Cache modeling and optimization for portable devices running MPEG-4 video decoder

There are increasing demands on portable communication devices to run multimedia applications. ISO (an International Organization for Standardization) standard MPEG-4 is an important and demanding multimedia application. To satisfy the growing consumer demands, more functions are added to support MPEG-4 video applications. With improved CPU speed, memory sub-system deficiency is the major barrier to improving the system performance. Studies show that there is sufficient reuse of values for caching that significantly reduce the memory bandwidth requirement for video data. Software decoding of MPEG-4 video data generates much more cache-memory traffic than required. Proper understanding of the decoding algorithm and the composition of its data set is obvious to improve the performance of such a system. The focus of this paper is cache modeling and optimization for portable communication devices running MPEG-4 video decoding algorithm. The architecture we simulate includes a digital signal processor (DSP) for running the MPEG-4 decoding algorithm and a memory system with two levels of caches. We use VisualSim and Cachegrind simulation tools to optimize cache sizes, levels of associativity, and cache levels for a portable device decoding MPEG-4 video. Abu Asaduzzaman is, currently, a PhD candidate in the department of Computer Science and Engineering (CSE), Florida Atlantic University (FAU), Boca Raton, Florida. He received his MS degree in computer engineering from FAU in 1997. Mr. Asaduzzaman worked for ECI Telecom as a software engineer from 1998 to 2001. From 2001 to 2003, he worked for BlueCross and BlueShield of Florida and SunPass (FDoT) as an IT Consultant. Currently, he is working as a research assistant at CSE Dept, FAU. His research interests include cache optimization, architecture exploration, embedded system evaluation, and networks-on-a-chip (NoC). He has published several research papers in these areas. Abu is a member of the honor society of Phi Kappa Phi, Tau Beta Pi, Upsilon Phi Epsilon, and the Association for Computing Machinery (ACM) FAU Chapter. Imad Mahgoub received the MS degree in applied mathematics and MS degree in electrical and computer engineering, both from North Carolina State University, Raleigh in 1983 and 1986 respectively and the PhD degree in computer engineering from the Pennsylvania State University, University Park, PA in 1989. Dr. Mahgoub joined Florida Atlantic University (FAU), Boca Raton, Florida in 1989. Currently he is a full professor of Computer Science and Engineering department and the director of the Mobile Computing Laboratory. His research interests include performance evaluation, mobile computing, sensor networks, and parallel and distributed processing. He has published over 80 research papers in these areas. He is the co-editor of the Mobile Computing Handbook and the Handbook of Sensor Networks. Dr. Mahgoub has served on the program committees of numerous conferences. He has been the vice-chair for the Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS) since 2003. He is a senior member of the IEEE. He is also a member of Tau Beta Pi, Upsilon Pi Epsilon, the IEEE Computer Society, and the ACM.     

Cache modeling and optimization for portable devices running MPEG-4 video decoder

