Abstract: Image feature selection and extraction (e.g., for image classifier training) is accomplished in an integrated manner, such that higher-order features are merely developed from first-order features selected for image classification. That is, first-order image features are selected for image classification from an image feature pool, initially populated with pre-extracted first-order image features. The selected first-order classifying features are paired with previously selected first-order classifying features to generate higher-order features. The higher-order features are placed into the image feature pool as they are developed or “on-the-fly” (e.g., for use in image classifier training).

Abstract: Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

Abstract: Images are classified as photos (e.g., natural photographs) or graphics (e.g., cartoons, synthetically generated images), such that when searched (online) with a filter, an image database returns images corresponding to the filter criteria (e.g., either photos or graphics will be returned). A set of image statistics pertaining to various visual cues (e.g., color, texture, shape) are identified in classifying the images. These image statistics, combined with pre-tagged image metadata defining an image as either a graphic or a photo, may be used to train a boosting decision tree. The trained boosting decision tree may be used to classify additional images as graphics or photos based on image statistics determined for the additional images.

Abstract: An application transfer protocol allows users to find applications relevant to a search query in an application search system. The application transfer protocol is used with an index that maintains a database of applications that includes parameters, such as features and/or content of the application. When a user submits a query, the system determines one or more applications relevant to the search query and implements the application transfer protocol to identify and present results to a user.

Abstract: An application search system may maintain an index of applications available from multiple different application stores, and includes parameters, such as features and/or content of the applications. When a user submits a query, the system may derive contextual information pertaining to a user device used to submit the query, applications installed on a particular user device and/or usage information for installed applications. The system then may, in one example, determine one or more applications relevant to the search query and, depending on the contextual information derived, may provide an entry point to access a particular application at a task level, may prompt the user to install the application, or may provide a web result related to the particular application.

Abstract: Images are classified as photos (e.g., natural photographs) or graphics (e.g., cartoons, synthetically generated images), such that when searched (online) with a filter, an image database returns images corresponding to the filter criteria (e.g., either photos or graphics will be returned). A set of image statistics pertaining to various visual cues (e.g., color, texture, shape) are identified in classifying the images. These image statistics, combined with pre-tagged image metadata defining an image as either a graphic or a photo, may be used to train a boosting decision tree. The trained boosting decision tree may be used to classify additional images as graphics or photos based on image statistics determined for the additional images.

Abstract: A personal broadcast server system provides a customized broadcast to one or more users over a transmission media. A data storage device stores a plurality of broadcast elements. A data management system stores a user profile and a user state for each of the one or more users and also stores information associated with each of the plurality of broadcast elements. A broadcast element selector, having at least one broadcast element selector function, selects broadcast elements from the data storage device based on information contained in the data management system. A broadcast server receives the selected broadcast elements from the data storage device and provides the selected broadcast elements to a user over the transmission media. The personal broadcast server system may provide streaming audio, streaming video, or other forms of broadcast signals.

Abstract: Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

Abstract: Computer-readable media, computer systems, and computing devices facilitate generating binary classifier and entity extractor training data. Seed URLs are selected and URL patterns within the seed URLs are identified. Matching URLs in a data structure are identified and corresponding queries and their associated weights are added to a potential training data set from which training data is selected.

Abstract: A system for organizing images includes an extraction component that extracts visual information (e.g., faces, scenes, etc.) from the images. The extracted visual information is provided to a comparison component which computes similarity confidence data between the extracted visual information. The similarity confidence data is an indication of the likelihood that items of extracted visual information are similar. The comparison component then generates a visual distribution of the extracted visual information based upon the similarity confidence data. The visual distribution can include groupings of the extracted visual information based on computed similarity confidence data. For example, the visual distribution can be a two-dimensional layout of faces organized based on the computed similarity confidence data—with faces in closer proximity faces computed to have a greater probability of representing the same person.

Abstract: Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

Abstract: In embodiments consistent with the subject matter of this disclosure, a user may input strokes as digital ink to a processing device. The processing device may partition the input strokes into multiple regions of strokes. A first recognizer and a second recognizer may score grammar objects included in regions and represented by chart entries. The scores may be converted to a converted score, which may have at least a near standard normal distribution. The processing device may present a recognition result based on highest converted scores according to a recurrence formula. The processing device may receive a correction hint with respect to misrecognized strokes and may add a penalty score with respect to chart entries representing grammar objects breaking the correction hint. Incremental recognition may be performed when a pause is detected during inputting of strokes.

Abstract: A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive/negative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system.

Abstract: Systems and methods are described for face recognition using discriminatively trained orthogonal rank one tensor projections. In an exemplary system, images are treated as tensors, rather than as conventional vectors of pixels. During runtime, the system designs visual features—embodied as tensor projections—that minimize intraclass differences between instances of the same face while maximizing interclass differences between the face and faces of different people. Tensor projections are pursued sequentially over a training set of images and take the form of a rank one tensor, i.e., the outer product of a set of vectors. An exemplary technique ensures that the tensor projections are orthogonal to one another, thereby increasing ability to generalize and discriminate image features over conventional techniques.

Abstract: A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive/negative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system.

Abstract: A technique for increasing efficiency of inference of structure variables (e.g., an inference problem) using a priority-driven algorithm rather than conventional dynamic programming. The technique employs a probable approximate underestimate which can be used to compute a probable approximate solution to the inference problem when used as a priority function (“a probable approximate underestimate function”) for a more computationally complex classification function. The probable approximate underestimate function can have a functional form of a simpler, easier to decode model. The model can be learned from unlabeled data by solving a linear/quadratic optimization problem. The priority function can be computed quickly, and can result in solutions that are substantially optimal. Using the priority function, computation efficiency of a classification function (e.g., discriminative classifier) can be increased using a generalization of the A* algorithm.

Abstract: A personal broadcast server system provides a customized broadcast to one or more users over a transmission media. A data storage device stores a plurality of broadcast elements. A data management system stores a user profile and a user state for each of the one or more users and also stores information associated with each of the plurality of broadcast elements. A broadcast element selector, having at least one broadcast element selector functions, selects broadcast elements from the data storage device based on information contained in the data management system. A broadcast server receives the selected broadcast elements from the data storage device and provides the selected broadcast elements to a user over the transmission media. The personal broadcast server system may provide streaming audio, streaming video, or other forms of broadcast signals.

Abstract: A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive/negative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system.

Abstract: The present invention leverages spatial relationships to provide a systematic means to recognize text and/or graphics. This allows augmentation of a sketched shape with its symbolic meaning, enabling numerous features including smart editing, beautification, and interactive simulation of visual languages. The spatial recognition method obtains a search-based optimization over a large space of possible groupings from simultaneously grouped and recognized sketched shapes. The optimization utilizes a classifier that assigns a class label to a collection of strokes. The overall grouping optimization assumes the properties of the classifier so that if the classifier is scale and rotation invariant the optimization will be as well. Instances of the present invention employ a variant of AdaBoost to facilitate in recognizing/classifying symbols. Instances of the present invention employ dynamic programming and/or A-star search to perform optimization.

Abstract: A system and method for determining hierarchical information is described. Aspects include using the Collins model for parsing non-textual information into hierarchical content. The system and process assign labels to lines that indicate how the lines relate to one another.