Abstract: Provided is a method performed by one or more computers for outputting a measurement of a dimension of a body part in an input image, the method includes receiving the input image captured using an image capturing unit, the input image includes the body part and a reference object of a predefined dimension, predicting a segmentation mask of the input image, the segmentation mask differentiating image pixels of the body part from image pixels of a background region in the input image, processing the reference object in the input image to predict a pixel dimension of the reference object, obtaining pixel coordinates of a plurality of key points of the body part using the segmentation mask, modifying the obtained pixel coordinates based on the predicted pixel dimension of the reference object and outputting the measurement of the dimension of the body part based on the modified pixel coordinates.

Abstract: A television programming recommender combines the explicit viewing preferences, i.e. user specified preferences, of viewers with their television viewing behavior (implicit preferences) to generate program recommendations. The explicit viewing preferences are utilized to generate an explicit recommendation score, E, for an upcoming television program. The implicit viewing preferences are utilized to generate an implicit recommendation score, I, for the program. A combined recommendation score, C, is computed based on the explicit and implicit scores, E and I. The combined recommendation score, C, can be computed using a weighted linear mapping.

Abstract: A method and apparatus are disclosed for updating a user profile in a recommendation system for a given user based on auditory or gestural feedback information provided by the user. The auditory or gestural feedback is detected using audio or video processing techniques, or both, and includes, for example, auditory or gestural commands or facial expressions indicating the strength of the user's preferences. The auditory or gestural feedback can be explicit or implicit. Once predefined behavioral feedback is identified, the present invention updates the corresponding user profile, in an appropriate manner.

Abstract: A method for generating a recommendation is provided. The method includes the steps of: receiving at least one of a negative and positive example from one or more other users; and determining a recommendation for a user based on at least one of the negative and positive examples. The method can further include the step of generating a user profile for the user based on previous behavior of the user, in which case the determining step can include determining the recommendation based on the negative example and the user profile. The determining step can also include the step of determining the recommendation based on both of the negative and positive examples.

Abstract: A method and arrangement for modifying settings of a television program recommender displays the rating (recommended or not recommended) for a selected television program, and also displays icons for selection by the user to indicate whether the user agrees or disagrees with the recommendation. The television program recommender then updates its settings based on the user's icon selection. In addition, if the user indicates that he/she disagrees with the recommendation, the television program recommender determines and displays the number of times that the user needs to indicate his/her desires with respect to the selected television program in order for the recommendation to agree with the user's desires.

Abstract: Extracting and processing video content encoded in a rendered color space to be emulated by an ambient light source, comprising extracting dominant color information from a video signal and transforming the color information through unrendered color space using tristimulus primary matrices to form a second rendered color space for ambient distribution. Steps include quantizing the rendered color space to form an assigned color distribution, such as by reducing possible color states, or binning to form superpixels; and selecting a dominant color using a mode, mean, median, or weighted average of pixel chromaticities. A color of interest can be further analyzed to produce a true dominant color, and past video frames can guide selection of dominant colors in future frames.

Abstract: In customizing a user profile employed by a recommendation system, users are prompted for feedback regarding content that is the subject of the recommendation system. Only feedback that does not degrade performance of the recommendation system, as measured by the error rate, is accepted and utilized to modify the user profile. Feedback that would degrade performance is discarded without being employed to alter the user profile. In this manner, error is continually driven toward a minimum by system changes based on feedback.

Abstract: An electronic programming guide (EPG) system employing a preference engine and processing system that combines explicit rule profile, history profile, and feedback profile data to generate new predictions. Television shows are presumed to be indexed by many features. These features are extracted and counted for TV shows watched (implicit profile), and for TV shows rated by the viewer (feedback profile). These profiles are straightforward to combine with suitably greater weight being given to the feedback information. In addition, explicit profiles can make recommendations that stand alone or may be used to modify recommendations arising from either of the two sources. The modifications may take the form of additive or multiplicative changes to the existing recommendations or some other suitable mathematical form.

Abstract: Extracting and processing video content encoded in a rendered color space to be emulated by an ambient light source, comprising extracting color information from a video signal and transforming the color information through unrendered color space using tristprimary matrices to form a second rendered color space to drive the ambient light source. Video signal decoding into frames can allow extracting average or other color information from an selected screen regions to reduce bitstream load, and negative gamma correction helps prevent garish or inappropriate chromaticities and luminance.

Abstract: Extracting and processing video content encoded in a rendered color space to be emulated by an ambient light source, using perceptual rules for intelligent dominant color selection. Steps include quantizing the video color space; performing dominant color extraction by using a mode, median, mean, or weighted average of pixel chromaticities; applying perceptual rules to further derive dominant chromaticities via [1] chromaticity transforms; [2] a weighted average using a pixel weighting function influenced by scene content; and [3] extended dominant color extraction where pixel weighting is reduced for majority pixels; and [4] transforming the dominant color chosen to the ambient light color space using tristimulus matrices. A color of interest can be further analyzed to produce a true dominant color, and past video frames can guide selection of dominant colors in future frames.