There are increasing demands on portable communication devices to run multimedia applications. ISO (an International Organization for Standardization) standard MPEG-4 is an important and demanding multimedia application. To satisfy the growing consumer demands, more functions are added to support MPEG-4 video applications. With improved CPU speed, memory sub-system deficiency is the major barrier to improving the system performance. Studies show that there is sufficient reuse of values for caching that significantly reduce the memory bandwidth requirement for video data. Software decoding of MPEG-4 video data generates much more cache-memory traffic than required. Proper understanding of the decoding algorithm and the composition of its data set is obvious to improve the performance of such a system. The focus of this paper is cache modeling and optimization for portable communication devices running MPEG-4 video decoding algorithm. The architecture we simulate includes a digital signal processor (DSP) for running the MPEG-4 decoding algorithm and a memory system with two levels of caches. We use VisualSim and Cachegrind simulation tools to optimize cache sizes, levels of associativity, and cache levels for a portable device decoding MPEG-4 video. Abu Asaduzzaman is, currently, a PhD candidate in the department of Computer Science and Engineering (CSE), Florida Atlantic University (FAU), Boca Raton, Florida. He received his MS degree in computer engineering from FAU in 1997. Mr. Asaduzzaman worked for ECI Telecom as a software engineer from 1998 to 2001. From 2001 to 2003, he worked for BlueCross and BlueShield of Florida and SunPass (FDoT) as an IT Consultant. Currently, he is working as a research assistant at CSE Dept, FAU. His research interests include cache optimization, architecture exploration, embedded system evaluation, and networks-on-a-chip (NoC). He has published several research papers in these areas. Abu is a member of the honor society of Phi Kappa Phi, Tau Beta Pi, Upsilon Phi Epsilon, and the Association for Computing Machinery (ACM) FAU Chapter. Imad Mahgoub received the MS degree in applied mathematics and MS degree in electrical and computer engineering, both from North Carolina State University, Raleigh in 1983 and 1986 respectively and the PhD degree in computer engineering from the Pennsylvania State University, University Park, PA in 1989. Dr. Mahgoub joined Florida Atlantic University (FAU), Boca Raton, Florida in 1989. Currently he is a full professor of Computer Science and Engineering department and the director of the Mobile Computing Laboratory. His research interests include performance evaluation, mobile computing, sensor networks, and parallel and distributed processing. He has published over 80 research papers in these areas. He is the co-editor of the Mobile Computing Handbook and the Handbook of Sensor Networks. Dr. Mahgoub has served on the program committees of numerous conferences. He has been the vice-chair for the Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS) since 2003. He is a senior member of the IEEE. He is also a member of Tau Beta Pi, Upsilon Pi Epsilon, the IEEE Computer Society, and the ACM.     

Combining Seminorms in Adaptive Lifting Schemes and Applications to Image Analysis and Compression

In this paper, we present some adaptive wavelet decompositions that can capture the directional nature of images. Our method exploits the properties of seminorms to build lifting structures able to choose between different update filters, the choice being triggered by the local gradient-type features of the input. In order to deal with the variety and wealth of images, one has to be able to use multiple criteria, giving rise to multiple choice of update filters. We establish the conditions under these decisions can be recovered at synthesis, without the need for transmitting overhead information. Thus, we are able to design invertible and non-redundant schemes that discriminate between different geometrical information to efficiently represent images for lossless compression methods. The work of Piella is supported by a Marie-Curie Intra-European Fellowships within the 6th European Community Framework Programme. Gemma Piella received the M.S. degree in electrical engineering from the Polytechnical University of Catalonia (UPC), Barcelona, Spain, and the Ph.D. degree from the University of Amsterdam, The Netherlands, in 2003. From 2003 to 2004, she was at UPC as a visiting professor. She then stayed at the Ecole Nationale des Telecommunications, Paris, as a Post-doctoral Fellow. Since September 2005 she is at the Technology Department in the Pompeu Fabra University. Her main research interests include wavelets, geometrical image processing, image fusion and various other aspects of digital image and video processing. Beatrice Pesquet-Popescu received the engineering degree in telecommunications from the “Politehnica” Institute in Bucharest in 1995 and the Ph.D. thesis from the Ecole Normale Supérieure de Cachan in 1998. In 1998 she was a Research and Teaching Assistant at Université Paris XI and in 1999 she joined Philips Research France, where she worked for two years as a research scientist, then project leader, in scalable video coding. Since Oct. 2000 she is an Associate Professor in multimedia at the Ecole Nationale Supérieure des Télécommunications (ENST). Her current research interests are in scalable and robust video coding, adaptive wavelets and multimedia applications. EURASIP gave her a “Best Student Paper Award” in the IEEE Signal Processing Workshop on Higher-Order Statistics in 1997, and in 1998 she received a “Young Investigator Award” granted by the French Physical Society. She is a member of IEEE SPS Multimedia Signal Processing (MMSP) Technical Committee and a Senior Member IEEE. She holds 20 patents in wavelet-based video coding and has authored more than 80 book chapters, journal and conference papers in the field. Henk Heijmans received his masters degree in mathematics from the Technical University in Eindhoven and his PhD degree from the University of Amsterdam in 1985. Since then he has been in the Centre for Mathematics and Computer Science, Amsterdam, where he had been directing the “signals and images” research theme. His research interest are focused towards mathematical techniques for image and signal processing, with an emphasis on mathematical morphology and wavelet analysis. Grégoire Pau was born in Toulouse, France in 1977 and received the M.S. degree in Signal Processing in 2000 from Ecole Centrale de Nantes. From 2000 to 2002, he worked as a Research Engineer at Expway where he actively contributed to the standardization of the MPEG-7 binary format. He is currently a PhD candidate in the Signal and Image Processing Departement of ENST-Telecom Paris. His research interests include subband video coding, motion compensated temporal filtering and adaptive non-linear wavelet transforms.     

