video files to the education and research community and is distinguished by an innovative user interface that offers multiple kinds of visual surrogates to people searching for video content. The OVDL is used by several thousand people around the world each month and part of this success is due to its user interface. This article examines the interplay between research and practice in the development of this particular digital library with an eye toward lessons for all digital libraries. We argue that theoretical and research goals blur into practical goals and practical goals raise new research questions as research and development progress—this process is akin to walking along a Möbius strip in which a locally two-sided surface is actually part of a globally one-sided world. We consider the gulf between the theories that guide current digital library research and current practice in operational digital libraries, provide a developmental history of the OVDL and the research frameworks that drove its development, illustrate how user studies informed its implementation and revision, and conclude with reflections and recommendations on the interplay between research and practice.

YAXIAO SONG: Multi-modal Surrogates for Retrieving and Making Sense of Videos: Is Synchronization between the Multiple Modalities Optimal? (Under the direction of Dr. Gary Marchionini) Video surrogates can help people quickly make sense of the content of a video before downloading or seeking more detailed information. Visual and audio features of a video are primary information carriers and might become important components of video retrieval and video sense-making. In the past decades, most research and development efforts on video surrogates have focused on visual features of the video, and comparatively little work has been done on audio surrogates and examining their pros and cons in aiding users’ retrieval and sense-making of digital videos. Even less work has been done on multi-modal surrogates, where more than one modality are employed for consuming the surrogates, for example, the audio and visual modalities. This research examined the effectiveness of a number of multi-modal surrogates, and investigated whether synchronization between the audio and visual channels is optimal. A user study was conducted to evaluate six different surrogates on a set of six recognition and inference tasks to answer two main research questions: (1) How do automatically-generated multi-modal surrogates compare to manuallygenerated ones in video retrieval and video sense-making? and (2) Does synchronization between multiple surrogate channels enhance or inhibit video retrieval and

We present a novel approach for summarizing video in the form of a multiscale image that is continuous in both the spatial domain and across the scale dimension: There are no hard borders between discrete moments in time, and a user can zoom smoothly into the image to reveal additional temporal details. We call these artifacts tapestries because their continuous nature is akin to medieval tapestries and other narrative depictions predating the advent of motion pictures. We propose a set of criteria for such a summarization, and a series of optimizations motivated by these criteria. These can be performed as an entirely offline computation to produce high quality renderings, or by adjusting some optimization parameters the later stages can be solved in real time, enabling an interactive interface for video navigation. Our video tapestries combine the best aspects of two common visualizations, providing the visual clarity of DVD chapter menus with the information density and multiple scales of a video editing timeline representation. In addition, they provide continuous transitions between zoom levels. In a user study, participants preferred both the aesthetics and efficiency of tapestries over other interfaces for visual browsing.

We investigate the influence of term selection and query operations on the text retrieval component of video search. Our main finding is that the greatest gain is to be found in the combination of character n-grams, stemmed text, and proximity terms.

We introduce the challenge problem for generic video indexing to gain insight in intermediate steps that affect performance of multimedia analysis methods, while at the same time fostering repeatability of experiments. To arrive at a challenge problem, we provide a general scheme for the systematic examination of automated concept detection methods, by decomposing the generic video indexing problem into 2 unimodal analysis experiments, 2 multimodal analysis experiments, and 1 combined analysis experiment. For each experiment, we evaluate generic video indexing performance on 85 hours of international broadcast news data, from the TRECVID 2005/2006 benchmark, using a lexicon of 101 semantic concepts. By establishing a minimum performance on each experiment, the challenge problem allows for component-based optimization of the generic indexing issue, while simultaneously offering other researchers a reference for comparison during indexing methodology development. To stimulate further investigations in intermediate analysis steps that inuence video indexing performance, the challenge offers to the research community a manually annotated concept lexicon, pre-computed low-level multimedia features, trained classifier models, and five experiments together with baseline performance, which are all available at http://www.mediamill.nl/challenge/.

We have witnessed great interest and a wealth of promise in content-based image retrieval as an emerging technology. While the last decade laid foundation to such promise, it also paved the way for a large number of new techniques and systems, got many new people involved, and triggered stronger association of weakly related fields. In this article, we survey almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation, and in the process discuss the spawning of related subfields. We also discuss significant challenges involved in the adaptation of existing image retrieval techniques to build systems that can be useful in the real world. In retrospect of what has been achieved so far, we also conjecture what the future may hold for image retrieval research.

