Abstract: Aspects of the present disclosure relate to predictive screen recording. In examples, a user initiates screen recording, such that an initial recording region is recorded. During screen recording, one or more events, user inputs, and/or any of a variety of other features are processed to generate a predicted recording region, which is used to update the region for which screen recording output is generated accordingly. Thus, the recorded region of the screen may change dynamically, thereby reducing the amount of postprocessing, planning, and computing resources that would otherwise be associated with recording the screen of a computing device, among other examples.

Abstract: A system, method, and computer program are provided for providing a multi-merchant electronic shopping cart within a web browser. The shopping cart can be used at a plurality of unrelated merchant shopping sites and remains within the browser regardless of the displayed website. When a user selects the shopping cart, a user interface is displayed with information about a product on the website without navigating to a new webpage. If the product has options, the user is able to select for the options via the user interface. The user is also able to save products from a plurality of shopping sites to the shopping cart or purchase products from the shopping cart at one time. For each product to be purchased, a purchase transaction is conducted, on behalf of the user, with the merchant associated with the website from which the user added the product to the shopping cart.

Abstract: A data structure programmatically links the first product to a second product. The second product is historically purchased by the customer whenever the customer has also purchased the first product. A determination is made as to whether the customer purchased the second product together with the first product based upon the sales data. When the customer has failed to purchase the second product with the first product, instructions are transmitted to the retail store over the network to perform a verification that the second product is out-of-stock. An outcome of the verification from the retail store is received via the network. A determination is made as to a level of certainty that the second product is actually out-of-stock based upon an analysis of the sales data and the outcome of the verification. When the level of certainty exceeds a predetermined threshold, the PI value is adjusted to zero.

Abstract: Embodiments include systems and methods for remotely measuring distances in an environment captured by a device. A device captures a video stream of a device along with AR data that may include camera pose information and/or depth information, and transmits the video stream and AR data to a remote device. The environment may be analyzed to identify objects such as lines, edges, curves, shapes, anchors/corners, products, e.g., appliances, and other things of interest. Some or all of objects may be identified to the remote device to facilitate selecting an object or region of interest. Selected points for an object may be more precisely located by snapping them to corresponding anchor points for an object. Using anchor points facilitates more precise identification and/or measurement of an aspect of an object, such as one of its dimensions, the volume of a space, or performing other actions such as replacement of an object.

Abstract: According to the present disclosure, there is disclosed a method of providing search information using an electronic apparatus, which includes: checking information on a product group corresponding to a keyword acquired from a user; checking color information on one or more products included in the product group; and providing a search result page corresponding to the keyword, the search result page including at least some of one or more color chips corresponding to the information on the product group and the color information on the one or more products.

Abstract: A virtual assistant server extracts concept(s) from a received user query and correlates the extracted concept(s) to a plurality of nodes in a knowledge graph to identify qualifying path(s) in the knowledge graph. Further, when the two or more qualifying paths are identified, the virtual assistant server addresses one or more ambiguities in the knowledge graph by: prompting the user device to resolve a current one of the one or more ambiguities progressing from contextual nodes towards leaf nodes in the knowledge graph; receiving a response to the prompt from the user device; and repeating the prompting and the receiving until each of the one or more ambiguities is resolved and a matching path to the received query is identified. Finally, the virtual assistant server outputs content associated with a leaf node of the matched path to the user device.

Abstract: A computer-implemented method, system and computer program product for optimally performing stress testing against big data management systems. A set of random test queries is generated and compiled to determine the data points of the features (e.g., table type being queried) of the set of random test queries. A distance (e.g., Mahalanobis distance) is then measured between the data points of the features and the mean of a distribution of data points corresponding to each same feature of an extracted feature set. Each random test query whose distance exceeds a threshold distance is then ranked. The ranked random test queries are then executed in order of rank. Those executed random test queries which resulted in an error (e.g., system failure) are added to a log, which is used to identify those queries to perform a stress test against the big data management system.

Abstract: Methods, systems, and computer program products are provided for optimizing searches of records including text elements. The methods, systems, and computer program perform operations including receiving a regular expression search query from a client. The operations also include parsing elements of the regular expression search query. The operations further include identifying search mechanisms based on the elements parsed from the search query. In addition, the operations include searching a data set identified by the regular expression search query using the search mechanisms. Further, the operations include returning a search result from the data set to the client based on a result of the searching.

Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform the steps of a method to dynamically ingest and monitor online products. The method may include receiving access to a webpage, determining whether the webpage includes a predetermined template, and in response to receiving the predetermined template, ingesting one or more product images and product metadata from the webpage. If no template is found, the system may request search engine optimization metadata to determine if at least one image is of a product before initializing a machine learning algorithm to determine whether the images correspond to product images. If no associated metadata is found, the system may request manual input of associated metadata before displaying, in real-time and in a standardized format, the ingested photos and metadata, allowing a user to select photos representing products of interest.

Abstract: An electronic device and a method for providing a service corresponding to the selection of an object in an image are provided.

Abstract: In one embodiment, a method includes receiving an instruction to transition to a first virtual reality (VR) environment of a first VR application, accessing attribute information of one or more real-world objects in a real-world environment proximate to a VR display device, determining, for each of the one or more real-world objects, one or more first mixed reality (MR) functionalities applicable to the real-world object based on its attribute information, and rendering, for one or more displays of the VR display device, the first VR environment with one or more MR objects corresponding to the one or more real-world objects, wherein each MR object comprises one of the first MR functionalities applicable to the corresponding real-world object.

Abstract: A home view data structure is described. The home view data structure is made up of multiple entries. Each entry contains information identifying a home; and a quantitative value scoring the view available from the identified home, such that the contents of the data structure are usable to compare the identified homes on the basis of the views available from them.

Abstract: Methods and systems for generating a plurality of matching items that match a reference item are disclosed. The method includes first determining reference attribute data for the reference item, where the reference attribute data is multimodal. Next, selecting a deep learning multimodal matching model from a plurality of candidate multimodal matching models. The selected deep learning multimodal matching model has a first deep learning neural network (DLNN) for processing data having a first data mode and a second DLNN analyzer for processing data having a second data mode. Then, matching a potential matching item to the reference item using the selected deep learning multimodal matching model to generate a match score, where the match score is computed based on the reference attribute data for the reference item and attribute data for the potential matching item. Finally, adding the potential matching item to the plurality of matching items based on the match score.

Abstract: A method for processing model data of a set of garments includes storing first and second model data of a first and a second garment of the set, each of the model data including two-dimensional or three-dimensional geometry data defining a mesh associated with the respective garment. A limiting object of the respective garment is defined by at least a portion of the geometry data and constitutes a separation between an interior and an exterior of the respective garment. The first and the second garment constitute an inner garment and an outer garment that is worn over the inner garment. At least one opening object for the outer garment is stored, defined as a portion of the limiting object and constituting a transition for an item between the interior and the exterior of the outer garment. Intersection objects are determined for each of the garments, defining one or more intersections between the limiting objects of the garments.

Abstract: A computer-implemented method that includes displaying a graphical user interface (“GUI”) and receiving personalized information from at least one server computing device. The GUI includes a page. The personalized information identifies a theatre location, movies playing at the theatre location, dates, and showtimes associated with the movies and dates. The method includes displaying on the page, the movies, dates on which a particular movie is showing, and a particular showtime on a particular date. A selection is entered by the user into a user input displayed on the page. The selection changes the theatre location, the particular movie, the particular date, and/or the particular showtime without the user exiting the page. The page updates automatically to display the user selection. An indication is received that the user has selected a purchase input display on the page, and a purchase of at least one movie ticket is completed.

Abstract: An online system accesses a list of features used as input into a predictor to predict a performance metric for content presented to users. The online system computes importance scores for one or more of the features. A ranked list of categories is created, with each category having one or more sub-categories. For each feature having a computed importance score, the online system assigns, for each attribute in the ranked list of attributes for that feature, the feature to a sub-category in one of the categories in the ranked list of categories that has the same rank as the attribute in the ranked list of attributes for the feature, where the sub-category is associated with a label that corresponds with the attribute. For each sub-category in each category, a cumulative score is computed for the sub-category based on the importance scores of the features of that sub-category.

Abstract: An analysis of the scans is performed to determine whether the selected item was moved from the back room to the shelf, then returned from the shelf to the back room. The analysis also determines a re-bin time when the selected product was returned to the back room. An adjustment to the PI is blocked when last PI adjustment time is later than the re-bin time. An adjustment to the PI is also blocked when an audit indicator is received at the interface indicating that the retail store is under an audit. An adjusted PI value is determined when the analysis indicates that the selected item was moved from the back room to the shelf, then returned from the shelf, the adjusted PI value being at least one more than the shelf capacity value.