An experimental analysis of DCT-based approaches for fine-grained multiresolution video

In the future, video-streaming systems will have to support adaptation over an extremely large range of display requirements (e.g., 90×60 to 1920×1080). This paper presents the architectural trade-offs of bandwidth efficiency, computational cost, and storage cost to support fine-grained multiresolution video over a large set of resolutions. While several techniques have been proposed, they have focused mainly on limited spatial resolution adaptation. In this paper, we examine the ability of current techniques to support wide-range spatial resolution adaptation. Based upon experiments with real video, we propose an architecture that can support wide-range adaptation efficiently. Our results indicate that multiple encodings with limited spatial adaptation from each encoding provide good trade-offs between efficient coding and the ability to adapt the stream to various resolutions. Jie Huang received her BS in computer and communications and MS in computer science from Beijing University of Posts and Telecommunications, Beijing, China, in 1992 and 1995 respectively, where she was an assistant professor from 1995 to 1999. Since 1999, she has been pursuing her PhD at OGI school of Science and Engineering at Oregon Health and Science University (from 1999 to 2004) and Portland State University (since 2004). Her research interests include multimedia networking and software engineering. Wu-chi Feng received his Ph.D. in Computer Science and Engineering from the University of Michigan in 1996. ~His research interests include multimedia systems, video-based sensor networking technologies, and networking. ~He currently serves as an Editor for the Springer-ACM Multimedia Systems Journal. ~He also serves on the national Orion Cyberinfrastructure Advisory committee. Jonathan Walpole received his Ph.D. degree in Computer Science from Lancaster University, UK. He is a Professor in the Computer Science Department at Portland State University. Prior to joining PSU he was a Professor and Director of the Systems Software Laboratory at the OGI School of Science and Engineering at Oregon Health & Science University. His research interests are in operating systems, networking, distributed systems and multimedia computing. He has pioneered research in adaptive resource management and the integration of application and system-level quality of service management. He has also done leading edge research on dynamic specialization for enhanced performance, survivability and evolvability of large software systems. His research on distributed multimedia systems began in 1988, and in the early 1990s he lead the development of one of the first QoS-adaptive Internet streaming video players.     

MPEG-4的系统结构解析

对MPEG-4中各种分层结构进行了深入的剖析,包括媒体对象语义的分层表达,媒体对象的分层编码,MPEG-4码流的分层组织及最终的多媒体集成传送框架的分层实现等。最后给出了MPEG-4的总体结构及分层技术的作用,并讨论了分层结构的思想方法、评价标准及不足等。     

DAg-stream: Distributed video adaptation for overlay streaming to heterogeneous devices

Combining the advantages of Peer-to-Peer (P2P) content distribution concept and metadata driven adaptation of videos in compressed domain, in this paper, we propose a simple but scalable design of distributed adaptation and overlay streaming using MPEG-21 gBSD, called DAg-stream. The objective is not only to shift the bandwidth burden to end participating peers, but also to move the computation load for adapting video contents away from dedicated media-streaming/adaptation servers. It is an initiative to merge the adaptation operations and the P2P streaming basics to support the expansion of context-aware mobile P2P systems. DAg-stream organizes mobile and heterogeneous peers into overlays. For each video, a separate overlay is formed. No control message is exchanged among peers for overlay maintenance. We present a combination of infrastructure-centric and application end-point architecture. The infrastructure-centric architecture refers to a tree controller, named DAg-master, which is responsible for tree/overlay administering and maintenance. The application end-point architecture refers to video sharing, streaming and adaptation by the participating resourceful peers. The motivation for this work is based on the experiences and lessons learned so far about developing a video adaptation system for heterogeneous devices. In this article, we present our architecture and some experimental evaluations supporting the design concept for overlay video streaming and online adaptation.

