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.

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.

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.

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.

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.

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.

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.

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 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.

R. Want and B. N. Schilit

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.

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.

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.

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.

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.

Available at the ACM Digital Library here

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.

R. Wakikawa, J. Trevor, B. N. Schilit, J. Boreczky.