Abstract: Systems and techniques are generally described for attribute-based content selection and search. In some examples, a graphical user interface (GUI) may display an image of a first product comprising a plurality of visual attributes. In some further examples, the GUI may display at least a first control button with data identifying a first visual attribute of the plurality of visual attributes. In some cases, a first selection of the first control button may be received. In some examples, a first plurality of products may be determined based at least in part on the first selection of the first control button. The first plurality of products may be determined based on a visual similarity to the first product, and a visual dissimilarity to the first product with respect to the first visual attribute. In some examples, the first plurality of products may be displayed on the GUI.

Abstract: Techniques are disclosed for incremental agglomerative clustering of data, including but not limited to digital image data. Fewer than all of a plurality of existing digital image fingerprints are sampled from a first hierarchical data cluster of digital image fingerprints stored in a data storage device, the first hierarchical data cluster excluding a new digital image fingerprint. The new digital image fingerprint and the existing digital image fingerprints sampled from the first hierarchical data cluster are clustered to produce a second hierarchical data cluster of digital image fingerprints, the second hierarchical data cluster including the new digital image fingerprint. If a majority of the existing digital image fingerprints in the first hierarchical data cluster match the new digital image fingerprint, then the second hierarchical data cluster is mapped to the first hierarchical data cluster based on the determination.

Abstract: An electronic indication of a nil pick is received. Item information associated with the desired product, sales data concerning the desired product, supply chain information associated with the desired product, and a perpetual inventory (PI) value of the desired product are stored. An adjustment to the PI of the desired product is blocked when a predetermined event occurs at the retail store, or when information that contradicts the validity of the nil pick is received from the retail store. When the adjustment to the PI of the desired product is not blocked, an amount of the adjustment is determined based upon one or more of: the item information associated with the product, the sales data concerning the product, and the supply chain information associated with the desired product.

Abstract: A computer process for entity resolution of natural language records including training a semantic embedding function on a corpus of unlabeled training materials. The semantic embedding function can take a word and represent it as a vector, where the vector represents the word as it relates to the semantic information of the corpus of unlabeled training materials. The process may transform a list of normalized descriptions using the semantic embedding function into a list of vector representations of the descriptions. The process may transform words from a natural language record to a vector representation of the natural language record using the semantic embedding function, and may use a named entity recognizer. The process may find a best match description from the list of normalized descriptions using the list of vector representations of the descriptions and the vector representation of the natural language record, and may include using word mover distance.

Abstract: Disclosed herein are a method and system that utilize a programmed content predictor to dynamically select electronic publishing content. In particular, the content predictor applies a selection model to select content for one or more selected webpages presented during an electronic transaction. The selection model utilizes a set of one or more machine learning models to select content based on calculated quality scores. The nature of the quality scores determined by the quality score model depend on the particular application. The predictor generates and populates a permutation quality table based on a set of selected content items and page variant, wherein the page variant defines locations of content positions within a webpage. The predictor then consumes the selection model to select a best permutation of content item-content position combinations to be returned for display on a webpage.

Abstract: A device for providing consumer feedback including an enclosure, processors housed within the enclosure, an image capturing device in communication with the processors and configured to capture a user gesture, a display screen, the display screen in communication with the processors, a memory, and a battery configured to supply power to the display screen, the image capturing device, the processors, and the memory. The memory contains instructions to display a question on the display screen and display answer options to the question. The answer options correspond to a particular user gesture. The device may receive a plurality of selected answers from a plurality of users in response to the question. Each selected answer is selected from the plurality of answer options via the particular user gesture corresponding to the selected answer. The device may aggregate the received selected answers and display the aggregated selected answers on the display screen.

Abstract: A data structure programmatically links the first product to a second product. The second product is historically purchased by the customer whenever the customer has also purchased the first product. A determination is made as to whether the customer purchased the second product together with the first product based upon the sales data. When the customer has failed to purchase the second product with the first product, instructions are transmitted to the retail store over the network to perform a verification that the second product is out-of-stock. An outcome of the verification from the retail store is received via the network. A determination is made as to a level of certainty that the second product is actually out-of-stock based upon an analysis of the sales data and the outcome of the verification. When the level of certainty exceeds a predetermined threshold, the PI value is adjusted to zero.

