Abstract: Users desiring to generate videos from video clips may want to locate moments of interest within the video clips. A system and method described herein may be configured to provide recommendations of moments of interest within video clips post capture of the video clips. User accounts associated with users of the system may include preference information that defines user preferences with respect to values of attributes of video clips. Moments of interest may be identified within individual video clips when the individual video clips have at least one value of at least one attribute specified by the user preferences. Recommendations of identified moments of interest may be provide to users.

Abstract: Feature information characterize features of video clips may be obtained. A given video clip may be selected as a segment of a video edit. Other video clips may be iteratively selected as other segments of the video edit based on the feature information of the video clips and recommended feature information of the segments. Recommended feature information of a particular segment may be obtained by processing feature information of a previously selected video clip through a trained recurrent neural network. Video edit information defining the video edit may be generated. The video edit may include the selected video clips as the segments of the video edit.

Abstract: A method for determining a longest common subsequence in a plurality of text strings. The method comprises: separately converting a plurality of text strings into word sequences (S100); classifying the word sequences (S400); and performing longest common subsequence computation on every class (S500). The time needed by LCS computation can be saved by classifying text strings.

Abstract: A method for retrieving an image-text block from a web page is provided, which comprises: retrieving an image node; filtering the image node to obtain candidate image nodes; traversing, for each of the candidate image nodes, a node in sequence toward an ancestor node of the candidate image node in a preset maximum traversal depth until an ancestor node with a text is visited, using the ancestor node with the text as a candidate image-text block; clustering the candidate image-text blocks based on hash values of the path information of the candidate image-text blocks; and determining, for each image-text block cluster, a common ancestor node of the candidate image-text blocks within the image-text block cluster based on the path information of the candidate image-text blocks, and determining path information of the image-text block cluster based on the common ancestor node.

Abstract: A method includes: receiving training data comprising a plurality of training data items, each training data item labelled under a respective class and comprising a elements arranged in conformity with a structured representation having an associated coordinate system; determining patches of the training data, each patch comprising a subset of the elements of a respective training data item and being associated with a location within the co-ordinate system of the structured representation; and initialising a set of parameters for a Gaussian process. The method further includes iteratively: processing pairs of the determined patches, using a patch response kernel to determine patch response data; determining, using the patch response data, entries of a covariance matrix; and updating the set of parameters in dependence on the determined entries of the covariance matrix.

Abstract: The present disclosure relates to systems and methods for generating headshots from a plurality of still images. In one implementation, the system may include a memory storing instructions and a processor configured to execute the instructions. The instructions may include instructions to receive a plurality of still images from one or more video feeds, score the plurality of images along a plurality of dimensions based on a scale, rank the plurality of images using at least one of a composite score or at least one of the dimensions, select a subset of the plurality of images using the ranking, and construct at least one headshot of the user from the subset of the plurality of images.

Abstract: In an embodiment, a user equipment (UE) recognizes a set of faces within a set of media files stored on the UE using facial recognition. The UE identifies a set of prevalent faces based on a set of criteria including a prevalence of one or more faces among the set of media files. The UE scans real-time media using facial recognition to determine whether any prevalent faces from the set of prevalent faces are present in the real-time media. The UE performs an action based on whether the scanning detects any prevalent faces from the set of prevalent faces in the real-time media. By way of example, the action may include adding one or more enhancement effects to the real-time media, authorizing a communicative operation to proceed, authorizing access to the UE, or any combination thereof.

Abstract: A method for image matching includes acquiring a template image and a target image; acquiring a group of template features according to the template image; extracting a group of target features according to the target image; and according to template features and target features, calculating an degree of image similarity between the template image and each frame of target images, and using a target image with the maximum degree of image similarity as a matched image to the template image. In the image-matching method, image matching is performed by calculating an degree of image similarity between a template image and each target image according to a degree of image similarity between template features and target features, so that non-redundancy of features in an image matching process and correct image matching can be guaranteed, and the image matching accuracy can be improved.