Typical approaches to the multi-label classification problem require learning an independent classifier for every label from all the examples and features. This can become a computational bottleneck for sizeable datasets with a large label space. In this paper, we propose an efficient and effective multi-label learning algorithm called model-shared subspace boosting (MSSBoost) as an attempt to reduce the information redundancy in the learning process. This algorithm automatically finds, shares and combines a number of base models across multiple labels, where each model is learned from random feature subspace and boots trap data samples. The decision functions for each label are jointly estimated and thus a small number of shared subspace models can support the entire label space. Our experimental results on both synthetic data and real multimedia collections have demonstrated that the proposed algorithm can achieve better classification performance than the non-ensemble baselineclassifiers with a significant speedup in the learning and prediction processes. It can also use a smaller number of base models to achieve the same classification performance as its non-model-shared counterpart.

Traditional program guides, TV applications, and online portals alone are no longer sufficient to expose all content, let alone offer the content that consumers want, at the times they are most likely to want it. DEEP, (Data Enrichment and Engagement Platform) by Orca Interactive, a comprehensive new content discovery solution, combines search, recommendation, and second-screen devices into a single immersive experience which invites exploration. The automated generation (using internet sources) of digital magazines for movies, TV shows, cast members and topics is a key value of DEEP. Unfortunately, using the internet as a source for pictures can result in the acquisition of so-called “Near Duplicate” (ND) images – similar images from a specific display context - for example, multiple red carpet images showing an actor from very similar angles or degrees of zoom on him/her. Therefore, in this paper we present a practical application of ND detection for image databases. The algorithm used is based on the MPEG-7 Colour Structure descriptor. For images that were provided by the developers of the DEEP software the algorithm performs very well, and the results are almost identical to those obtained during the training phase.

Today's ubiquity of visual content as driven by the availability of broadband Internet, low-priced storage, and the omnipresence of camera equipped mobile devices conveys much of our thinking and feeling as individuals and as a society. As a result the growth of video repositories is increasing at enourmous rates with content now being embedded and shared through social media. To make use of this new form of social multimedia, concept detection, the automatic mapping of semantic concepts and video content has to be extended such that concept vocabularies are synchronized with current real-world events, systems can perform scalable concept learning with thousands of concepts, and high-level information such as sentiment can be extracted from visual content. To catch up with these demands the following three contributions are made in this thesis: (i) concept detection is linked to trending topics, (ii) visual learning from web videos is presented including the proper treatment of tags as concept labels, and (iii) the extension of concept detection with adjective noun pairs for sentiment analysis is proposed. In order for concept detection to satisfy users' current information needs, the notion of fixed concept vocabularies has to be reconsidered. This thesis presents a novel concept learning approach built upon dynamic vocabularies, which are automatically augmented with trending topics mined from social media. Once discovered, trending topics are evaluated by forecasting their future progression to predict high impact topics, which are then either mapped to an available static concept vocabulary or trained as individual concept detectors on demand. It is demonstrated in experiments on YouTube video clips that by a visual learning of trending topics, improvements of over 100% in concept detection accuracy can be achieved over static vocabularies (n=78,000). To remove manual efforts related to training data retrieval from YouTube and noise caused by tags being coarse, subjective and context-depedent, this thesis suggests an automatic concept-to-query mapping for the retrieval of relevant training video material, and active relevance filtering to generate reliable annotations from web video tags. Here, the relevance of web tags is modeled as a latent variable, which is combined with an active learning label refinement. In experiments on YouTube, active relevance filtering is found to outperform both automatic filtering and active learning approaches, leading to a reduction of required label inspections by 75% as compared to an expert annotated training dataset (n=100,000). Finally, it is demonstrated, that concept detection can serve as a key component to infer the sentiment reflected in visual content. To extend concept detection for sentiment analysis, adjective noun pairs (ANP) as novel entities for concept learning are proposed in this thesis. First a large-scale visual sentiment ontology consisting of 3,000 ANPs is automatically constructed by mining the web. From this ontology a mid-level representation of visual content – SentiBank – is trained to encode the visual presence of 1,200 ANPs. This novel approach of visual learning is validated in three independent experiments on sentiment prediction (n=2,000), emotion detection (n=807) and pornographic filtering (n=40,000). SentiBank is shown to outperform known low-level feature representations (sentiment prediction, pornography detection) or perform comparable to state-of-the art methods (emotion detection). Altogether, these contributions extend state-of-the-art concept detection approaches such that concept learning can be done autonomously from web videos on a large-scale, and can cope with novel semantic structures such as trending topics or adjective noun pairs, adding a new dimension to the understanding of video content.

