Abstract: A method for monitoring and controlling the presentation of electronic media according to a credit-based scheme. “Debit-bearing” media may include video, audio, interactive software, etc. “Credit-bearing” media typically include commercials or banner ads. Other credit factors include cash, prizes, etc. The customer determines how to accumulate credits and how to spend them.

Abstract: A method of filtering video packets for video stream monitoring is provided. A video packet of a video stream is received. One or more features are extracted from a specified frame of the video packet via one or more histograms and frequency domain coefficients of the specified frame. One or more concept detectors are implemented on the one or more features creating one or more confidence values. The confidence values are transmitted to a display module for filtering of video packets.

Abstract: A computer-implemented method for configuring a classifier structure includes receiving a classifier structure for identifying a feature of input data, adding a plurality of operating points to a parent binary classifier of the classifier structure, and setting the operating points to minimize a total cost based on resources available to the classifier structure. Each operating point controls how data is classified by the parent binary classifier for distribution to the child binary classifiers.

Abstract: A system and method for streaming data over a communications network with varying streaming conditions, includes conditioning a data stream to create conditioned data representations including encoded representations targeting running conditions, wherein conditioning includes partitioning the data stream into data units, and generating the encoded representations of each of the data units, packaging the conditioned data representations with metadata specifying a target set of running conditions, wherein the conditioned data representations are packaged by pre-computing one or more trajectories among the encoded representations based on a given finite set of streaming conditions, observing a current run-time condition and selecting one of the packaged conditioned data representations for streaming over the computing network according to the running conditions in view of the current run-time condition in accordance with the observed current streaming condition, and a communications network responsive to the med

Abstract: A method of filtering video packets for video stream monitoring is provided. A video packet of a video stream is received. One or more features are extracted from a specified frame of the video packet via one or more histograms and frequency domain coefficients of the specified frame. One or more concept detectors are implemented on the one or more features creating one or more confidence values. The confidence values are transmitted to a display module for filtering of video packets.

Abstract: Disclosed is a method, upstream processing node, and computer readable medium for processing data packets. The method includes receiving an allocation for at least one computing resource. At least one data packet at one or more upstream processing elements in an upstream processing node is received. The method also includes determining if at least one output queue of the upstream processing elements includes available space for processing of the data packet. The data packet is processed in response to the output queue including available space to form a resulting data packet. The method further includes determining that an input queue of at least one downstream processing element of a plurality of downstream processing elements includes available space for receiving the resulting data packet In response to the determining, the resulting data packet is transmitted from the upstream processing element to the downstream processing element.

Abstract: A method is presented which reduces data flow and thereby increases processing capacity while preserving a high level of accuracy in a distributed speech processing environment for speaker detection. The method and system of the present invention includes filtering out data based on a target speaker specific subset of labels using data filters. The method preserves accuracy and passes only a fraction of the data by optimizing target specific performance measures. Therefore, a high level of speaker recognition accuracy is maintained while utilizing existing processing capabilities.

Abstract: Systems and methods for adaptive signal sampling and sample quantization for resource-constrained stream processing. Exemplary embodiments include a signal sampling and signal quantization method for a data stream from a ECG sensor into a pervasive device, the method including adaptively sampling the data stream, compressing data samples from the data stream, reducing the number of samples via quantization, defining a utility function for signal reconstruction, and formulating optimization on the reconstructed signal that is jointly sampled and quantized.

Abstract: One embodiment of the present method and apparatus for identifying a conversing pair of users of a two-way speech medium includes receiving a plurality of binary voice activity streams, where the plurality of voice activity streams includes a first voice activity stream associated with a first user, and pairing the first voice activity stream with a second voice activity stream associated with a second user, in accordance with a complementary similarity between the first voice activity stream and the second voice activity stream.

Abstract: A signal stream is transmitted when an available transmission bandwidth becomes reduced by providing alternate signal streams of different bit rates from the same source. The alternate signal streams are sub-sampled to form frames that have particular identifiers added thereto. The server is informed in advance, before actually providing the frames, of the identifiers. Because the server knows the current bandwidth limitations and knows the identifiers of the frames, the server can pass for transmission only those frames of the alternate signal stream that can fit within the transmission bandwidth that is available.

Abstract: Techniques for securely and adaptively delivering multimedia content. It is assumed that a set of alternate access units for each time slot is obtained. Then, the encryption stream index of each access unit from the set of alternate access units of the previous time slot are obtained. An encryption stream index is then assigned to each access unit in the set of alternate access units in the current time slot, such that the encryption index increases over time. Thus, the invention overcomes the problem of encrypting a multimedia stream that may have multiple access units for each time slot by selecting the encryption index for each access unit such that the encryption index increases, regardless of which access unit the delivery system (e.g., server) selects for transmission.

