Abstract: The present disclosure relates to an object selection system that automatically detects and selects objects in a digital image based on natural language-based inputs. For instance, the object selection system can utilize natural language processing tools to detect objects and their corresponding relationships within natural language object selection queries. For example, the object selection system can determine alternative object terms for unrecognized objects in a natural language object selection query. As another example, the object selection system can determine multiple types of relationships between objects in a natural language object selection query and utilize different object relationship models to select the requested query object.

Abstract: The present disclosure provides method and apparatus for providing a summary of a multimedia document in a session. In some implementations, a message may be received from a user in a session and the session is between the user and an electronic conversational agent. The multimedia document may be obtained based at least on the message. The emotion information in the multimedia document may be extracted. The summary of the multimedia document may be generated based at least on the message and the extracted emotion information. A response including the generated summary of the multimedia document may be provided to the user.

Abstract: A query is received that requests issues relevant to a user. Thereafter, a plurality of issues responsive to the query are retrieved. The retrieved issues are ranked using a first machine learning model to result in a first subset of the retrieved issues. The first subset of the retrieved issues are then ranked using a second, different machine learning model to result in a second subset of the retrieved issues which are a subset of the first subset of the retrieved issues. Data can then be provided which is responsive the query and includes at least a portion of the second subset of the retrieved issues. Related apparatus, systems, techniques and articles are also described.

Abstract: The invention uses document retrieval to explain to a human user the properties of a query object that are revealed by a machine learning procedure, lending interpretability to the procedure. A query object is compared to reference objects by transforming the query object and reference objects into representative tokens. Reference objects with many tokens in common with the query object are returned as relevant result objects by a document retrieval system. The token representation furthermore admits comparison between features of the query object and matched features of the reference object or between the query object and groups of reference objects having common features, thus emphasising characteristics of the query and reference objects of semantic importance to the user based on the intention of their search. Embodiments include retrieval of 2-dimensional or 3-dimensional images, audio clips, and text.

Abstract: The present disclosure provides systems and methods that enable map search recommendations based on a geo-semantic index developed using image content analysis. In one example, a computer-implemented method can include obtaining, by one or more computing devices, a vocabulary of image feature types associated with user activities. The method can include obtaining a collection of imagery. The method can include performing image content analysis on the collection of imagery based on the vocabulary of image feature types. The method can include generating at least one activity score for each of a plurality of location cells in a geo-semantic index based at least in part on the vocabulary of image feature types. The method can include populating the geo-semantic index of location cells, the geo-semantic index of location cells including data indicative of the at least one activity score for each location cell.

Abstract: A method for clustering groups of photographs, wherein users are each identified by a unique identifier, each user photographs. The method includes capturing photographs; assigning, to each captured photograph, at least one metadata defined by a type, comparing the metadata assigned to each photograph to determine at least one discriminant type, grouping at least two photographs by discriminant type of metadata and clustering the groups if the number of photographs is superior to a first predefined limit value. The method further includes determining a degree of similarity of a cluster of photographs depending on metadata, and defining a common cluster among the users if the degree of similarity is superior to a second predefined limit value.

Abstract: Systems and methods data structures queries to manage loading time of multimedia content are provided. A system receives an input audio signal from a computing device and identifies a request. The system identifies a quantized day value and a quantized time value. The system retrieves, via a lookup in a multi-dimensional matrix data structure with the quantized day value and quantized time value, signals for the quantized day value and the quantized time value. The system generates a query with the signals, and applies the query to a multimedia content data structure to identify a plurality of multimedia content items that match the plurality of signals. The system provides an indication of the plurality of multimedia content items that match the signals for the quantized day value and the quantized time value retrieved from the multi-dimensional matrix data structure.

Abstract: A story album display method and apparatus, and relate to the field of communications technologies, so that a thematic story album can be generated. The method includes: aggregating, by a terminal, N images in a gallery based on a first dimension, where the first dimension includes a photographing time and/or a photographing location, and N>1; and removing, by the terminal, an invalid image from the N images, to obtain the story album comprising the M images, wherein the invalid image comprises an image with an invalid label, or one or more images with an image similarity greater than a threshold; and displaying, by the terminal, an album cover of a story album, where the story album includes M images in the N images, the M images are associated with a theme of the story album, and M<N.

Abstract: A system for searching for similar medical images includes a reference library in the form of a multitude of medical images, at least some of which are associated with metadata including clinical information relating to the specimen or patient associated with the medical images. A computer system is configured as a search tool for receiving an input image query from a user. The computer system is trained to find one or more similar medical images in the reference library system which are similar to the input image. The reference library is represented as an embedding of each of the medical images projected in a feature space having a plurality of axes, wherein the embedding is characterized by two aspects of a similarity ranking: (1) visual similarity, and (2) semantic similarity such that neighboring images in the feature space are visually similar and semantic information is represented by the axes of the feature space.

Abstract: A server obtains user data corresponding to a first content domain. The server identifies, from the user data, a plurality of labels. A respective label of the plurality of labels corresponds to a distinct characteristic of content items of the first content domain. The server utilizes a neural network to generate a plurality of user embeddings. A respective user embedding of the plurality of user embeddings includes a plurality of labels that correspond to a respective user. The server determines, using the plurality of user embeddings, a first content item of a plurality of content items of a second type that meets matching criteria for a first user. The server further provides, to a device of the first user, information that corresponds to the first content item of the second content domain.

