http://www.computer.org/multimedia IEEE MultiMedia covers technical information on a broad range of issues in multimedia systems and applications. Typical topics include hardware and software for media compression, media storage/transport, workstation support for multimedia, data modeling, and abstractions to embed multimedia in application programs. The information consists of articles, product reviews, new product descriptions, book reviews and announcements of conferences and workshops. Articles discuss research as well as advanced practice in hardware/software and span the range from theory to working systems. en-us Tue, 21 May 2013 10:00:17 GMT http://csdl.computer.org/common/images/logos/multimedia.gif List of recently published journal articles http://www.computer.org/multimedia http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.17 Similar to organisms that evolve in biology, a doc- ument can change slightly overtime while each new version is also able to generate other versions. Multimedia Phylogeny investigates the history and evolutionary process of digital objects which includes finding the causal and ancestry document relation- ships, source of modifications and the order and transformations that originally created the set of near duplicates. Multimedia Phylogeny has direct applications in security, forensics, and infor- mation retrieval. In this paper, we explore the phylogeny problem for near-duplicate images in large-scale scenarios, and present solutions that have straightforward extension to other media such as videos. Experiments with about two million test cases (with synthetic and real data) show that our methods automatically build image phylogeny trees from partial information about the near-duplicates, improving the efficiency and effectiveness of the whole process, and represent a step-forward determining causal relationships of digital images overtime. http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.17 http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.15 In this paper, we propose a novel partial-duplicate image retrieval scheme based on saliency-guided visually matching, where the localization of duplicate is done simultaneously. The image is abstracted by the Visually Salient and Rich Regions (VSRR), which are of both high visual saliency and rich visual content. To obtain the compact representation with sparsity at the region level, VSRR is represented by sparse code with group lasso. Further, we construct a relative saliency ordering constraint to refine the retrieval result, which captures the robust relative saliency layout among interest points of the VSRR. Collaborating with this constraint, we propose an efficient algorithm to embed it into the index system to speedup the retrieval. Comparison experiments with state-of-the-art methods on five image databases show the efficiency and effectiveness of our approach. http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.15 http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.62 For video copy detection, it has been recognized that none of any single audio-visual feature, or single detector based on several features, can work well for all transformations. In this article, we propose a novel video copy detection and localization approach with scalable cascading of complemen-tary detectors and multi-scale sequence matching. In this cascade framework, a soft threshold learning algorithm is utilized to estimate the optimal decision thresholds for de-tectors, and a multi-scale sequence matching method is em-ployed to precisely locate copies through 2D Hough transform and multi-granularities similarity evaluation. Excellent per-formance on the TRECVID-CBCD 2011 benchmark dataset shows the effectiveness and efficiency of our approach. http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.62 http://doi.ieeecomputersociety.org/10.1109/MPRV.2013.40 Interactive playgrounds are technology-enhanced installations that aim to provide rich game experiences for children playing in them by combining the benefits of traditional playgrounds with those of digital games. These game experiences could be attained by addressing three design considerations: context-awareness, adaptability and personalization. We propose to use social signal processing (SSP), a field of research that encompasses the automatic analysis of social behavior, to enhance current interactive playgrounds to meet these criteria. This paper surveys SSP techniques and how they can be used to automatically sense and interpret children’s social interactions during play, adapt the playground’s game mechanics to induce targeted social behavior, and learn from the sensed behavior to meet players’ expectations and desires. We discuss the challenges and opportunities faced when introducing SSP into the interactive playground. http://doi.ieeecomputersociety.org/10.1109/MPRV.2013.40 http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.18 Effective feature representation and efficient feature matching are two fundamental problems in many computer vision applications such as image matching and image retrieval. In this paper, we propose a new feature representation, named Nested-SIFT, which utilizes the nesting relationship between SIFT features to naturally group local interest points of different scales to enhance the discriminative power of individual local features and improve the efficiency of image matching. A Nested-SIFT group consists of a bounding feature and several