Clip lengths are balanced automatically using a spring-based algorithm.
Publication Details
  • In Proceedings of the International Symposium on Music Information Retrieval, in press.
  • Oct 23, 2000

Abstract

Close
We introduce an audio retrieval-by-example system for orchestral music. Unlike many other approaches, this system is based on analysis of the audio waveform and does not rely on symbolic or MIDI representations. ARTHUR retrieves audio on the basis of long-term structure, specifically the variation of soft and louder passages. The long-term structure is determined from envelope of audio energy versus time in one or more frequency bands. Similarity between energy profiles is calculated using dynamic programming. Given an example audio document, other documents in a collection can be ranked by similarity of their energy profiles. Experiments are presented for a modest corpus that demonstrate excellent results in retrieving different performances of the same orchestral work, given an example performance or short excerpt as a query.