Abstract: Provided are a method, a system, and a non-transitory computer-readable record medium for comparing common features of products and providing a comparison result. A product comparison method includes recognizing at least two comparable products from at least one image; displaying at least one common attribute of the at least two comparable products through a user interface; and based on the user interface receiving a user input that selects one of the at least one common attribute, as a selected attribute, providing a result of comparison between the at least two comparable products with regard to the selected attribute.

Abstract: Disclosed are various embodiments for generating a search results interface for sharing user content for subsequent media searches of a physical object. In one example, a system comprises machine readable instructions stored in the a memory of a client device. The instructions cause the client device to at least transmit to a computing device a request for an image search of an object. The request comprises an image of the object. An image result is received from the computing device in response to the request for the image search. The instructions cause the client device to display an image search results interface. The image search results interface includes an image result from the image search and an upload user interface component. The upload user interface component is configured to display an input interface for uploading user content associated with the object in the image result.

Abstract: A computer-implemented method for providing a vehicle recommendation to a user may include: obtaining one or more vehicle images via a device associated with the user; identifying one or more user-selected images of the one or more vehicle images based on user interaction with the one or more vehicle images performed by the user via a user interface; identifying one or more first-level attributes from the one or more user-selected images; obtaining one or more vehicle identifications from the one or more user-selected images; determining one or more second-level attributes based on the one or more vehicle identifications; determining a value of each of the one or more first-level attributes and the one or more second-level attributes; determining the vehicle recommendation based on the value; and transmitting, to the device associated with the user, a notification indicating the vehicle recommendation.

Abstract: Methods, systems, and computer-readable media for catalog item selection based on visual similarity are disclosed. A similarity detection system selects candidate items for an unavailable item in a catalog. The candidate items are selected from one or more item categories in which the unavailable item is classified. The system determines respective similarity scores for at least some of the candidate items with respect to the unavailable item. For a particular candidate item, the similarity score is determined based at least in part on a visual similarity between an image of the unavailable item and an image of the particular candidate item. The system selects, from the candidate items, a set of visually similar items to the unavailable item based at least in part on the similarity scores. The visually similar items are available to the user.

Abstract: The present invention aims to provide an information processing device, an information processing method, and the like capable of reducing labor of associating an item for sale with a category. The information processing device acquires an image specified by a user. The information processing device extracts a feature value of the specified image. The information processing device acquires category information corresponding to an item for sale represented by the specified image. The information processing device searches for images similar to the specified image, based on the extracted feature value. The information processing device causes at least one of the found images to be displayed as a search result. The information processing device, when the user has selected any one image from the displayed search result, makes a storage unit store the acquired category information in association with sale item identification information corresponding to the selected image.

Abstract: Systems and methods electronically obtain data regarding a plurality of sources and corresponding amounts of resources received from the sources for a plurality of relationship instances each associated with one or more respective domains of a plurality of domains. For each relationship instance of the plurality of relationship instances: the system electronically identifies a rate to calculate an amount of resource due to one or more respective domains associated with the relationship instance based on a source of a resource received for the relationship instance and the one or more respective domains and calculates an amount of resources due to at least one respective domain associated with the relationship instance based on the identified rate. For each domain of the plurality of domains, the system aggregates a total amount of resources due to the domain based on the calculated amount of resources due for each relationship instance associated with the domain.

Abstract: The disclosure relates to extraction of rationales for studied outcome. A method comprises: grouping features as expert to align with a set of operating practices; generating interpretable features using operating rules, combining with statistical dependence analysis to bin selected features to generate favorite practice actions; grouping features as expert that combine a subset of the interpretable features to align with a set of operating practices.

Abstract: Systems and methods are disclosed for determining the appropriateness of medical interventions. In one embodiment, a machine learning system for determining the appropriateness of a selected medical intervention includes health-related data sources, the health-related data sources providing at least one data file of a first type, and a second data file of a second type. A machine learning module is configured to receive the first and second data files, perform a normalization procedure on at least one of the first and second data files, and apply at least one previously trained machine learning model to the normalized data files to produce a prediction output. The prediction output may include a confidence level associated with an appropriateness of the selected medical intervention.

