Stephen W. Smoliar

Bio: Stephen W. Smoliar is an academic researcher from National University of Singapore. The author has contributed to research in topics: Video tracking & Video processing. The author has an hindex of 17, co-authored 43 publications receiving 4186 citations.

Automatic partitioning of full-motion video

Abstract: Partitioning a video source into meaningful segments is an important step for video indexing. We present a comprehensive study of a partitioning system that detects segment boundaries. The system is based on a set of difference metrics and it measures the content changes between video frames. A twin-comparison approach has been developed to solve the problem of detecting transitions implemented by special effects. To eliminate the false interpretation of camera movements as transitions, a motion analysis algorithm is applied to determine whether an actual transition has occurred. A technique for determining the threshold for a difference metric and a multi-pass approach to improve the computation speed and accuracy have also been developed.

Content based video indexing and retrieval

Abstract: Video management tools and techniques are based on pixels rather than perceived content. Thus, state-of-the-art video editing systems can easily manipulate such things as time codes and image frames, but they cannot "know," for example, what a basketball is. Our research addresses four areas of content-based video management. >

Video parsing, retrieval and browsing: an integrated and content-based solution

Abstract: This paper presents an integrated solution for computer assisted video parsing and content-based video retrieval and browsing. The uniqueness and effectiveness of this solution lies in its use of video content information provided by a parsing process driven by visual feature analysis. More specifically, parsing will temporally segment and abstract a video source, based on low-level image analyses; then retrieval and browsing of video will be based on key-frames selected during abstraction and spatial-temporal variations of visual features, as well as some shot-level semantics derived from camera operation and motion analysis. These processes, as well as video retrieval and browsing tools, are presented in detail as functions of an integrated system. Also, experimental results on automatic key-frame detection are given.

Video parsing and browsing using compressed data

Abstract: Parsing video content is an important first step in the video indexing process. This paper presents algorithms to automate the video parsing task, including partitioning a source video into clips and classifying those clips according to camera operations, using compressed video data. We have developed two algorithms and a hybrid approach to partitioning video data compressed according to the JPEG and MPEG standards. The algorithms utilize both the video content encoded in DCT (Discrete Cosine Transform) coefficients and the motion vectors between frames. The hybrid approach integrates the two algorithms and incorporates multi-pass strategies and motion analyses to improve both accuracy and processing speed. Also, we present content-based video browsing tools which utilize the information, particularly about the shot boundaries and key frames, obtained from parsing.

Principles of data mining

Abstract: The growing interest in data mining is motivated by a common problem across disciplines: how does one store, access, model, and ultimately describe and understand very large data sets? Historically, different aspects of data mining have been addressed independently by different disciplines. This is the first truly interdisciplinary text on data mining, blending the contributions of information science, computer science, and statistics. The book consists of three sections. The first, foundations, provides a tutorial overview of the principles underlying data mining algorithms and their application. The presentation emphasizes intuition rather than rigor. The second section, data mining algorithms, shows how algorithms are constructed to solve specific problems in a principled manner. The algorithms covered include trees and rules for classification and regression, association rules, belief networks, classical statistical models, nonlinear models such as neural networks, and local "memory-based" models. The third section shows how all of the preceding analysis fits together when applied to real-world data mining problems. Topics include the role of metadata, how to handle missing data, and data preprocessing.

The Human Side of Enterprise.

Abstract: \"What are your assumptions (implicit as well as explicit) about the most effective way to manage people?\" So began Douglas McGregor in this 1960 management classic. It was a seemingly simple question he asked, yet it led to a fundamental revolution in management. Today, with the rise of the global economy, the information revolution, and the growth of knowledge-driven work, McGregor's simple but provocative question continues to resonate-perhaps more powerfully than ever before. Heralded as one of the most important pieces of management literature ever written, a touchstone for scholars and a handbook for practitioners, The Human Side of Enterprise continues to receive the highest accolades nearly half a century after its initial publication. Influencing such major management gurus such as Peter Drucker and Warren Bennis, McGregor's revolutionary Theory Y-which contends that individuals are self-motivated and self-directed-and Theory X-in which employees must be commanded and controlled-has been widely taught in business schools, industrial relations schools, psychology departments, and professional development seminars for over four decades. In this special annotated edition of the worldwide management classic, Joel Cutcher-Gershenfeld, Senior Research Scientist in MIT's Sloan School of Management and Engineering Systems Division, shows us how today's leaders have successfully incorporated McGregor's methods into modern management styles and practices. The added quotes and commentary bring the content right into today's debates and business models. Now more than ever, the timeless wisdom of Douglas McGregor can light the path towards a management style that nurtures leadership capability, creates effective teams, ensures internal alignment, achieves high performance, and cultivates an authentic, value-driven workplace--lessons we all need to learn as we make our way in this brave new world of the 21st century.

Photobook: content-based manipulation of image databases

Abstract: We describe the Photobook system, which is a set of interactive tools for browsing and searching images and image sequences. These query tools differ from those used in standard image databases in that they make direct use of the image content rather than relying on text annotations. Direct search on image content is made possible by use of semantics-preserving image compression, which reduces images to a small set of perceptually-significant coefficients. We discuss three types of Photobook descriptions in detail: one that allows search based on appearance, one that uses 2-D shape, and a third that allows search based on textural properties. These image content descriptions can be combined with each other and with text-based descriptions to provide a sophisticated browsing and search capability. In this paper we demonstrate Photobook on databases containing images of people, video keyframes, hand tools, fish, texture swatches, and 3-D medical data.

Automatic partitioning of full-motion video

Abstract: Partitioning a video source into meaningful segments is an important step for video indexing. We present a comprehensive study of a partitioning system that detects segment boundaries. The system is based on a set of difference metrics and it measures the content changes between video frames. A twin-comparison approach has been developed to solve the problem of detecting transitions implemented by special effects. To eliminate the false interpretation of camera movements as transitions, a motion analysis algorithm is applied to determine whether an actual transition has occurred. A technique for determining the threshold for a difference metric and a multi-pass approach to improve the computation speed and accuracy have also been developed.

Content-based classification, search, and retrieval of audio

Abstract: Many audio and multimedia applications would benefit from the ability to classify and search for audio based on its characteristics. The audio analysis, search, and classification engine described here reduces sounds to perceptual and acoustical features. This lets users search or retrieve sounds by any one feature or a combination of them, by specifying previously learned classes based on these features, or by selecting or entering reference sounds and asking the engine to retrieve similar or dissimilar sounds.