Today's medical institutions produce enormous amounts of data on patients, including multimedia data, which is increasingly produced in digital form. These data in their clinical context contain much information and experience that is currently not being used up to its full potential. Through the digital form the data has become accessible for automatic analysis and treatment for a variety of applications. At the same time, the variety of images produced can be confusing even for trained specialists causing an information overload exists for many medical doctors. This suggests that content-based image retrieval can be a valuable tool for helping manage these data and access the right information at the right time. This article gives a short state of the art of content-based medical image retrieval followed by a description of the medGIFT project on image retrieval with its main components. Then, several challenges are used to illustrate areas where much more work is currently needed to advance biomedical image retrieval. This shows that we have now progresses beyond the phase, where medical doctors transfer a database to computer scientists to only evaluate their algorithms. We conclude that visual information retrieval can have a real impact in the medical field if the techniques can adapt to this rapidly changing field and get integrated into the workflow in radiology and other medical fields.

This tutorial lays the foundation for the exciting new horizons that arise when multimedia data can automatically be indexed by its semantic content. It will cover basic video analysis techniques, explain the different methods for video indexing, and explore how users can be given interactive access to the data. For both indexing and interactive access TRECVID evaluations will be considered. Finally, some more insight on the challenges ahead and how to meet them will be presented.

This thesis presents my research concerning audio and video signal processing and machine learning. Specifically, the topics of my research include computationally efficient classifier compounds, automatic speech recognition (ASR), music dereverberation, video cut point detection and video classification. Computational efficacy of information retrieval based on multiple measurement modalities has been considered in this thesis. Specifically, a cascade processing framework, including a training algorithm to set its parameters has been developed for combining multiple detectors or binary classifiers in computationally efficient way. The developed cascade processing framework has been applied on video information retrieval tasks of video cut point detection and video classification. The results in video classification, compared to others found in the literature, indicate that the developed framework is capable of both accurate and computationally efficient classification. The idea of cascade processing has been additionally adapted for the ASR task. A procedure for combining multiple speech state likelihood estimation methods within an ASR framework in cascaded manner has been developed. The results obtained clearly show that without impairing the transcription accuracy the computational load of ASR can be reduced using the cascaded speech state likelihood estimation process. Additionally, this thesis presents my work on noise robustness of ASR using a nonnegative matrix factorization (NMF) -based approach. Specifically, methods for transformation of sparse NMF-features into speech state likelihoods has been explored. The results reveal that learned transformations from NMF activations to speech state likelihoods provide better ASR transcription accuracy than dictionary label -based transformations. The results, compared to others in a noisy speech recognition -challenge show that NMF-based processing is an efficient strategy for noise robustness in ASR. The thesis also presents my work on audio signal enhancement, specifically, on removing the detrimental effect of reverberation from music audio. In the work, a linear prediction -based dereverberation algorithm, which has originally been developed for speech signal enhancement, was applied for music. The results obtained show that the algorithm performs well in conjunction with music signals and indicate that dynamic compression of music does not impair the dereverberation performance.

This paper provides an overview of a pilot evaluation of video summaries using rushes from several BBC dramatic series. It was carried out under the auspices of TRECVID. Twenty-two research teams submitted video summaries of up to 4% duration, of 42 individual rushes video files aimed at compressing out redundant and insignificant material. The output of two baseline systems built on straightforward content reduction techniques was contributed by Carnegie Mellon University as a control. Procedures for developing ground truth lists of important segments from each video were developed at Dublin City University and applied to the BBC video. At NIST each summary was judged by three humans with respect to how much of the ground truth was included, how easy the summary was to understand, and how much repeated material the summary contained. Additional objective measures included: how long it took the system to create the summary, how long it took the assessor to judge it against the ground truth, and what the summary's duration was. Assessor agreement on finding desired segments averaged 78% and results indicate that while it is difficult to exceed the performance of baselines, a few systems did.

This paper proposes a novel temporal data segmentation approach based on a graph partition model. To find the optimal segmentation, which maintains maximal connectivity within the same segment while keeping minimum association between different ones, we adopt the min-max cut as an objective function. For temporal data, a linear time algorithm is designed by importing the temporal constraints. With multi-pair comparison strategy, the proposed method is more robust than the existing pair-wise comparison ones. The experiments on TRECVID benchmarking platform demonstrate the effectiveness of our approach.