Abstract: Accessing measurements associated with garments and leveraging the measurements to determine fit characteristics associated with the garments is described. The fit characteristics may be leveraged to provide information about how a garment fits relative to another garment to streamline online shopping transactions. Fit characteristics may correspond to scores that are determined based at least in part on one or more measurements of a garment. Individual measurements may be standardized and/or weighted. The individual measurements may be combined to determine a score representative of a fit characteristic. Fit characteristics associated with two or more garments may be compared and a user interface may be caused to be displayed to compare garments. The user interface may summarize fit characteristic comparisons via textual descriptions, graphical representations, etc. Users may leverage fit characteristics and resulting user interfaces to comparison shop between various garments.

Abstract: A method for searching for apparel online includes storing multiple apparel cut patterns and determining a distance between points of the multiple apparel cut patterns. The method also includes retrieving a reference apparel item cut pattern from the multiple apparel cut patterns based on user input corresponding to a reference apparel item. The method further includes identifying a search apparel cut pattern from the multiple apparel cut patterns based on the determined distance and generating an overlay of a visual representation of the search apparel cut pattern and corresponding to a visual representation of the reference apparel cut pattern. The method still further includes displaying the overlay and information of a search apparel item corresponding to the search apparel cut pattern.

Abstract: A cloud service broker apparatus and method thereof are provided. The cloud service broker apparatus includes a controller configured to provide a brokerage service between a plurality of cloud service providers and a cloud service user by dividing a cloud service requested by the cloud service user into a plurality of cloud service segments and distributing each of the cloud service segments to each of the clouds.

Abstract: The present disclosure provides embodiments of a method of providing a virtual window treatment decorating interface that comprises receiving, at a processor, window data pertaining to at least one window of a premises, providing a user interface for selection of a window treatment for the at least one window, rendering one of the at least one window in the user interface, the rendering being generated based on the window data, receiving a selection of a window treatment to be applied to the rendered window, and rendering the window treatment onto the rendered window in the user interface. Preferably, the method includes setting dimensions of the rendered window and window treatment to correspond to professional measurement data of the window to provide an accurate virtual visualization of the window with the selected treatment.

Abstract: Devices and methods for detecting credit card skimmers are provided herein. A device can include a printed circuit board having a pattern of electrical traces on its surface, and a computer readable medium comprising instructions that cause a processor to direct an electrical voltage to a trace and detect an electrical current between two points of the trace. A gap can be disposed between the two points across which a voltage is applied in order to detect a magnetic reader. A count of the detected magnetic readers within a credit card reading device may be indicative of the presence of a credit card skimmer.

Abstract: Systems and methods for analyzing image data depicting properties are disclosed. According to certain aspects, an electronic device may analyze image data depicting a property to identify a set of attributes of the property. The electronic device may identify, based on the set of attributes, an architectural style of the property. Further, the electronic device may identify at least one additional property having the same architectural style. Data indicative of the at least one additional property may be presented to a user for viewing and assessment.

Abstract: Text input data may be aggregated and mapped to create composite text input data for electronic records. A semantic event may be automatically detected, triggered by a semantic rule and associated semantic tag. The detected semantic event may be flagged, and a text mining result database may be updated by adding an entry to the database. An indication associated with the event may be transmitted, and a back-end application computer server may establish a hierarchy for multiple elements of the electronic records. The computer server may determine a weight variable and response variable for each element in the hierarchy and apply a hierarchical credibility weighting methodology to the elements from level 1, representing the least granular level in the hierarchy, to level n, representing the most granular level in the hierarchy, calculated recursively from level n, to determine a final estimated credibility for the electronic records.

Abstract: A device that automates a design of an engagement ring. The handheld device comprises a display for displaying a series of questions to a customer and an input device that is capable of receiving at least one answer to the series of questions. The device also includes a microprocessor; and a memory that stores instructions, which cause the microprocessor to: input the at least one answer into an algorithm; identify on behalf of the customer a plurality of engagement rings that best matches the at least one answer; generate an information box in the display, in response to the selection of a specific engagement ring from the plurality of engagement rings; receive the customer's feedback on the specific engagement ring; and generating a recommended engagement ring to the customer.

Abstract: Embodiments of the present invention disclose a query result bottom retrieval method and apparatus. The query result bottom retrieval method includes: acquiring, from a resource library and based on a user input target query, query resources associated with the user input target query; acquiring comparative scoring characteristics of each of the query resources, the comparative scoring characteristics including base relevance characteristics; inputting the comparative scoring characteristics of each of the query resources into a pre-trained rank model, to acquire relevance scoring values corresponding to the query resources and output by the rank model, the rank model being a GBRank model; and ranking the query resources based on the relevance scoring values, and selecting, according to the ranking result, a set number of target resources as a bottom retrieval result corresponding to the target query.

