Abstract: Described is a technology in which image near-duplicate retrieval is performed using similarities between patterns of query image words and patterns of database image words. In general, the image retrieval problems resulting from visual polysemy are reduced by using such visual patterns. Visual word vectors and visual pattern vectors are determined for the query image and a database image. These four vectors are used to determine similarity between the database image and the query image. The similarity scores may be used for ranking and/or re-ranking the database image similarity to the query image relative to other database images' similarity scores. Also described is expanding a query visual word of the query image to a set of visual words that are visual synonyms with the query visual word, to help reduce image retrieval problems resulting from visual synonymy.

Abstract: Described is a technology in which an image retrieval system is updated incrementally as new image data becomes available. Updating is incrementally performed and only triggered when the new image data is large enough or diverse enough relative to the image data currently in use for image retrieval. Incremental updating updates the leaf nodes of a vocabulary tree based upon the new image data. Each leaf node's feature frequency is evaluated against upper and/or lower threshold values, to modify the nodes of the tree based on the feature frequency.

Abstract: Method for determining a relevance between an image and information pertaining to the image, including receiving information about a geographical region, displaying the image related to the geographical region, receiving an estimated location information of the image, and determining the relevance between the image and the information based on the estimated location information.

Abstract: A coherent phrase model for near-duplicate image retrieval enforces coherency across multiple descriptors for every local region. Two types of visual phrase (FCP and SCP) are employed to represent feature and spatial coherency and can be utilized without increasing the computational complexity. The FCP utilizes the information of different features by enforcing the feature coherency across multiple types of descriptors for every local region, and the SCP utilizes spatial information by enforcing the spatial coherency across the spatial neighborhoods of different sizes around every local region. Moreover, the disclosed model improves the matching accuracy by reducing the number of false matches and preserves the matching efficiency because of the sparsity of the representation.

Abstract: A method and system for transmitting an image progressively is provided. The transmission system identifies a first region and a second region of the image. The transmission system also identifies a first resolution and a second resolution. The transmission system then transmits the image by transmitting, in the following order, the first region in the first resolution, the second region in the first resolution, the first region in the second resolution, and the second region in the second resolution. The transmission system may identify the regions based on the likelihood of being the focus of user attention.

Abstract: A method and system for providing location-based advertisements to requesting devices is provided. An advertisement system aggregates advertisements by collecting advertisements from multiple advertisement sources, extracting data from the collected advertisements, and storing the extracted data in a common format. After aggregating the advertisements, the advertisement system transforms each advertisement into multiple advertisement formats that are specific to protocols supported by the various device types. When the advertisement system receives queries for advertisements, it identifies matching advertisements and ranks them based on a location. The advertisement system then selects an advertisement format that is appropriate for the requesting device.

Abstract: A method and system for identifying locations associated with a web resource is provided. The location system identifies three different types of geographic locations: a provider location, a content location, and a serving location. A provider location identifies the geographic location of the entity that provides the web resource. A content location identifies the geographic location that is the subject of the web resource. A serving location identifies the geographic scope that the web page reaches. An application can select to use the type of location that is of particular interest.

Abstract: Described is using density to efficiently mine co-location patterns, such as closely located businesses frequently found together in business listing databases, geographic search logs, and/or GPS-based data. A data space of such information is geographically partitioned into a grid of cells, with dense cells scanned first. A dynamic upper bound of prevalence measure of co-location patterns is maintained during the scanning process. If the current upper bound is smaller than a threshold, the scanning is stopped, thereby significantly reducing the computation cost for processing many cells, while providing suitable results.

Abstract: A method and system for transmitting an image progressively is provided. The transmission system identifies a first region and a second region of the image. The transmission system also identifies a first resolution and a second resolution. The transmission system then transmits the image by transmitting, in the following order, the first region in the first resolution, the second region in the first resolution, the first region in the second resolution, and the second region in the second resolution. The transmission system may identify the regions based on the likelihood of being the focus of user attention.

Abstract: Described is a technology by which co-located query patterns are mined from a data space such as a geographic search log. An overall data space (basic) approach and/or a lattice-based approach may be used when mining. The data space contains objects, each comprising associated type and location information. The location information is used to determine the distance between different two or more types of objects, e.g., pairs. The frequency of occurrence of those pairs within the data space determines whether that pairing of object types indicates a co-located pattern. Also described is partitioning the data space into regions, including for the purpose of categorizing a co-located pattern as a local pattern or a global pattern based on how that co-located pattern is distributed among the regions.

Abstract: Methods and systems for determining the serving area of a web resource by address, by query content, and by business category are provided. A location system may determine the serving area of a web resource based on addresses of users who access the web resource. The location system may determine the serving area for a web site (or other web resource) based on query terms that resulted in a click-through to the web site. The location system may determine the serving area of a web site (or other web resource) based on the business category of the web site and a “provider location” associated with the web site.