Abstract: A diagnosis system includes circuitry configured to form an image to be used for diagnosing the image forming apparatus, receive designation of a first diagnosis condition for detecting abnormality of the image formed by using the image forming apparatus, scan the image formed by the image forming apparatus, using a scanner, extract feature information representing the abnormality from the scanned image in accordance with the designated first diagnosis condition, diagnose the abnormality of the image forming apparatus based on the extracted feature information in accordance with the designated first diagnosis condition, and determine, in response to receiving designation of a second diagnosis condition different from the first diagnosis condition after performing a diagnosis under the first diagnosis condition, whether the feature information extracted for the diagnosis under the first diagnosis condition is usable for a diagnosis under the second diagnosis condition.

Abstract: A first user and a second user may exchange messages during a session and the exchanged messages may be processed to suggest resources to the first user. For example, the first user may be a customer service representative assisting a customer, and the suggested resources may include text of a message to send to the customer. The resources may be suggested by computing a semantic representation of the messages in the session, computing a context vector that describes a context of the session, computing a context hash vector from the context vector, and retrieving one or more resources from a data store of resources using the context hash vector. Information about a resource may be presented to the first user to assist the first user in responding to the second user.

Abstract: Systems and methods for image classification include receiving imaging data of in-vivo or excised tissue of a patient during a surgical procedure. Local image features are extracted from the imaging data. A vocabulary histogram for the imaging data is computed based on the extracted local image features. A classification of the in-vivo or excised tissue of the patient in the imaging data is determined based on the vocabulary histogram using a trained classifier, which is trained based on a set of sample images with confirmed tissue types.

Abstract: A method for allowing a computer to classify an input containing data. A list of categories is received. A sub list of categories is selected, wherein the sub-list comprises those categories in the list that have corresponding distinct correlation scores above a predetermined value. Input data that tends to over correlate to the classification system is received. A truncated snapshot is generated, the truncated snapshot comprising only attributes from the plurality of input attributes that have corresponding input categories that match categories in the sub-list of categories. The data is classified using the truncated snapshot and the classification system.

Abstract: The use of the alternating direction method of multipliers (ADMM) algorithm to train a classifier may reduce the amount of classifier training time with little degradation in classifier accuracy. The training involves partitioning the training data for training the classifier into multiple data blocks. The partitions may preserve the joint distribution of input features and an output class of the training data. The training may further include performing an ADMM iteration on the multiple data blocks in an initial order using multiple worker nodes. Subsequently, the training of the classifier is determined to be completed if a stop criterion is satisfied following the ADMM iteration. Otherwise, if the stop criterion is determined to be unsatisfied following the ADMM iteration, one or more additional ADMM iterations may be performed on different orders of the multiple data blocks until the stop criterion is satisfied.

Abstract: Techniques are provided that include obtaining a vocabulary including a set of content indices that reference corresponding cells in a descriptor space based on an input set of descriptors. A plurality of local features of an image are identified based on the vocabulary, the local features being represented by a plurality of local descriptors. An associated visual word in the vocabulary is determined for each of the plurality of local descriptors. A plurality of global signatures for the image are generated based on the associated visual words, wherein some of the plurality of global signatures are generated using local descriptors corresponding to different cropped versions of the image, two or more of the different cropped versions of the image being centered at a same pixel location of the image, and an image recognition search is facilitated using the plurality of global signatures to search a document image dataset.

Abstract: A method for determining an impact score for a digital image includes providing the digital image wherein the digital image includes faces; using a processor to determine an image feature for the faces; using the processor to compute an object impact score for the faces, wherein the object impact score is based at least upon one of the determined image features; weighting the object impact score for the faces based on one of the determined image features for a face; using the processor to compute an impact score for the digital image by combining the weighted object impact scores for the faces in the image; and storing the computed impact score in a processor accessible memory.

Abstract: A system and method for grouping units for forecasting purposes is presented. A plurality of stock keeping units (SKUs) is presented to an embodiment. Initial medoids are chosen based on a vertex within a set of vertices, each of which represent a SKU. Then, each vertex within the set of vertices is associated with its closest medoid to form initial clusters. There can be a cap on the number of vertices in each cluster. Thereafter, an iterative algorithm is performed wherein a probability is assigned to each vertex. One or more vertices are randomly chosen, with the weights of the vertices weighting the random choice. The chosen one or more vertices are moved to another cluster. The algorithm is performed until no further improvements result from moving one or more vertices to another cluster. Other embodiments are also disclosed herein.