A motion compensated lifting wavelet codec for 3D video coding

A motion compensated lifting (MCLIFT) ramework for the 3D wavelet video coding is proposed in this paper,By using bi-directional motion compensation in each lifting step of the temporal direction,the video frames are effectively de-correlated,With the proper entropy coding and bit-stream packaging schemes,the MCLIFT wavelet video coder is scalable at frame rate and quality level .Experimental results show that the MCLIFT video coder outperforms the 3D wavelet video coder without motion by an average of 0.9-1.3dB,and outperforms MPEG-4 coder by an average of 0.2-0.6dB.     

The Two-Dimensional Clifford-Fourier Transform

Recently several generalizations to higher dimension of the Fourier transform using Clifford algebra have been introduced, including the Clifford-Fourier transform by the authors, defined as an operator exponential with a Clifford algebra-valued kernel. In this paper an overview is given of all these generalizations and an in depth study of the two-dimensional Clifford-Fourier transform of the authors is presented. In this special two-dimensional case a closed form for the integral kernel may be obtained, leading to further properties, both in the L ₁ and in the L ₂ context. Furthermore, based on this Clifford-Fourier transform Clifford-Gabor filters are introduced. AMS subject classification numbers: 42B10, 30G35 Fred Brackx received a diploma degree in mathematics from Ghent University, Belgium, in 1970 and a Ph.D. degree in mathematics from the same university in 1973. Since 1984 he is professor for mathematical analysis at Ghent University and currently he is leading the Clifford Research Group. His main interests are function theory and functional analysis for functions with values in quaternion and Clifford algebras. The research covers Clifford distributions, generalized Fourier, Radon and Hilbert transforms, orthogonal polynomials and multi-dimensional wavelets. Nele De Schepper received a diploma degree in mathematics from Ghent University, Belgium, in 2001. Since then she holds an assistantship at the Department of Mathematical Analysis of Ghent University and is a member of the Clifford Research Group. Her main interests are function theory and functional analysis for functions with values in Clifford algebras. The research covers generalized Fourier transforms, orthogonal polynomials and multi-dimensional wavelets. Frank Sommen received a diploma degree in mathematics from Ghent University, Belgium, in 1978, a Ph.D. degree in mathematics from the same university in 1980, and a habilitation degree in mathematical analysis in 1984. From 1978 until 1999 he was at the National Fund for Scientific Research (Flanders). Since 2000 he holds a Research professorship at Ghent University. His main interests are function theory and functional analysis for functions with values in quaternion and Clifford algebras. The research covers Clifford distributions, generalized Fourier, Radon and Hilbert transforms, orthogonal polynomials and multi-dimensional wavelets, algebraic analysis, hyperfunctions and radial algebra.     