Abstract: Categorizing page block functionality to improve document layout for browsing is described. In one aspect, document content is analyzed with respect to multiple block function criteria. Results of this analysis are used to assign a respective block function to blocks of the document content. These block function assignments are used to generate one or more customized document layouts for browsing by a user.

Abstract: A system for logging life experiences using geographic cues. The system variously provides a comprehensive life-logging tool for recording each life event; a vacation album for revisiting and reliving vacation routes and associated photos; an information service for finding popular routes and locations; a statistical tool for analyzing metrics of a person's life; and a personal website service for sharing personal information. In one implementation, the system receives a user's GPS log files and multimedia content at a website. The system segments the GPS log files into geographic routes corresponding to user trips, and tags the multimedia content with geographic cues from the GPS log files. Then, the system indexes the geographic routes so that users can retrieve the geographic routes by browsing or by search techniques. The system displays animations of selected routes on a map, and displays the multimedia content at corresponding locations along the map route, as the route is replayed.

Abstract: Described is a technology by which raw GPS data is processed into segments of a trip, with a predicted mode of transportation (e.g., walking, car, bus, bicycling) determined for each segment. The determined transportation modes may be used to tag the GPS data with transportation mode information, and/or dynamically used. Segments are first characterized as walk segments or non-walk segments based on velocity and/or acceleration. Features corresponding to each of those walk segments or non-walk segments are extracted, and analyzed with an inference model to determine probabilities for the possible modes of transportation for each segment. Post-processing may be used to modify the probabilities based on transitioning considerations with respect to the transportation mode of an adjacent segment. The most probable transportation mode for each segment is selected.

Abstract: Described is a technology by which uploaded GPS data is indexed according to spatio-temporal relationships to facilitate efficient insertion and retrieval. The indexes may be converted to significantly smaller-sized data structures when new updates to that structure are not likely. GPS data is processed into a track of spatially-partitioned segments such that each segment has a cell. Each cell has an associated temporal index (a compressed start-end tree), into which data for that cell's segments are inserted. The temporal index may include an end time index that relates each segment's end time to a matching start time index. Given query input comprising a spatial predicate and a temporal predicate, tracks may be searched for by determining which spatial candidate cells may contain matching results. For each candidate cell, the search accesses the cell's associated temporal index to find any track or tracks that correspond to the temporal predicate.

Abstract: A method and system for identifying locations associated with a web resource is provided. The location system identifies three different types of geographic locations: a provider location, a content location, and a serving location. A provider location identifies the geographic location of the entity that provides the web resource. A content location identifies the geographic location that is the subject of the web resource. A serving location identifies the geographic scope that the web page reaches. An application can select to use the type of location that is of particular interest.

Abstract: A system for learning an attention model for an image based on user navigation actions while viewing the image is provided. An attention model learning system generates an initial attention model based on static features derived from the image. The learning system logs the actions of users as they view the image. The learning system identifies from the actions of the users those areas of the image that may be of user interest: After the learning system identifies areas that may be of user interest, the learning system attempts to identify attention objects based on those identified areas. After identifying the user attention objects, the learning system updates the attention model for the image to reflect the additional information provided by the user attention objects.

Abstract: Systems and methods to present web image search results for effective image browsing are described. In one aspect, task-based attention objects for each of multiple images associated with image search results are generated. Thumbnail images from respective ones of the images are created as a function of at least the task-based attention objects. The thumbnail images emphasize image region(s) of greater priority to a user in view of a keyword or expanded keyword associated with the search results.

Abstract: A method and system for generating a search request from a multimodal query that includes a query image and query text is provided. The multimodal query system identifies images of a collection that are textually related to the query image based on similarity between words associated with each image and the query text. The multimodal query system then selects those images of the identified images that are visually related to the query image. The multimodal query system may formulate a search request based on keywords of web pages that contain the selected images and submit that search request to a search engine service.

Abstract: A method and system for generating a hybrid index for indexing objects based on location and keyword attributes and performing location-based searching is provided. A search system performs a location-based search using a hybrid index that indexes both location and keyword attributes of objects. The search system generates the hybrid index either using the location attribute as the primary index or the keyword attribute as the primary index. When the location attribute is the primary index, the keyword attribute is the secondary index, and vice versa. To generate the hybrid index, the search system identifies the values for the keyword and location attributes of each object. The search system generates the primary index to map each value of a first attribute to a secondary index. The search system thus generates, for each value of the first attribute, a secondary index to map values of a second attribute to objects that have the associated values of the first and second attributes.