Abstract: Disclosed aspects relate to commentary management in a social networking environment. The social networking environment may include a set of media clips. The set of media clips may be analyzed in the social networking environment with respect to a set of commentary typology data. Based on the analyzing, a set of benchmark typology data which indicates a set of commentary norms of the set of media clips may be determined. A set of benchmark typology data may be established for utilization by the social networking environment.

Abstract: A system for unloading tables of a database is provided. In some aspects, the system performs operations including determining that a number of accesses to a table occurring within a time period has satisfied an access threshold. The operations may further include identifying, in response to the determining, a first timestamp indicating a most recent access to the table. The operations may further include determining whether a difference between a current timestamp and the first timestamp satisfies a first time threshold. The operations may further include comparing, in response to the difference satisfying the first time threshold, a ratio of the difference and a size of the table to a ratio threshold. The operations may further include unloading, in response to satisfying the ratio threshold, the table. The operations may further include adjusting, based on the feedback, the first time threshold and/or the ratio threshold.

Abstract: The disclosed embodiments provide a method and system for processing network data. During operation, the system obtains one or more event streams from one or more remote capture agents over one or more networks, wherein the one or more event streams include event data generated from network packets captured by the one or more remote capture agents. Next, the system applies one or more transformations to the one or more event streams to obtain transformed event data from the event data. The system then enables querying of the transformed event data.

Abstract: Systems and methods for gathering research data using multiple monitoring devices are provided. The systems and methods include a processor to generate message data by supplementing first information collected by a first monitoring device with second information collected by a second monitoring device, the first information and the second information collected from media presented by a monitored device, and process the message data to determine a portion of the media that is encoded and a portion of the media that is unencoded. The example systems and methods also include a memory to store an indication that the message data is valid when the message data represents a code encoded in the media, and store data indicating the portion of the media that is encoded.

Abstract: The disclosed embodiments provide a system that facilitates the processing of network data. During operation, the system obtains a set of event streams from one or more remote capture agents over one or more networks, wherein the set of event streams comprises time-series event data generated from network packets captured by the one or more remote capture agents. Next, the system causes for display, within a graphical user interface (GUI), a first set of user interface elements, wherein the first set of user interface elements includes event stream information for an event stream in the set of event streams and a first graph of a metric associated with the time-series event data in the event stream. The system then updates the first graph in real-time with the time-series event data from the one or more remote capture agents.

Abstract: Techniques allow a computer to responsively search for graph shapes similar to a user-selected graph shape much faster. Data can be pre-processed and stored as vectors, along with an index. The index can be used to find similar vectors that represent graph shapes similar to a user-selected shape in a computationally efficient manner. Vectors of multiple resolutions can be used to anticipate different sizes of a graph that a user can select, and comparisons can be repeated and refined. When a satisfactorily small number of candidate vectors are determined, more computationally intensive distance calculations can be performed on data reconstructed from the vectors.

Abstract: The disclosed embodiments provide a system that facilitates the processing of network data. During operation, the system causes for display a graphical user interface (GUI) for configuring the generation of time-series event data from network packets captured by one or more remote capture agents. Next, the system causes for display, in the GUI, a first set of user-interface elements for specifying a grouping of a set of event streams containing the time-series event data by an event stream attribute associated with the event streams. The system then causes for display, in the GUI, a second set of user-interface elements containing event stream information for one or more subsets of the event streams represented by the grouping of the event streams by the event stream attribute.

Abstract: An image search device receives an image search request and selects, from a plurality of images, a first group of images that match search conditions based on the search request. The image search device further selects, from the first group of images, a second group of images based on a score calculated by a predetermined evaluation formula, and outputs information about the second group of images as a search result. The predetermined evaluation criteria may be set so as to increase the score for an image in the first group of images based on positive engagement by many people on the predetermined internet service and based on the extent that the image is less similar to other images in the first group of images.

Abstract: A system for performing data classification operations. In one embodiment, the system comprises a file system configured to store a plurality of computer files and a scanning agent configured to traverse the file system and compile data regarding the attributes and content of the plurality of computer files. The system also comprises an index configured to store the data regarding attributes and content of the plurality of computer files and a file classifier configured to analyze the data regarding the attributes and content of the plurality of computer files and to classify the plurality of computer files into one or more categories based on the data regarding the attributes and content of the plurality of computer files. Results of the file classification operations can be used to set appropriate security permissions on files which include sensitive information or to control the way that a file is backed up or the schedule according to which it is archived.

Abstract: A method includes accessing an audiovisual composition comprising a target video segment and a source video segment. The method also includes, in response to presence of the target video segment and the source video segment in the audiovisual composition: accessing a first keyword associated with the source video segment; and calculating a first relevance score for the first keyword relative to the target video segment based on a temporal position of the source video segment in the audiovisual composition and a temporal position of the target video segment in the audiovisual composition; accessing a textual query comprising the first keyword. The method additionally includes: generating a first query result based on the textual query, the first query result comprising the target video segment based on the first relevance score; and at a native composition application, rendering a representation of the first query result.