An Integrated Framework for Semantic Annotation and Adaptation

Tools for the interpretation of significant events from video and video clip adaptation can effectively support automatic extraction and distribution of relevant content from video streams. In fact, adaptation can adjust meaningful content, previously detected and extracted, to the user/client capabilities and requirements. The integration of these two functions is increasingly important, due to the growing demand of multimedia data from remote clients with limited resources (PDAs, HCCs, Smart phones). In this paper we propose an unified framework for event-based and object-based semantic extraction from video and semantic on-line adaptation. Two cases of application, highlight detection and recognition from soccer videos and people behavior detection in domotic^* applications, are analyzed and discussed.Domotics is a neologism coming from the Latin word domus (home) and informatics.Marco Bertini has a research grant and carries out his research activity at the Department of Systems and Informatics at the University of Florence, Italy. He received a M.S. in electronic engineering from the University of Florence in 1999, and Ph.D. in 2004. His main research interest is content-based indexing and retrieval of videos. He is author of more than 25 papers in international conference proceedings and journals, and is a reviewer for international journals on multimedia and pattern recognition.Rita Cucchiara (Laurea Ingegneria Elettronica, 1989; Ph.D. in Computer Engineering, University of Bologna, Italy 1993). She is currently Full Professor in Computer Engineering at the University of Modena and Reggio Emilia (Italy). She was formerly Assistant Professor (‘93–‘98) at the University of Ferrara, Italy and Associate Professor (‘98–‘04) at the University of Modena and Reggio Emilia, Italy. She is currently in the Faculty staff of Computer Engenering where has in charges the courses of Computer Architectures and Computer Vision.Her current interests include pattern recognition, video analysis and computer vision for video surveillance, domotics, medical imaging, and computer architecture for managing image and multimedia data.Rita Cucchiara is author and co-author of more than 100 papers in international journals, and conference proceedings. She currently serves as reviewer for many international journals in computer vision and computer architecture (e.g. IEEE Trans. on PAMI, IEEE Trans. on Circuit and Systems, Trans. on SMC, Trans. on Vehicular Technology, Trans. on Medical Imaging, Image and Vision Computing, Journal of System architecture, IEEE Concurrency). She participated at scientific committees of the outstanding international conferences in computer vision and multimedia (CVPR, ICME, ICPR, ...) and symposia and organized special tracks in computer architecture for vision and image processing for traffic control. She is in the editorial board of Multimedia Tools and Applications journal. She is member of GIRPR (Italian chapter of Int. Assoc. of Pattern Recognition), AixIA (Ital. Assoc. Of Artificial Intelligence), ACM and IEEE Computer Society.Alberto Del Bimbo is Full Professor of Computer Engineering at the Università di Firenze, Italy. Since 1998 he is the Director of the Master in Multimedia of the Università di Firenze. At the present time, he is Deputy Rector of the Università di Firenze, in charge of Research and Innovation Transfer. His scientific interests are Pattern Recognition, Image Databases, Multimedia and Human Computer Interaction. Prof. Del Bimbo is the author of over 170 publications in the most distinguished international journals and conference proceedings. He is the author of the “Visual Information Retrieval” monography on content-based retrieval from image and video databases edited by Morgan Kaufman. He is Member of IEEE (Institute of Electrical and Electronic Engineers) and Fellow of IAPR (International Association for Pattern Recognition). He is presently Associate Editor of Pattern Recognition, Journal of Visual Languages and Computing, Multimedia Tools and Applications Journal, Pattern Analysis and Applications, IEEE Transactions on Multimedia, and IEEE Transactions on Pattern Analysis and Machine Intelligence. He was the Guest Editor of several special issues on Image databases in highly respected journals.Andrea Prati (Laurea in Computer Engineering, 1998; PhD in Computer Engineering, University of Modena and Reggio Emilia, 2002). He is currently an assistant professor at the University of Modena and Reggio Emilia (Italy), Faculty of Engineering, Dipartimento di Scienze e Metodi dell’Ingegneria, Reggio Emilia. During last year of his PhD studies, he has spent six months as visiting scholar at the Computer Vision and Robotics Research (CVRR) lab at University of California, San Diego (UCSD), USA, working on a research project for traffic monitoring and management through computer vision. His research interests are mainly on motion detection and analysis, shadow removal techniques, video transcoding and analysis, computer architecture for multimedia and high performance video servers, video-surveillance and domotics. He is author of more than 60 papers in international and national conference proceedings and leading journals and he serves as reviewer for many international journals in computer vision and computer architecture. He is a member of IEEE, ACM and IAPR.     