Abstract: A method is presented which reduces data flow and thereby increases processing capacity while preserving a high level of accuracy in a distributed speech processing environment for speaker detection. The method and system of the present invention includes filtering out data based on a target speaker specific subset of labels using data filters. The method preserves accuracy and passes only a fraction of the data by optimizing target specific performance measures. Therefore, a high level of speaker recognition accuracy is maintained while utilizing existing processing capabilities.

Abstract: Disclosed are a method, upstream processing node, and computer readable medium for dynamically stabilizing a stream processing system. The method includes receiving at least one computing resource allocation target. The further includes determining that an input data flow rate of at least one upstream processing element varies. The computing resource is dynamically allocated to the upstream processing element in response to the input rate of the upstream processing element varying. Data flow is dynamically controlled between the upstream processing element and at least one downstream processing element.

Abstract: Disclosed is a method, upstream processing node, and computer readable medium for processing data packets. The method includes receiving an allocation for at least one computing resource. At least one data packet at one or more upstream processing elements in an upstream processing node is received. The method also includes determining if at least one output queue of the upstream processing elements includes available space for processing of the data packet. The data packet is processed in response to the output queue including available space to form a resulting data packet. The method further includes determining that an input queue of at least one downstream processing element of a plurality of downstream processing elements includes available space for receiving the resulting data packet In response to the determining, the resulting data packet is transmitted from the upstream processing element to the downstream processing element.

Abstract: Techniques for securely and adaptively delivering multimedia content. It is assumed that a set of alternate access units for each time slot is obtained. Then, the encryption stream index of each access unit from the set of alternate access units of the previous time slot are obtained. An encryption stream index is then assigned to each access unit in the set of alternate access units in the current time slot, such that the encryption index increases over time. Thus, the invention overcomes the problem of encrypting a multimedia stream that may have multiple access units for each time slot by selecting the encryption index for each access unit such that the encryption index increases, regardless of which access unit the delivery system (e.g., server) selects for transmission.

Abstract: A method of filtering video packets for video stream monitoring is provided. A video packet of a video stream is received. One or more features are extracted from a specified frame of the video packet via one or more histograms and frequency domain coefficients of the specified frame. One or more concept detectors are implemented on the one or more features creating one or more confidence values. The confidence values are transmitted to a display module for filtering of video packets.

Abstract: A system, method and computer program product for classification of an analog electrical signal using statistical models of training data. A technique is described to quantize the analog electrical signal in a manner which maximizes the compression of the signal while simultaneously minimizing the diminution in the ability to classify the compressed signal. These goals are achieved by utilizing a quantizer designed to minimize the loss in a power of the log-likelihood ratio. A further technique is described to enhance the quantization process by optimally allocating a number of bits for each dimension of the quantized feature vector subject to a maximum number of bits available across all dimensions.

Abstract: A resource-efficient live streaming system includes a broadcaster and a streaming server. The broadcaster receives a live feed and broadcasts a media stream to the streaming server containing several descriptions of the live feed along with control information. The broadcaster includes a stream thinner that implements a pruning algorithm. If descriptions from different streams are similar enough, one or more of them may be discarded without penalizing the quality of service perceived by the receivers. The streaming server assembles compressed data units into streams according to the control information from the broadcaster. The streaming server may also gather client feedback in order to estimate the status of the transmission channels and forwards the information to the broadcaster. The streaming server builds and streams media information to clients according to user preferences and receiver capabilities.

Abstract: Techniques for computing a multimedia stream schedule in a resource-constrained environment. In one aspect of the invention, a technique for processing multiple media streams in accordance with a resource-constrained environment includes the following steps/operations. An optimization associated with a composite representation of the multiple media streams is computed based on timing constraints associated with the multiple media streams and one or more constraints associated with at least one device in the resource-constrained environment useable to present at least one of the multiple media streams. Scheduling transmission and/or storage of the multiple media streams, based on the optimization, is then performed. The multiple media streams may be encoded, based on the optimization, prior to the scheduling step/operation.

Abstract: A system for enforcing data stream continuity, in accordance with the present invention, includes a server coupled to a transmission link for providing a data stream to at least one client over the transmission link. The data stream is segmented into units. The server includes a scrambler for encrypting at least one first unit using an encryption key, and a steganographic unit for embedding the encryption key into at least one second unit for the data stream such that steganographic information is needed by the client to determine the encryption key and decipher the data stream.