member features covered by the bounding feature. To obtain a compact representation, we further compress the member features in a Nested-SIFT group into a binary code using the SimHash strategy. Based on this new representation, the similarity between two Nested-SIFT groups can be efficiently computed by using quantized visual words and binary hash codes. Experimental results of image matching and image retrieval show that our method is 25% more accurate and 29.6 times faster than a highly optimized nearest neighbor search implementation in image matching on a large scale landmark image dataset, and achieves 59% improvement in retrieval accuracy, 40% reduction in memory cost and 20% reduction in response time, compared with the baseline methods in image retrieval on a dataset of one million web images for near-duplicate detection. http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.18 http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.16 This paper proposes a new method of recognizing human gait. The method is based on the idea that problem of human gait recognition can be transformed from spatio-temporal problem in to spatial domain, specifically 2D image domain. This is done by representing a sample of human gait as a still image. By doing so all the recorded information are kept while enabling the use of proven Content Based Image Retrieval techniques for recognition. Method enables the use of new Human Computer Interaction technology called Microsoft Kinect for gait acquisition. In order to prove the validity of the proposed approach we conducted a study with 50 participants and presented the gathered results. http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.16 http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.14 The main issues of Web scale Image retrieval are to achieve a good accuracy while retaining low computational time and memory footprint. In this paper, we propose a compact image signature by aggregating tensors of visual descriptors. Efficient aggregation is achieved by preprocessing the descriptors. Compactness is achieved by projection and quantization of the signatures. We compare our method to other efficient signatures on a 1 million images dataset, and show the soundness of the approach. http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.14 http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.13 Retrieving relevant videos from a large corpus on mobile devices is a vital challenge. This paper addresses two key issues for mobile search on user-generated videos. The first is the lack of good relevance measurement, due to the unconstrained nature of online videos, for learning semantic-rich representations. The second is due to the limited resource on mobile devices, stringent bandwidth, and delay requirement between the device and the video server. We propose a knowledge-embedded sparse projection learning approach. To alleviate the need for expensive annotation for hash learning, we investigate varying approaches for pseudo label mining, where explicit semantic analysis leverages Wikipedia and performs the best. In addition, we propose a novel sparse projection method to address the efficiency challenge. It learns a discriminative compact representation that drastically reduces transmission cost. With less than 10% non-zero element in the projection matrix, it also reduces computational and storage cost. The experimental results on 100K videos show that our proposed algorithm is competitive in the performance to the prior state-of-the-art hashing methods which are not applicable for mobiles and solely rely on costly manual annotations. The average query time on 100K videos consumes only 0.592 seconds. http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.13 http://doi.ieeecomputersociety.org/10.1109/MPRV.2013.25 Classic research on human factors has found that automation never fully eliminates the human operator from the loop. Instead, it shifts the operator’s responsibilities to the machine and changes the operator’s control demands, sometimes with adverse consequences, called the “ironies of automation.” In this paper, we revisit the problem of automation in the era of social media, focusing on privacy concerns. Present-day social media automatically disclose information such as users’ whereabouts, likings, and undertakings. Our review of empirical studies exposes three recurring privacy-related issues in automated disclosure: 1) insensitivity to situational demands, 2) inadequate control of nuance and veracity, and 3) inability to control disclosure with service providers and third parties. We claim that the “all-or-nothing” type of automation has proven problematic and that social network services should design their user controls with all stages of the disclosure process in mind. http://doi.ieeecomputersociety.org/10.1109/MPRV.2013.25 http://doi.ieeecomputersociety.org/10.1109/MPRV.2013.24 Systematically and quantitatively determining patterns in consumer flow is an important question in marketing research. Identifying these patterns can facilitate understanding of where and when consumers purchase products and services at physical retail shops. Collecting data on real consumers who shop at retail stores is one of the most challenging and expensive aspects of these studies. This paper introduces a phone-based data collection system, called ConvenienceProbe, for retail trade area analysis. The proposed method specifically targets local residents shopping