Video JET: packet loss-resilient video joint encryption and transmission based on media-hash-embedded residual data

Media encryption technologies actively play the first line of defense in securing the access of multimedia data. Traditional cryptographic encryption can achieve provable security but is unfortunately sensitive to a single bit error, which will cause an unreliable packet to be dropped creating packet loss. In order to achieve robust media encryption, the requirement of error resilience can be achieved with error-resilient media transmission. This study proposes a video joint encryption and transmission (video JET) scheme by exploiting media hash-embedded residual data to achieve motion estimation and compensation for recovering lost packets, while maintaining format compliance and cryptographic provable security. Interestingly, since video block hash preserves the condensed content to facilitate search of similar blocks, motion estimation is implicitly performed through robust media hash matching – which is the unique characteristic of our method. We analyze and compare the performance of resilience to (bursty) packet loss between the proposed method and forward error correction (FEC), which has been extensively employed to protect video packets over error-prone networks. The feasibility of our packet loss-resilient video JET approach is further demonstrated through experimental results.

Segmentation of convex cells with partially undefined edges

This paper presents an algorithm for segmentation of convex cells with partially undefined edges based on application of a marker-controlled watershed transform to a combination of a source grayscale image and the result of a “geodesic distance” morphological operation, applied to the result of binarization of a source image. The presented approach is used in computer image processing systems for analysis of several industrial materials. The text was submitted by the authors in English. Ilia V. Safonov received his MS degree in automatic and electronic engineering from Moscow Engineering Physics Institute/University (MEPhI), Russia in 1994 and his PhD degree in computer science from MEPhI in 1997. Since 1998 he is an associate professor of faculty of Cybernetics of MEPhI while conducting researches in image segmentation, features extraction and pattern recognition problems. Since 2004, Dr. I. Safonov has joint Image Enhancement Technology Group, Printing Technology Lab, Samsung Research Center, Moscow, Russia where he is engaged in photo, video, and document image enhancement projects. Konstantin A. Kryzhanovsky received the MS degree in cybernetics from Moscow Engineering Physics Institute/University (MEPhI), Russia in 2000. Since 2006 he is an assistant professor of faculty of Cybernetics of MEPhI. He is presently working towards his Ph.D. degree. His current research interests include image processing and pattern recognition. Gennady N. Mavrin received his MS degree in automatic and electronic engineering from Moscow Engineering Physics Institute/University (MEPhI), Russia in 1998. Since 2002 he is an assistant professor of faculty of Cybernetics of MEPhI. He is currently pursuing the PhD degree. His research interests include image segmentation and feature extraction problems.     

一种基于单环结构的扩展基本层FGS视频编码方法

可分级编码是解决Internet流视频应用中网络带宽不断波动的一种有效方法，所以MPEG-4标准中采用了FGS(fine granularity scalability)编码方法来获得精细颗粒可分级能力，但其代价是编码效率的下降。为解决此问题，现提出在增强层中采用运动补偿的MC加FGS(motion compensation加FGS)结构，用于去除FGS方案中增强层在时域上的冗余，以提高FGS方案编码效率的双环和单环两种方法。在比较了两种结构各自的优缺点后，选定了一种复杂度小、实现简单、效率高的单环结构，并提出了对单环结构的缺陷进行改善的方法。实验结果表明，该方法的编码性能优于MPEG-4 FGS方法。     

Seamless switching of scalable video bitstreams for efficient streaming

Efficient adaptation to channel bandwidth is broadly required for effective streaming video over the Internet. To address this requirement, a novel seamless switching scheme among scalable video bitstreams is proposed in this paper. It can significantly improve the performance of video streaming over a broad range of bit rates by fully taking advantage of both the high coding efficiency of nonscalable bitstreams and the flexibility of scalable bitstreams, where small channel bandwidth fluctuations are accommodated by the scalability of a single scalable bitstream, whereas large channel bandwidth fluctuations are tolerated by flexible switching between different scalable bitstreams. Two main techniques for switching between video bitstreams are proposed. Firstly, a novel coding scheme is proposed to enable drift-free switching at any frame from the current scalable bitstream to one operated at lower rates without sending any overhead bits. Secondly, a switching-frame coding scheme is proposed to greatly reduce the number of extra bits needed for switching from the current scalable bitstream to one operated at higher rates. Compared with existing approaches, such as switching between nonscalable bitstreams and streaming with a single scalable bitstream, our experimental results clearly show that the proposed scheme brings higher efficiency and more flexibility in video streaming.     