This paper presents the semantic pathfinder architecture for generic indexing of video archives. The pathfinder automatically extracts semantic concepts from video based on the exploration of different paths through three consecutive analysis steps, closely linked to the video production process, namely: content analysis, style analysis, and context analysis. The virtue of the semantic pathfinder is its learned ability to find a best path of analysis steps on a per-concept basis. To show the generality of this indexing approach we develop detectors for a lexicon of 32 concepts and we evaluate the semantic pathfinder against the 2004 NIST TRECVID video retrieval benchmark, using a news archive of 64 hours. Top ranking performance indicates the merit of the semantic pathfinder

This paper presents the semantic pathfinder architecture for generic indexing of multimedia archives. The semantic pathfinder extracts semantic concepts from video by exploring different paths through three consecutive analysis steps, which we derive from the observation that produced video is the result of an authoring-driven process. We exploit this authoring metaphor for machine-driven understanding. The pathfinder starts with the content analysis step. In this analysis step, we follow a data-driven approach of indexing semantics. The style analysis step is the second analysis step. Here, we tackle the indexing problem by viewing a video from the perspective of production. Finally, in the context analysis step, we view semantics in context. The virtue of the semantic pathfinder is its ability to learn the best path of analysis steps on a per-concept basis. To show the generality of this novel indexing approach, we develop detectors for a lexicon of 32 concepts and we evaluate the semantic pathfinder against the 2004 NIST TRECVID video retrieval benchmark, using a news archive of 64 hours. Top ranking performance in the semantic concept detection task indicates the merit of the semantic pathfinder for generic indexing of multimedia archives

This paper presents novel dissimilarity space specially designed for interactive multimedia retrieval. By providing queries made of positive and negative examples, the goal consists in learning the positive class distribution. This classification problem is known to be asymmetric, i.e. the negative class does not cluster in the original feature spaces. We introduce here the idea of Query-based Dissimilarity Space (QDS) which enables to cope with the asymmetrical setup by converting it in a more classical 2-class problem. The proposed approach is evaluated on both artificial data and real image database, and compared with state-of-the-art algorithms.

This paper presents a two-level queueing system for dynamic summarization and interactive searching of video content. Video frames enter the queueing system; some insignificant and redundant frames are removed; the remaining frames are pulled out of the system as top-level key frames. Using an energy-minimization method, the first queue removes the video frames that constitute the gradual transitions of video shots. The second queue measures the content similarity of video frames and reduces redundant frames. In the queueing system, all key frames are linked in a directed-graph index structure, allowing video content to be accessed at any level-of-detail. Furthermore, this graph-based index structure enables interactive video content exploration, and the system is able to retrieve the video key frames that complement the video content already viewed by users. Experimental results on four full-length videos show that our queueing system performs much better than two existing methods on video key frame selection at different compression ratios. The evaluation on video content search shows that our interactive system is more effective than other systems on eight video searching tasks. Compared with the regular media player, our system reduces the average content searching time by half.

This paper presents a system for video shot retrieval in which shots are retrieved based on matching video objects using a combination of colour, shape and texture. Rather than matching on individual objects, our system supports sets of query objects which in total reflect the user's object-based information need. Our work also adapts to a shifting user information need by initiating the partitioning of a user's search into two or more distinct search threads, which can be followed by the user in sequence. This is an automatic process which maps neatly to the ostensive model for information retrieval in that it allows a user to place a virtual checkpoint on their search, explore one thread or aspect of their information need and then return to that checkpoint to then explore an alternative thread. Our system is fully functional and operational and in this paper we illustrate several design decisions we have made in building it.

This paper outlines a framework that would enable the detailed indexing of film and television media through crowdsourcing. By making it easier to generate detailed data about these media on a large scale, fans and scholars can more efficiently produce a wide range of artifacts that reflect their interests in this content. Our development of a test collection included detailed indexing of 12 feature films and 8 television programs. We describe the conditions that make crowdsourcing an ideal approach for accomplishing this work on a larger scale; present a three-level development framework; and discuss how automated indexing, crowdsourcing quality, and copyright concerns might influence continued development of the project. Our framework highlights the potential of both multimedia indexing and crowdsourcing and can serve as a model for others embarking on projects that involve indexing, annotating, or labeling large multimedia collections.