MPEG-4, under the auspices of the ISO, is specifying tools to enable object-based audio-visual presentations. These include tools to encode individual objects, compose presentations with objects, store these object-based presentations and access these presentations in a distributed manner over networks. The main distinguishing feature of object-based audio-visual presentations is the scene composition at the user terminal. The objects that are part of a scene are composed and displayed at the user end as opposed to encoding the composed scenes as is done in the case of MPEG-2. Such object-based representation and presentation has several benefits including compression efficiency and interaction with individual objects.

Mashups refer to integrating content from disparate sources to create new data for supporting new functionality. By hybridization of information, reusing and remixing available content through associations and recombination, new services can be provided to the users. Although data mashups are not new, mashups of multimedia content is still in its infancy. We propose a new language - Multimedia Mash up Markup Language (M3L) - that enables flexible access and easy combination of multimedia content. We first describe state-of-the-art in mashups before presenting our proposed language, while emphasizing its distinct features compared with state-of-the-art. We also propose extending Synchronized Multimedia Integration Language (SMIL) to support logic for data manipulation necessary for handling result set processing.

Face recognition is one of the most promising and successful applications of image analysis and understanding. Applications include biometrics identification, gaze estimation, emotion recognition, human computer interface, among others. A closed system trained to recognize only a predetermined number of faces will become obsolete very easily. In this paper, we describe a demo that we have developed using face detection and recognition algorithms for recognizing actors/actresses in movies. The demo runs on a Samsung tablet to recognize actors/actresses in the video. We also present our proposed method that allows user to interact with the system during training while watching video. New faces are tracked and trained into new face classifiers as video is continuously playing and the face database is updated dynamically.

The Frustrated Shopper Typical Experiences in a large shopping mall - Searching for the mall directory - Looking for merchandise - Looking for a sales assistant - Waiting for the cashier to check out items - Searching for promotional, discount items - Locating shopping partner who has wandered off separately, locating restrooms, etc - No idea what accessories match items - No time to shop leisurely!

Video surveillance systems increasingly use H.264 coding to achieve 24 x 7 recording and streaming. However, with the proliferation of security cameras, and the need to store several months of video, bandwidth and storage costs can be significant. We propose a new compression technique to significantly improve the coding efficiency of H.264 for surveillance video. Video content is analyzed and video semantics are extracted using video analytics algorithms such as segmentation, classification and tracking. In contrast to existing approaches, our Analytics-Modulated Compression (AMC) scheme does not require coding of object shape information and produces bit-streams that are standards-compliant and not limited to specific H.264 profiles. Extensive experiments were conducted involving real surveillance scenes. Results show that our technique achieves compression gains of 67% over JM. We also introduced AMC Rate Control (AMC RC) which allocates bits in response to scene dynamics. AMC RC is shown to significantly reduce artifacts in constant-bitrate video at low bitrates.

An apparatus and method for combining multimedia data are provided. The method includes obtaining first multimedia content from a first source, obtaining second multimedia content from a second source, selectively combining the first multimedia content with the second multimedia content, and outputting the selectively combined multimedia content. According to implementations of the invention, selected portions and/or fragments of multimedia content may be mashed up rather than the entirety of the multimedia content from either or both sources. Also, the mashup of the multimedia content may be varied and adapted based on the characteristics of the device performing the mashup as well as the characteristics of the available transport mechanism. Finally, implementations of the invention provide for flexible transformation and precise synchronization among multimedia elements.

We address the problem of rate scaling of multiple layered video streams in applications such as a multi-camera video surveillance system. This differs from the single video streaming scenario in that relevant information from all sources has to be aggregated and a collective decision made. We propose a scenario to achieve better granularity in quality adaptation by considering inter-source and inter-layer streaming jointly, using Operation Research techniques to arrive at an optimal or nearoptimal solution. We formulate our Multi-Source MultiLayer Selection (SLS) problem in the form of a MultipleChoice Knapsack Problem (MCKP). We analyze optimal and approximate algorithms to determine their suitability for solving the problem. We present a simple modification based on an existing greedy aglorithm by exploiting some properties of layered video. The modified SLS algorithm is extended to incorporate weights (Weighted SLS - WSLS - algorithm). Via experimental results using MPEG-4 FGS, we show that WSLS improves the performance for specialized applications. We also discuss the various network configurations of a multi-source video distribution system.

A method and apparatus to generate receive and share anchored location information and associated information on content enjoyment experience over a network. The method includes, responsive to receiving a request to stream the multimedia content over the network, determining whether anchored location information for the multimedia content has been generated. The method includes requesting the anchored location information for the multimedia content. Additionally, the method includes, responsive to receiving the anchored location information, displaying a number of visual indicators for the anchored location information on a presentation timeline for the multimedia content, and generating additional anchoring location information to be shared with other users.

Mobile Cloud Computing refers to mobile services that use the computing resources and data on the cloud to provide a requested service. A request from a mobile client leads to a process in the cloud that operates on the data in the cloud and the result of this processing is returned to the mobile client. The main reasons for using the cloud to deliver mobile services are lack of sufficient computing and data resources on the mobile client This cloud computing model works especially well for mobile devices and enables services that are not otherwise possible because of limited computing and communication resources. Cloud computing can also improve the energy performance of mobile applications when computationally intensive tasks are off loaded to the cloud.

We describe the implementation of a streaming client-server system for object-based audio-visual presentations in general and MPEG-4 content in particular. The system augments the MPEG-4 demonstration software implementation(IM1) for PC's by adding network-based operation with full support for the Delivery Multimedia Integration Framework (DMIF) specification, a streaming PC-based server with DMIF support (via Xbind Inc's XDMIF suite), and multiplexing software. We describe XDMIF, the first reference implementation of the DMIF specification. The MPEG-4 server is designed for delivering object-based audio-visual presentation. We discuss the issues in the design and implementation of MPEG-4 servers. The system also implements a novel architecture for client-server interaction in object-based audio-visual presentations, using the mechanism of command routes and command descriptors. This new concept of command routes and command descriptors is useful in developing sophisticated interactive applications.