Robust Quality Adaptation for Internet Video Streaming

Internet video streaming is a widely popular application however, in many cases, congestion control facilities are not well integrated into such applications. In order to be fair to other users that do not stream video, rate adaptation should be performed to respond to congestion. On the other hand, the effect of rate adaptation on the viewer should be minimized and this extra mechanism should not overload the client and the server. In this paper, we develop a heuristic approach for unicast congestion control. The primary feature of our approach is the two level adaptation algorithm that utilizes packet loss rate as well as receiver buffer data to maintain satisfactory buffer levels at the receiver. This is particularly important if receiver has limited buffer such as in mobile devices. When there is no congestion, to maintain best buffer levels, fine grain adjustments are carried out at the packet level. Depending on the level of congestion and receiver buffer level, rate shaping that involves frame discard and finally rate adaptation by switching to a different pre-encoded video stream are carried out. Additive increase multiplicative decrease policy is maintained to respond to congestion in a TCP- friendly manner. The algorithm is implemented and performance results show that it has adaptation ability that is suitable for both local area and wide area networks. E. Turhan Tunali received B.Sc. Degree in Electrical Engineering from Middle East Technical University and M.Sc. Degree in Applied Statistics from Ege University, both in Turkey. He then received D.Sc. Degree in Systems Science and Mathematics from Washington University in St. Louis, U.S.A. in 1985. After his doctorate study, he joined Computer Engineering Department of Ege University as an assistant professor where he became an associate professor in 1988. During the period of 1992–1994, he worked in Department of Computer Technology of Nanyang Technological University of Singapore as a Visiting Senior Fellow. He then joined International Computer Institute of Ege University as a Professor where he is currently the director. In the period of 2000–2001 he worked in Department of Computer Science of Loyola University of Chicago as a Visiting Professor. His current research interests include adaptive video streaming and Internet performance measurements. Dr. Tunali is married with an eighteen year old son. Aylin Kantarci received B.Sc., M.Sc. and Ph.D. degrees all from Computer Engineering Department of Ege University, Izmir, Turkey, in 1992, 1994 and 2000, respectively. She then joined the same department as an assistant professor. Her current research interests include adaptive video streaming, video coding, operating systems, multimedia systems and distributed systems. Nukhet Ozbek received B.Sc. degree in Electrical and Electronics Engineering from School of Engineering and M.Sc. degree in Computer Science from International Computer Institute both in Ege University, Izmir, Turkey. From 1998 to 2003 she worked in the DVB team of Digital R&D at Vestel Corporation, Izmir-Turkey that produces telecommunication and consumer electronics devices. She is currently a Ph.D. student and a research assistant at International Computer Institute of Ege University. Her research areas include video coding and streaming, multimedia systems and set top box architectures.     

Personalized retrieval of sports video based on multi-modal analysis and user preference acquisition

In this paper, we present a novel framework on personalized retrieval of sports video, which includes two research tasks: semantic annotation and user preference acquisition. For semantic annotation, web-casting texts which are corresponding to sports videos are firstly captured from the webpages using data region segmentation and labeling. Incorporating the text, we detect events in the sports video and generate video event clips. These video clips are annotated by the semantics extracted from web-casting texts and indexed in a sports video database. Based on the annotation, these video clips can be retrieved from different semantic attributes according to the user preference. For user preference acquisition, we utilize click-through data as a feedback from the user. Relevance feedback is applied on text annotation and visual features to infer the intention and interested points of the user. A user preference model is learned to re-rank the initial results. Experiments are conducted on broadcast soccer and basketball videos and show an encouraging performance of the proposed method.

