Abstract: Overall latency is reduced when processing tasks such as search queries by determining which tasks are “expensive,” or likely to exceed desired latency thresholds. For expensive queries processed according to partitions, the segments for each partition can be divided among various sub-queries, which allow each partition to be processed in parallel by multiple devices without the need for repartitioning. Further, the responses to the sub-queries can be monitored, and if one or more responses are not received within a specified amount of time then each sub-query for which a response is missing can be resent. The first response received will be consolidated with the results from the other queries, and the result returned.

Abstract: Common search queries can be provided that are associated with a predicted path of movement of a mobile device. A location of a mobile device can be determined, along with a destination or direction of movement. Common search queries associated with the path of movement and locations along the path can be transmitted to the mobile device. A user of the mobile device is able to execute the common search queries from the mobile device.

Abstract: Systems and methods are provided for creating contour images that represent the contour of objects reflected in images, calculating contour histogram descriptors of the contour images, and classifying images based in part on the histogram descriptors of the contour images. For example, a contour image of an image is created. A radial-polar grid having a plurality of radial-polar bins is then positioned on the contour image. A contour histogram descriptor is created to include a number of bins that correspond to the radial-polar bins of the radial-polar grid, where the contents of the bins of the contour histogram descriptor represent the number of pixels of the contour image that are located in the corresponding radial-polar bins of the radial-polar grid. Images are classified at least based in part on comparisons between contour histogram descriptors of the images and contour histogram descriptors of training images.

Abstract: Various algorithms are presented that enable an image of a barcode, captured by a camera of an electronic device, to be decoded on the device without need to upload the image information to a server for processing. The algorithms can account for variations in focus of the image, as may result in blur due to move movement or auto-focus features. The approaches can handle multiple barcode formats, and can handle barcodes on curved surfaces, barcodes with damaged areas, or barcodes that are otherwise uneven. Such algorithms are highly accurate while being fast and lightweight enough to execute on portable electronic devices, such as tablet computers and smart phones.

Abstract: Systems and methods of classifying sessions are disclosed. A particular method monitors user activity at one or more servers accessible via a network and capturing event entries in an activity log for user activity that is detected. The event entries include descriptive information regarding a user action, a client identifier and a session identifier. The method also includes attempting to classify sessions associated with a plurality of event entries of the activity log as legitimate use or illegitimate use of resources of the one or more servers. The method further includes identifying unclassified sessions. The method also includes determining a count of a number of unclassified sessions associated with a particular client identifier and determining a total number of sessions associated with the particular client identifier. The method further includes classifying the unclassified sessions as legitimate use or illegitimate use of the resources of the one or more servers.

Abstract: The present invention relates to a method, system, and a computer program product for delivering content to a communication device, in response to an image sent by the communication device. The received image is matched with a plurality of images, and, when a match is found for the received image, content corresponding to the image is delivered to the communication device. The plurality of images is stored in an image database, and the corresponding content is stored in a content repository. The present invention enables a content provider to automatically update the image database and the content repository without any human intervention.

Abstract: A method, system and computer program product for representing an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.

Abstract: A first portion of content relating to a first markup document may be displayed to a user of the client system. Information relating to the first portion of content is stored at a server system. An action to display a current version of the first markup document on the client system is received. A current version of content for the first markup document is retrieved from the host server. The stored information relating to the first portion of content may be used to identify a third portion of content associated with the first markup document which has not previously been displayed to the user. The display of markup document content associated with the first markup document may then be modified in a manner which facilitates the user in identifying the third portion of content.

Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.

Abstract: A method, system and computer program product for virtually placing an object on an image of a human appendage is provided. First, image boundaries are detected in the image of the appendage and converted into a set of line segments. A pair of line segments is evaluated according to a function that combines subscores of the pair of line segments to produce a score. The subscores of the line segments are computed based on various properties such as orientation difference, extent, proximity to the center of the image, bilateral symmetry, and the number of skin-colored pixels. A pair of line segments with the highest score is chosen as the appendage boundaries and is used to determine the position, orientation, and extent of the object. The image of the object is then transformed according to the determined parameters and combined with the image of the appendage to produce the desired result.