Abstract: Embodiments are generally directed to global optimal path determination utilizing parallel processing. An embodiment of an apparatus includes a central processing unit (CPU); a graphical processing unit (GPU), the GPU being capable of a plurality of processing threads; and a memory to store data for a system under evaluation, the system under evaluation including a set of nodes having a first endpoint, a second endpoint, and multiple paths between the first endpoint and the second endpoint. The apparatus is to determine a most energy efficient path between the first endpoint and the second endpoint utilizing parallel processing of a push and relabel graph cut algorithm. Performance of the push and relabel algorithm includes a plurality of process iterations, each process iteration including performance of a relabel operation, a push operation in a first direction, and a push operation in a second direction.

Abstract: The present disclosure relates to systems, methods, and devices for facial recognition identification for in-store payment transactions. In particular, a payment system allows a user to engage in a payment transaction with a merchant to purchase goods or services at an in-store checkout location. For example, one or more implementations involve receiving a payment request to initiate an in-store payment transaction between a user and a merchant, the payment request including an image of the user. One or more embodiments identify a payment account for the user based on the image and send a payment confirmation request to a client device of the user. Additionally, one or more embodiments process the in-store payment transaction based on a confirmation response received from the client device.

Abstract: Computer-implemented methods are provided for analyzing datasets. Consistent with disclosed embodiments, a computing system may be configured to select a cluster from clusters partitioning the dataset. The clusters may include a subset of the dataset, and may be associated with a current medoid of the cluster and a current cost of the cluster. The computing system may determine a new cost of the selected cluster and a new medoid of the selected cluster based on a matrix with rows corresponding to data in a subset of the cluster. The columns may correspond to data in the dataset or only to data in the cluster. The computer system may replace the current medoid of the selected cluster with the new medoid of the selected cluster based on the new cost of the selected cluster. The computer system may output the cluster information to determine a structure of the dataset.

Abstract: A system and method for training a system for monitoring administration of medication. The method includes the steps of a method for training a medication administration monitoring apparatus, comprising the steps of defining one or more predetermined medications and then acquiring information from one or more data sources of a user administering medication. A first network is trained to recognize a first step of a medication administration sequence, and then a second network is trained to recognize a second step of a medication administration sequence based upon the training of the first network.

Abstract: A computer-implemented method for real-time coding of medical group codes such as diagnosis and procedure related groups is described. In one embodiment, one or more initial medical group codes may be assigned to a patient record based on a first set of inputs. Upon assigning the one or more initial medical group codes, a coding summary of the one or more assigned medical group codes may be displayed. While displaying the coding summary, at least one input from a subsequent set of inputs may be received and updating one or more medical group codes in the patient record.

Abstract: A computer-implemented system and method for generating document training sets is provided. Unclassified documents are provided to two or more classifiers. A classification code assigned to each unclassified document is received. A determination is made as to whether a disagreement exists between classification codes assigned to a common unclassified document via different classifiers. The common unclassified document with a disagreement in classification codes are provided for further review. Results of the further review include one of a new classification code and confirmation of one of the assigned classification codes. The unclassified documents for which a disagreement exists are grouped as a training set.

Abstract: The present invention discloses a mobile health intelligent medical guide system and method thereof. The method comprises: collecting patient chief complaint by use of a mobile terminal, sending the patient chief complaint to a cloud server through the mobile phone device internet, analyzing and processing the patient chief complaint by use of the keyword extraction, text word segmentation, fuzzy matching and sorting recommendation technologies based on a medical knowledge base, automatically generating a disease examination result, and generating an intelligent medical guide result to be fed back to the mobile terminal in combination with the doctor information; and then optimizing the disease examination result and the intelligent medical guide result one by one until the patient ends the query or the diagnosis result achieves the optimum. The system can assist the patient to perform self-helped disease examination and medical guide in the mobile environment.

Abstract: The present disclosure relates to an image classification and clustering method and device. Two images containing human faces may be classified into one cluster or different clusters based on a cluster merging threshold adaptively determined according to the combinational face poses in the two images. The adaptive cluster merging threshold help reduce false positive and false negative classification of human face containing images into clusters.