The CPR Model for Summarizing Video

Most past work on video summarization has been based on selecting key frames from videos. We propose a model of video summarization based on three important parameters: Priority (of frames), Continuity (of the summary), and non-Repetition (of the summary). In short, a summary must include high priority frames and must be continuous and non-repetitive. An optimal summary is one that maximizes an objective function based on these three parameters. We show examples of how CPR parameters can be computed and provide algorithms to find optimal summaries based on the CPR approach. Finally, we briefly report on the performance of these algorithms.Marat Fayzullin has received his PhD degree in Computer Science from the University of Maryland, College Park, in 2004. He has done research in Distributed Simulation Environments, Multimedia Database Algebras, and Automated Content Summarization. His topics of interest also include Mobile Agent Networks and Reasoning with Semantic Networks.V.S. Subrahmanian received his Ph.D. in Computer Science from Syracuse University in 1989. Since then, he has been on the faculty of the Computer Science Department at the University of Maryland, College Park, where he currently holds the rank of Professor. He also serves as Director of the University of Marylands Institute for Advanced Computer Studies (UMIACS) established by the State of Maryland in the mid-1980s to pursue interdisciplinary research involving IT. He received the NSF Young Investigator Award in 1993 and the Distinguished Young Scientist Award from the Maryland Academy of Science/Maryland Science Center in 1997. Prof. Subrahmanian is recognized for his work on nonmonotonic and probabilistic logics, inconsistency management in databases, database models views and inference, rule bases, heterogeneous databases, multimedia databases, and probabilistic databases. More recently, he has developed techniques to agentize legacy software, allowing multiple software modules to dynamically collaborate with each other to solve complex problems. He has edited two books, one on nonmonotonic reasoning (MIT Press) and one on multimedia databases (Springer). He has co-authored an advanced database textbook (Morgan Kaufman, 1997) and a book on heterogeneous software agents. He is the sole author of the best known textbook on multimedia databases (Morgan Kaufmann)—a second edition of this book is under preparation. Prof. Subrahmanian has given invited talks at numerous national and international conferences—in addition, he has served on numerous conference and funding panels, as well as on the program committees of numerous conferences. He has also chaired several conferences. Prof. Subrahmanian is or has previously been on the editorial board of IEEE Transactions on Knowledge and Data Engineering, Artificial Intelligence Communications, Multimedia Tools and Applications, Journal of Logic Programming, Annals of Mathematics and Artificial Intelligence, Distributed and Parallel Database Journal, and Theory and Practice of Logic Programming.Prof. Subrahmanian has served on DARPAs (Defense Advanced Research Projects Agency) Executive Advisory Council on Advanced Logistics and as an ad-hoc member of the US Air Force Science Advisory Board (2001).Antonio Picariello received the Laurea degree in Electronics Engineering from the University of Napoli, Italy, in 1991. In 1993 he joined the Istituto Ricerca Sui Sistimi Informatici Paralleli, The National Research Council, Napoli, Italy. He received a Ph.D. degree in Computer Science and Engineering in 1998 from the University of Naples Federico II. In 1999, he joined the Dipartimento di Informatica e Sistemistica, University of Napoli Federico II, Italy, and is currently an Associate Professor of Data Base. He has been active in the field of Computer Vision, Medical Image Processing and Pattern Recognition, Object-Oriented models for image processing, Multimedia Data Base and Information Retrieval. His current research interests lie in Knowledge Extraction and Management, Multimedia Integration and Image and Video databases. He is a member of the International Association of Pattern Recognition.Maria Luisa Sapino has got her master degree and Ph.D. in Computer Science at the University of Torino, where shes currently Associate Professor. She initially worked in the area of logic programming and artificial intelligence, specifically interested in the semantics of negation in logic programming, and in the abductive extensions of logic programs. Her current research interests include heterogeneous and multimedia databases, in particular similarity based information retrieval, and modeling and querying multimedia presentations. She has been serving as a reviewer for several international conferences and journals.