Abstract: Systems and methods described and suggested herein utilize various techniques to assess the degree of specificity of search queries. By assessing the degree of specificity of search queries, the systems and methods may be used to determine where the submitting users' intentions fall along the continuum between specific and general searching. Thus, the systems and methods may be used to, among other uses, deliver search results that more closely coincide with the users' intentions. For example, if data associated with a search query indicates that users typically submit the search query with the intention of specific searching, embodiments may tailor search results to include a limited number of highly relevant search-result items. On the other hand, for example, if data associated with a search query indicates that users typically submit the search query with the intention of general searching, embodiments may tailor search results to include a diverse set of search-result items from multiple categories.

Abstract: Multiple paths of an index tree may be traversed to discover a set of content descriptors that are match candidates for a set of query descriptors. A size of the set of candidate content descriptors may be optimized, for example, to reduce false positive matching errors, query latencies and/or index tree traversal times, at least in part by determining a number of child nodes to traverse based at least in part on current traverse level and/or traverse neighborhood thresholds. Index trees for large content descriptor sets may be built in resource constrained environments with approximation and/or refining build techniques.

Abstract: Systems and methods use behavioral data to assess listings for items. The behavior data may relate to information regarding user actions in connection with listings for the items. The listings may be collections of information about the items. Behavioral data in connection with a collection of listings is used to assess how changing listings affects one or more performance measures and/or to score listing quality. The assessment may be used for various purposes, such as identifying listings that may be changed to achieve one or more improved performance measures for corresponding items and for other applications.

Abstract: A search facility may optimize search result ranking by applying inverted decay transformations to history-dependent ranking components. Ranking scores for content in a content collection may be based on a set of ranking components including history-dependent ranking components. History-dependent ranking components may be based on historical behavioral data such as historical searches, actions taken with respect to content such as viewing content and content-related purchases. Content recently added to the content collection may be disadvantaged relative to content with an established history. Inverted decay transformations may correspond to simulations of additional historical behavioral data.

Abstract: Methods and apparatus for rendering search results are described. In one aspect of the invention, a search request is received from a computerized client. A search is performed based on the search request in at least two different categories of information to obtain search results in the searched categories. Selected search results are returned to the client to facilitate rendering the search results at the client. Search results from different search categories are returned in a manner configured to be presented in different panes of a graphical user interface rendered on the client. In another aspect, what searches to perform can be determined based at least in part upon search results display settings associated with the client, such that searches are performed only in categories of information that are associated with a pane that is in an open state on the client.

Abstract: A method for displaying a search history for a user is shown. The method includes generating a search history for a user including one or more listings of search results, displaying a first search result listing on a web page, and displaying at least a second search result listing on the web page, the second search result listing having a relationship to the first search result listing within the search history.

Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.

Abstract: False positive match rates between query content and content in a collection may be reduced with a minimum content region test and/or a minimum features per scale test. The quality of correlations between query descriptors and content descriptors may be improved with a modified sub-region descriptor construction. Content regions associated with detected content features may be partitioned into disjoint sets of sub-regions that cover the content regions, the sub-regions modified so as to at least partially overlap, and descriptor components generated for the modified sub-regions. Matching of feature-sparse content may be improved by adding blurred versions to the collection.

Abstract: The present invention is directed to a method and system for providing information obtained from both online stores and offline stores and for offering more purchasing options to customers. A customer can specify a particular item with detailed aspects for an information search, along with location information to define a local geographic area. The gathered local price information is presented to the customer over a network connection. The customer can purchase the item from either online stores or offline stores over a network connection.

Abstract: Techniques for augmenting an image of an object captured and displayed in real time with associated content are disclosed. In one embodiment, the method for augmenting the image includes receiving information defining a sampled frame of a video being captured by an electronic device in substantially real time, determining information representative of an object captured in the sampled frame based on the received information, causing the determined information to match stored information defining a plurality of items to locate an item matched to the captured object, retrieving content associated with the matched item, and providing the retrieved content for display with the captured image on the electronic device. The retrieved content may be rendered in an overlay element that overlays the captured image displayed on the electronic device. The rendered content is configured to enable a user to interact with the content.