at neighborhood convenience stores. This study deploys and tests the system by collecting real customer flow data in neighborhood convenience stores. Results show that the consumer flow data collected from the ConvenienceProbe system is comparable to that from a traditional face-to-face interview method. http://doi.ieeecomputersociety.org/10.1109/MPRV.2013.24 http://doi.ieeecomputersociety.org/10.1109/MPRV.2013.23 Evaluation of Ambient Assisted Living (AAL) sys- tems is particularly challenging due to the complexity of such systems and to the variety of solutions adopted and services offered. This problem is related to the evaluation of pervasive and ubiquitous systems that has been the focus of many researchers in the recent years and that still awaits for solutions. On the other hand, analyzing and comparing AAL solutions is paramount for the assessment of the research results in this area. EvAAL (Evaluating AAL Systems Through Competitive Benchmarking) is a recently established international competition that aims to address this problem in order to let benchmarking and com- parison methodologies of AAL systems emerge from experience. This work describes the first EvAAL competition which was devoted to localization and tracking; proposed evaluation criteria, benchmarks, and achieved results are reported. All evaluation data are freely available from the EvAAL web site. http://doi.ieeecomputersociety.org/10.1109/MPRV.2013.23 http://doi.ieeecomputersociety.org/10.1109/MPRV.2012.82 Mobile geo-social networking services are believed to be the killing application for the next generation mobile computing. However, the privacy issue, particularly the location privacy, has been raising increasing concern from both end-users and government authorities. In this article, we address this issue for the "nearby friend alert" service, a common and fundamental service in mobile geo-social networks. We provide a thorough review of representative works on privacy-preserving proximity detection, and present a new quantitative solution. We adopt the grid-and-hashing paradigm and develop optimal grid overlay and multi-level grids to increase the detection accuracy while saving the wireless bandwidth. Based on these techniques, we devise the client-side location update scheme and the server-side update handling procedure for continuous proximity detection. Simulation results show that our approach is efficient and scalable under various system parameters and user moving speeds. http://doi.ieeecomputersociety.org/10.1109/MPRV.2012.82 http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.61 Facial expressions are important not only in communication but also in media. This article looks into applications of automatic analysis and modelling of faces with computer vision techniques for media production. http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.61 http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.60 Triggered by the new wave and rise of social networks, community based image sharing platforms emerge at an increasing rate. Currently, almost every repository offers a different interaction interface and metadata description format. Unfortunately, this prevents unified and efficient access to those repositories. Consequently, data exchange between systems is often cumbersome. In this context, ISO/IEC SC29WG1 (more commonly known as JPEG) initiated the JPSearch framework standardization. It aims fostering the interaction with and among image repositories. The standard focuses on three main cornerstones supporting (i) repository synchronization, (ii) search and access and (iii) image collection creation and maintenance. This paper discusses the main concepts, parts and achievements of the JPSearch framework and demonstrates its use through a set of substantial case studies. http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.60 http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.58 Standards-based middleware architectures for content management are suitable to develop a wide range of business scenarios. In this context, we present the case of the ongoing MPEG-M standard but we mainly focus on the MIPAMS standards-based architecture. We provide a selection of relevant deployment scenarios which cover from content licensing to authorization-based content access control, including a specific case for mobile scenarios. We illustrate each of the presented scenarios with our experience and results by analyzing real implementations developed in several research projects and contracts with the industry. http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.58 http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.57 Given that multimedia services are becoming increasingly popular, they are expected to play a dominant role for the Future Internet. In this context, it is essential that Content-Aware Networking (CAN) architectures, as envisaged in the frame of the Future Internet, explicitly address the efficient delivery and processing of multimedia content. This article proposes adopting a content-aware approach into the network infrastructure, thus making it capable of identifying, processing, and manipulating (i.e., adapting, caching, etc.) media streams and objects in real time towards Quality of Service/Experience (QoS/QoE) maximization. Our proposal is built upon the exploitation of scalable media coding technologies within such a content-aware networking environment and is discussed based on four representative use