Abstract: Presented herein are techniques for assignment of an identity to a group of captured images. A plurality of captured images that each include an image of at least one person are obtained. For each of the plurality of captured images, relational metrics indicating a relationship between the image of the person in a respective captured image and the images of the persons in each of the remaining plurality of captured images is calculated. Based on the relational metrics, a clustering process is performed to generate one or more clusters from the plurality of captured images. Each of the one or more clusters are associated with an identity of an identity database. The one or more clusters may each be associated with an existing identity of the identity database or an additional identity that is not yet present in the identity database.

Abstract: A security system to detect a concealed item carried by a traveler in motion, the security system includes a camera configured to capture an image series of the traveler in a Eulerian or Lagrangian frame of reference, wherein the captured image series contains motions generated by the concealed item; an alarm system configured to produce an alert signal; and an electronic control unit. The electronic control unit is configured to magnify motions generated by the concealed item to generate perceptible motions, provide an output image series that contains the perceptible motion, detect characteristic kinematic behaviors of the concealed item from the output image series, measure characteristic kinematic quantities of the characteristic kinematic behaviors, determine a presence of the concealed item from the characteristic kinematic quantities, and activate the alarm system to produce the alert signal.

Abstract: In the present work, quantum clustering is extended to provide a dynamical approach for data clustering using a time-dependent Schrödinger equation. To expedite computations, we can approximate the time-dependent Hamiltonian formalism by a truncated calculation within a set of Gaussian wave-functions (coherent states) centered around the original points. This allows for analytic evaluation of the time evolution of all such states, opening up the possibility of exploration of relationships among data points through observation of varying dynamical-distances among points and convergence of points into clusters. This formalism may be further supplemented by preprocessing, such as dimensional reduction through singular value decomposition and/or feature filtering. Additionally, the parameters of the analysis can be modified in order to improve the efficiency of the dynamic quantum clustering processes.

Abstract: An information processing apparatus includes a set specifying unit, a clustering unit, an image selection unit, and an image arrangement unit. The set specifying unit specifies a set of images from among a plurality of images under a predetermined condition. The clustering unit classifies, after the set of images is specified by the set specifying unit, the plurality of images into any of the same number of clusters as that of image layout regions. The image selection unit collectively selects images that constitute the set of images from among the images included in the clusters generated by the clustering unit. The image arrangement unit arranges, in the image layout regions that correspond to the clusters one-to-one, the images constituting the set of images selected from the clusters by the image selection unit.

Abstract: A computer system gleans data from patient records and clinical trial descriptions using NLP techniques. NLP annotation data is used to generate clinical trial feature vectors and patient feature vectors. Clinical trial feature vectors and patient feature vectors are compared to match appropriate patient candidates with clinical trial openings.

Abstract: In one embodiment, a computing device receives an image. A large hash value is generated for the image based on a content-aware hashing function, resulting in the large hash value having a first number of dimensions. A small hash value is calculated for the image based on the large hash value and a locality-sensitive hashing function. The small hash value has a reduced number of dimensions compared to the large hash value. The small hash values for two or more images, respectively, will be close to each other if the two or more images are similar in content, and the small hash values will be different if the images are not similar. The small hash value for the image is used to determine whether the image is similar to one or more other images.

Abstract: A method for organizing and processing feature based data structures that can be used in linguistic spell checking and auto-correction, comprising: splitting an original dictionary into sub-dictionaries based on different values of a common feature such as high frequency words; receiving an input text that contains errors; determining a sub-dictionary selection feature from the input human-readable text; selecting the sub-dictionary based on the determined sub-dictionary selection feature; executing a first matching in the selected sub-dictionary, wherein a match is found if a similarity between the characters, words, or phrases in proximity of the errors in the input text and a character, word, or phrase in the sub-dictionary is above a threshold; if a unique match is found, the result is returned as an output to correct the errors; otherwise, executing a second matching with a raised threshold, and repeating the second matching until a unique match is found.

Abstract: Techniques are disclosed for generating a low-dimensional representation of an image. An image driver receives an image captured by a camera. The image includes features based on pixel values in the image, and each feature describes the image in one or more image regions. The image driver generates, for each of the plurality of features, a feature vector that includes values for that feature corresponding to at least one of the image regions. Each value indicates a degree that the feature is present in the image region. The image driver generates a sample vector from each of the feature vectors. The sample vector includes each of the values included in the generated feature vectors.