Abstract: In one embodiment, a method includes a computing device receiving postings from users of an online social networking system. A postings may include location data along with one or more tags that may describe the content of the posting. The computing device may identify regions and subregions from which the postings originated, and may determine a distribution of the tags according to two data dimensions: the ubiquity of the tags across the regions, and the ubiquity of the tags across the subregions. Based on the distribution, the computing device may create a neighborhood characterization to accurately describe one or more subregions. The computing device may also determine applications for the neighborhood characterization.

Abstract: Systems and methods for analyzing image data depicting portions of properties are disclosed. According to certain aspects, an electronic device may analyze image data depicting a portion of a property to identify a set of elements and a set of characteristics associated therewith. The electronic device may access a desired set of characteristics and may calculate a monetary amount associated with modifying the set of elements to achieve the desired set of characteristics.

Abstract: User interfaces associated with devices and applications for distributing digital media content are described. A user interface may be provided that includes a favorites selection button allowing a user to identify selected media tracks and/or associated artists to be played more frequently. A ban selection button may be also provided allowing a user to selectively ban media tracks and/or associated artists. Additional controls may be provided including controls and interfaces for creating user customized stations to customize content delivery based on user specified preferences stored in a user profile.

Abstract: An online system receives tracking requests from client devices interacting with a website. The online system analyzes user interactions with websites using the tracking requests. The online system predicts an accurate label for the web page that caused the tracking request to be generated. The online system uses the accurate label for generating reports describing user interactions with the website. The online system determines a quality of tracking requests generated by the website based on various factors including a number of web pages of the website that generate tracking requests, the type of information provided by the tracking requests, and so on. The online system generates reports describing the quality of the tracking requests. The online system uses a metric indicating the quality of tracking requests of the website to determine whether to use predicted labels instead of labels provided by tracking requests for generating reports of the website.

Abstract: Improved techniques for media item sharing are described. In one embodiment, for example, an apparatus may comprise a classification module to assign a media item to a content category, a correlation module to determine context information for the media item, and an estimation module to determine a set of relevance values for a set of contacts based at least in part on a sharing history and to generate a set of suggested recipients for the media item based at least in part on the set of relevance values and the set of contacts. Other embodiments are described and claimed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer readable storage medium, for identifying entities based on value. In one aspect, the method may include actions for receiving a query that specifies a location. Additional actions may include identifying candidate entities that are identified as responsive to the query and that are associated with the location, selecting a subset of the candidate entities, and determining a representative value of an attribute that is associated with each candidate entity of the subset of the candidate entities. Other actions may include in response to determining that the current value of the attribute that is associated with the particular candidate entity of the subset deviates more than a threshold amount from the representative value, adjusting a ranking score for the particular candidate entity, and ranking the particular candidate based at least on the ranking score for the particular candidate entity.

Abstract: A computer implemented system for e-commerce includes a server hosting a system management domain, and a number of domains. A first domain provides a first website displaying a plurality of products for purchase using a first shopping cart provided by the system management domain. A second domain provides a second website displaying a plurality of products for purchase using a second shopping cart provided by the system management domain. The system management domain may display on the first website a link pointing to a product displayed by the second website when certain conditions exist. When the link is followed to the second website, the first shopping cart is used for purchases at the second website.

Abstract: In one embodiment, a Domain Name Service (DNS) server pre-fetches domain information regarding a domain that includes certificate information for the domain. The DNS server receives a DNS request that includes a security request for the domain in metadata of a Network Service Header (NSH) of the DNS request. The DNS server retrieves the certificate information for the domain from the pre-fetched information regarding the domain, in response to receiving the security request. The DNS server sends, to a Transport Layer Security (TLS) proxy, a DNS response for the domain that includes the certificate information in metadata of an NSH of the DNS response.

Abstract: A computing device can determine visual words for images in a first set of images associated with a description that includes a term. Each visual word can describe pixels in an image. The device can determine visual words for images in a second set of images that are associated with a description that does not include the term. The device can determine a set of visual words that are associated with the term. The device can determine regions in images corresponding to visual words in the set of visual words. The device can associate the respective determined regions for the images with the term in a database. When a search query is received that includes an image that is determined to be associated with the term, the database can be utilized to determine images responsive to the query by identifying images that are also associated with the term.