Abstract: Flicker free operation of ambient light sources that emulate video content during low luminance conditions, where the ambient light source is output thresholded so that an on/off change of state of the ambient light source can be initiated after an intensity variable passes one or two thresholds. Output thresholding is used when extracting and processing video content encoded in a rendered color space, which can be decoded into frames tapped by an interframe interpolation process using only color information from selected frames, such as extracting average or other color information from an selected screen regions. Negative gamma correction helps prevent garish or inappropriate chromaticities and lumina.

Abstract: A program recommender (300) that receives one or more starring actor data fields for a program. The recommender adjusts one or more of the received starring actor data fields (600) by utilizing a source separate from the received starring actor data fields to identify one or more starring actors in the program. The adjusted data fields may be made available for use in creating a viewer profile (400), or alternatively may be made available for determining a recommendation (330) for the program.

Abstract: A television programming recommender is disclosed that selectively obtains feedback information from a user to update one or more profiles associated with the user. Previously obtained implicit and explicit preferences are utilized to selectively focus the collection of feedback information to further update and refine the implicit and explicit preferences. The present invention obtains feedback from a user in a manner that maximizes the value of the obtained information and improves the performance of the television programming recommender. The present invention automatically requests feedback from the user upon the occurrence of predefined criteria. The nature of the requested feedback, and the manner in which the obtained feedback is used to adjust a profile, can vary.

Abstract: A system to autonomously authorize billing for a subscription plan for a user using data including available subscription services, a user profile, and a user supplied criteria for subscription service selection such as a spending limit related to the available subscription services. In one embodiment, the present invention may rate the available subscription services in accordance with the user profile and may then select a given number of high rated subscription services for the subscription plan. The user profile may be updated to reflect changes in a user's preference. The subscribed content may be provided to the user as a personal television channel.

Abstract: A method and apparatus are disclosed for recommending items of interest to a user based on recommendations made to one or more third parties. The recommendation scores generated by a primary recommender are influenced by recommendations generated for one or more third parties, such as a friend, colleague or trendsetter. The disclosed recommender corroborates with other recommenders when recommending items of interest and adjusts a conventional recommender score based on third party recommendations. The third party recommendations may be a top-N list of recommended items for a given third party, and may optionally include a recommendation score and an indication of whether or not the third party actually selected the recommended item. A recommender evaluates the viewing or purchase habits of a user and communicates with one or more other recommenders to determine the items that are being recommended by such other recommenders.

Abstract: Extracting and processing video content encoded in a rendered color space to be emulated by an ambient light source, comprising extracting color information from a video signal and transforming the color information through unrendered color space using tristprimary matrices to form a second rendered color space to drive the ambient light source. Video signal decoding into frames can allow extracting average or other color information from an selected screen regions to reduce bitstream load, and negative gamma correction helps prevent garish or inappropriate chromaticities and luminance.

Abstract: A system and method for customizing an advertisement based on a surrounding broadcast are provided. A start of a new advertisement is detected (S2) and its characteristic data, including a video characteristic and/or an audio characteristic are extracted (S4). Also surrounding broadcast data, including the video characteristic and/or the audio characteristic of the surrounding broadcast are extracted (at S3). A replacement advertisement, may be selected (S7) based on a comparison (S6) of the surrounding broadcast data with advertisement characteristic of the new advertisement and of stored advertisements; and based on the surrounding broadcast data, the video characteristic and/or the audio characteristic of the replacement advertisement are customized (S8). The selecting of the replacement advertisement and customizing it are performed such that its characteristic data match most closely the surrounding broadcast data.

Abstract: A method and apparatus are disclosed for recommending items of interest to a user, such as television program recommendations, before a viewing history or purchase history of the user is available. A third party viewing or purchase history is processed to generate stereotype profiles that reflect the typical patterns of items selected by representative viewers. A user can select the most relevant stereotype(s) from the generated stereotype profiles and thereby initialize his or her profile with the items that are closest to his or her own interests. A clustering routine partitions the third party viewing or purchase history (the data set) into clusters, such that points (e.g., television programs) in one cluster are closer to the mean of that cluster than any other cluster. A distance computation routine evaluates the closeness of a television program to each cluster based on the distance between a given television program and the mean of a given cluster.

Abstract: A program recommender (300) that receives one or more starring actor data fields for a program. The recommender adjusts one or more of the received starring actor data fields (600) by utilizing a source separate from the received starring actor data fields to identify one or more starring actors in the program. The adjusted data fields may be made available for use in creating a viewer profile (400), or alternatively may be made available for determining a recommendation (330) for the program.

Abstract: Flicker free operation of ambient light sources that emulate video content during low luminance conditions, where the ambient light source is output thresholded so that an on/off change of state of the ambient light source can be initiated after an intensity variable passes one or two thresholds. Output thresholding is used when extracting and processing video content encoded in a rendered color space, which can be decoded into frames tapped by an interframe interpolation process using only color information from selected frames, such as extracting average or other color information from an selected screen regions.