Abstract: A marker tracking system configured to detect light patterns (e.g., infrared light patterns) generated by one or more markers is described. A given marker is configured with a code which identifies the marker in a motion tracking camera field of view. Motion tracking camera(s) record the emitted infrared light and are configured to directly, or in conjunction with an associated computing device, computationally distinguish a given marker with high accuracy and efficiently.

Abstract: A method of dynamically updating a feature database that contains features corresponding to a known target object includes providing an image, extracting a first set of features from within the captured image, and comparing the first set of features to the features stored in the feature database. If it is determined that the target object is present in the image then at least one of the extracted features of the first set that are not already included in the feature database are added to the feature database.

Abstract: A method for building a tree of parse items involves receiving a plurality of parse items stored in an ordered data structure, processing semantic attributes associated with the plurality of parse items, generating a merged parse item from at least two parse items of the plurality of parse items, and forming a portion of a tree data structure such that the merged parse item is a parent of the at least two parse items.

Abstract: A method is provided for image processing. The method includes receiving an image dataset having image data for a plurality of images and a group dataset having group information for each image. The method further includes transforming the image dataset into a sparse vector by applying sparse coding and using the group information. The method also includes dividing each of dimensions of the sparse vector into multiple groups with a matrix. The matrix is generated such that the matrix takes on a higher value when samples in a same group from among the multiple groups have same non-zero dimensions above a threshold amount of time and takes on a lower value compared to the higher value when the samples in the same group lack the same non-zero coefficients above the threshold amount of time. The method additionally includes transforming the sparse vector into a summation vector using the multiple groups.

Abstract: A document analysis module analyzes electronic media items and identifies regions and region types for the electronic media items. The document analysis module may use rules, typographical feature sets, and cluster analysis to identify regions and region types. The document analysis module may also receive user input and may use the user input to identify regions and region types. The document analysis module may further use template pages to identify regions and region types.

Abstract: A same person determination device, a same person determination method, and a control program of a computer of the same person determination device capable of determining whether persons are the same persons even when there are similar faces are provided. It is determined whether there are a plurality of approximation and non-approximation relationships in which a feature amount of one face of one image approximates to a feature amount of one face of the other image (YES in step 28), and the feature amount of the one face of the one image does not approximate to feature amounts of all other faces other than the one face of the other image (YES in step 29) (step 31). In a case where there are the plurality of approximation and non-approximation relationships, the one face of one image and the one face of the other image are determined to be of the same person.

Abstract: The disclosure concerns processing hyperspectral or multispectral images. Image data comprises a sampled image spectrum represented by first values for each pixel location representative of an intensity associated with a wavelength index. A processor determines for each pixel location second values based on a measure of similarity between pixel locations with respect to the first values such that two pixel locations that 5 are similar with respect to the first values are also similar with respect to the second values. The processor then stores for each pixel location the determined one or more second values associated with that pixel location on a data store. This way, the image data is made suitable for applications, such as clustering or displaying, while pixels that are similar in the input image are also similar in the output data. This means that a 10 structure between the pixels in the input image is preserved.

Abstract: A method that incorporates teachings of the subject disclosure may include, for example, determining, by a system comprising a processor, more common features of a plurality of images according to similarity matrices indicating relative similarities between instances of common features occurring within multiple images of the plurality of images, defining, by the system, cluster groups associated with the more common features, where each cluster group comprises cluster images of the plurality of images, and where the more common features are present in each the cluster images, and performing, by the system, quality-based filtering on the cluster images to identify a target cluster image to represent the cluster images for each of the cluster groups. Other embodiments are disclosed.

Abstract: A computer-implemented system and method for cluster spine group arrangement is provided. A set of spine groups each having one or more spines of clusters and at least one singleton cluster is obtained. Unique spine groups are identified within the set and placed in a center of a display. At least a portion of the remaining spine groups in the set are placed to extend radially from the unique spine groups in the display center.

Abstract: A method for collecting and processing remotely sensed imagery in order to achieve precise spatial co-registration (e.g., matched alignment) between multi-temporal image sets is presented. Such precise alignment or spatial co-registration of imagery can be used for change detection, image fusion, and temporal analysis/modeling. Further, images collected in this manner may be further processed in such a way that image frames or line arrays from corresponding photo stations are matched, co-aligned and if desired merged into a single image and/or subjected to the same processing sequence. A second methodology for automated detection of moving objects within a scene using a time series of remotely sensed imagery is also presented. Specialized image collection and preprocessing procedures are utilized to obtain precise spatial co-registration (image registration) between multitemporal image frame sets.