cases for media delivery (unicast, multicast, peer-to-peer, and adaptive HTTP streaming) and with respect to a selection of CAN challenges, specifically flow processing, caching/buffering, and QoS/QoE management. http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.57 http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.55 The goal of the W3C's Media Annotation Working Group (MAWG) is to promote interoperability between multimedia metadata formats on the Web. As experienced by everybody, audiovisual data is omnipresent on today's Web. However, different interaction interfaces and especially diverse metadata formats prevent unified search, access, and navigation. MAWG has addressed this issue by developing an interlingua ontology and an associated API. This article discusses the rationale and core concepts of the ontology and API for media resources. The specifications developed by MAWG enable interoperable contextualized and semantic annotation and search, independent of the source metadata format, and connecting multimedia data to the Linked Data cloud. Some demonstrators of such applications are also presented in this article. http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.55 http://doi.ieeecomputersociety.org/10.1109/MPRV.2012.57 It has always been a challenge for designers and developers to readily pinpoint potentially viable opportunities for newly emerging technologies in people’s daily lives. Especially in ubiquitous computing, the uncontrollable dynamics of a user’s context makes this issue even more prominent. In this research, we assume that we cannot successfully hypothesize what users of new technologies will desire, neither by observing only the current situations where the new technologies are absent nor by deploying a technology-centered hypothetical idea and testing it in the field. To overcome this challenge, we developed a new prototyping technique using discovery-driven prototypes, namely Discovery-Driven Prototyping, through which we let users be entirely in control of what they can and would like to do with the new technologies. In this paper, we describe this technique and its effectiveness, which are examined through a series of in-situ user studies. http://doi.ieeecomputersociety.org/10.1109/MPRV.2012.57 http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.30 This paper reviews the recent progress of learning based approaches for web image search reranking. A mathematical definition of the image search reranking problem and a formulation of representative approaches are presented. Being aware of the limitation of existing approaches, our prospect on the future work to make it realized in practical image search engines is also discussed. http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.30 http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.29 Algorithmic parameterization and hardware architectures can ensure secure transmission of multimedia data in resource-constrained environments such as wireless video surveillance networks, tele-medicine frameworks for distant health care support in rural areas, and Internet video streaming. Joint multimedia compression and encryption techniques can significantly reduce the computational requirements of video processing systems. We present an approach to reduce the computational cost of multimedia encryption, while also preserving the properties of compressed video (useful for scalability, transcoding, and retrieval), which endanger loss by naive encryption. Hardware-amenable design of proposed algorithms makes them suitable for real-time embedded multimedia systems. This approach alleviates the need of additional hardware for encryption in resource constrained scenario, and can be otherwise used to augment existing encryption methods used for content delivery in Internet or other applications. In this work, we show how two compression blocks for video coding: a modified frequency transform (called as Secure Wavelet Transform or SWT) and a modified entropy coding scheme, (called Chaotic Arithmetic Coding (CAC)) can be used for video encryption. A bit sensitivity analysis for key and plaintext is presented along with experimental tests for selective encryption are given. http://doi.ieeecomputersociety.org/10.1109/MMUL.2012.29 http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.62 Human behavior modeling at a large-scale and under real-world conditions is still an open problem. Existing classification models do not always perform well on a diverse population. Training personalized models that incorporate different contextual conditions and individual user characteristics are effective in addressing this challenge. However, this approach burdens the users with collecting and manually labeling their own training data which is not scalable. In this article, we propose CoCo (Cooperative Communities), a learning framework that leverages different types of everyday social connections between people to personalize classification models. CoCo exploits social networks to selectively combine small contributions of labeled data from people with shared context or user characteristics. Under CoCo a personalized classifier is trained for each individual user, but by exploiting social networks, the burden of providing training data can be spread over the entire community. http://doi.ieeecomputersociety.org/10.1109/MPRV.2011.62 http://www.computer.org/portal/site/multimedia/ IEEE MultiMedia http://www.computer.org/portal/site/multimedia/