Abstract: Embodiments of the present disclosure disclose a picture ranking method and a terminal. The picture ranking method comprises acquiring pictures stored in a terminal, detecting whether the pictures are first-type pictures, where the first-type picture refers to a picture including a human face, and when the pictures are first-type pictures, ranking the pictures according to a social relation model, or when the pictures are not first-type pictures, ranking the pictures according to a preset rule.

Abstract: A computing system is configured to categorize digital data records each relating to an interaction between a call center agent and a customer. The system includes a rules module to determine a first probability that a data record belongs to a category based one or more rules each rule defining a relationship between one or more features of the data record and the category; a probabilistic module to determine a second probability that the data record belongs to the category based on one or more probabilistic models of relationships between one or more of the features and the category; an arbitration module to determine whether or not the data record belongs to the category based on the first and second probabilities; and an action module to receive from the arbitration processor an indication that the interaction belongs to the category and to initiate an action appropriate to the category.

Abstract: Determining relationships between graphical elements in a fixed format document is provided. Graphical element sizes and their relative positions may be analyzed to determine whether two or more graphical elements should be aggregated together or whether the graphical elements should belong to different graphical groups. Graphs and figures comprising objects that are absolutely positioned may be detected, as well as objects where inter-element positions need to be preserved from regular document flow. Additionally, background objects may be differentiated from regular text flow when the objects overlap with text.

Abstract: Various embodiments provide a computer-implemented system and method providing a user interface framework for viewing large scale graphs. An example embodiment includes obtaining graph data including information related to a plurality of nodes, the plurality of nodes corresponding to search queries performed on a particular host site; constructing a plurality of sub-graphs, the sub-graphs being clusters of search results that are formed based on an amount of overlap among the search results produced from the search queries; rendering the graph by displaying each of the plurality of nodes at a respective absolute position within the graph and generating a plurality of tiles representing images of the plurality of sub-graphs; and displaying a sub-graph image corresponding to a selected position and zoom level.

Abstract: System and method for creating a collection of images are described, the method comprising: receiving images from at least one source of images; processing the images to produce an output collection of images, the processing comprising grouping the images to clusters of related images and selecting the preferred images in the clusters; and outputting the output collection of images, the output collection of images comprising the clusters of related images and indication of the preferred images in the clusters. The system for creating a collection of images comprising: a storage medium to receive images from at least one source of images; a processor to produce an output collection of images by grouping the images to clusters of related images and selecting the preferred images in the clusters; and a collection output medium for outputting the output collection of images.

Abstract: A method including: clustering a plurality of records, each record comprises at least one object image and at least one textual field associated with the object, to yield a plurality of clusters such that the object images in each cluster exhibit between them a visual similarity above a specified value; associating each cluster with a label by applying a dictionary function to the textual fields of each cluster, wherein the label reflects a common semantic factor of the textual fields of each cluster, wherein the common semantic factor has a value above a specified threshold. Accordingly, the visual similarity provides a measure of resemblances between two visual objects that can be based on at least one of: the fit between their color distribution such as correlation between their HSV color histograms, the fit between their texture, the fit between their shapes, the correlation between this edge histograms and face similarity.

Abstract: The technology relates to navigating imagery that is organized into clusters based on common patterns exhibited when imagery is captured. For example, a set of captured images which satisfy a predetermined pattern may be determined. The images in the set of set of captured images may be grouped into one or more clusters according to the predetermined pattern. A request to display a first cluster of the one or more clusters may be received and, in response, a first captured image from the requested first cluster may be selected. The selected first captured image may then be displayed.

Abstract: Various automated data flow tracking techniques can involve obtaining metadata identifying the data items from multiple data sources and using that information to identify the relationships among the data items. This information can then be provided to users. For example, a method can involve receiving a query; accessing metadata, which identifies data items generated by multiple data sources; identifying a set of responsive data items from among the available data items; identifying one or more relationships between the data items in the set of responsive data items, and responding to the query with information identifying the set of responsive data items and the one or more relationships.