Abstract: Techniques for analyzing effectiveness of an urban area based on traffic patterns collected from route-oriented vehicles. A process collects sequences of global positioning system (GPS) points in logs and identifies geographical locations to represent the urban area where the route-oriented vehicles traveled. The process models traffic patterns by: partitioning the urban area into regions based at least in part on major roads, segmenting the GPS points from the logs into time slots, and identifying the GPS points associated with transporting a passenger in the route-oriented vehicles. The process models traffic patterns by projecting the identified GPS points onto the regions to construct transitions of the identified GPS points travelling between the regions. Then the process builds a matrix of the regions for each time slot in each day based on a number of the transitions. Each item in the matrix represents an effectiveness of a connection between two regions.

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. Upon completion of the incremental updating, a server that performed the incremental updating is switched to an active state with respect to handling client queries for image retrieval, and another server that was actively handling client queries is switched to an inactive state, awaiting a subsequent incremental updating before switching back to active state.

Abstract: Functionality is described for generating a vocabulary from a source dataset of image items or other non-textual items. The vocabulary serves as a tool for retrieving items from a target dataset in response to queries. The vocabulary has at least one characteristic that allows it to be used to retrieve items from multiple different target datasets. A target dataset can have a different size than the source dataset and/or a different type than the source dataset. The enabling characteristic may correspond to a size of the source dataset above a prescribed minimum number of items and/or a size of the vocabulary above a prescribed minimum number of words.

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: Trajectory data representing tracked positions of a vehicle along a trajectory having a start and end point is accessed. The trajectory data may include spatio-temporal information about the vehicle at different points along the trajectory. The trajectory may be divided into segments based, at least in part, on knowledge of inferred-parking locations. The segments may be map-matched to corresponding road segments. Additionally, historical data representing spatio-temporal travel patterns of vehicles learned from historical trajectories of vehicles corresponding to the map-matched-road segments may also be accessed. A behavioral state of the vehicle for a segment or position within a segment may be inferred, based at least in part, on (i) the vehicle's spatio-temporal information corresponding to the segment or position within a segment, (ii) knowledge of the map-matched-road segment, and (iii) the historical data.

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: 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: Techniques for determining a status of a user are described. A mobile device equipped with sensors may collect sensor data pertaining to transportation modes of the user, tracking locations of the user, identifying environmental noise levels surrounding the user, or speech being spoken in proximity to the user. Features of the collected sensor readings are then used to infer activities the user may be performing. Based at least in part on the multiple inferred activities, a status of the user is determined.

Abstract: Techniques for providing mining life pattern are described. This disclosure describes mining a life pattern of an individual, for example, by identifying places visited during the individual's daily activities. Mining the individual life pattern includes collecting location data for the individual and predicting behaviors and preferences of the individual based at least in part on a location history. The location history of the individual is represented with a sequence of geographical regions that have been visited by the individual with corresponding arrival and departure times for each region. Once the life pattern is predicted from the location history, information is recommended to the individual based at least in part on the life pattern.

Abstract: One or more techniques and/or systems are disclosed for prioritizing one or more travel itineraries based on an itinerary query. Respective candidate itineraries from a set of candidate itineraries are ranked based on one or more ranking factors for the candidate itineraries, where the candidate itineraries were identified from a location-interest graph using the query. A desired number of the ranked candidate itineraries are re-ranked based on a one or more historical travel sequences, such that one or more prioritized travel itineraries can be identified in response to the itinerary query.

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: Described is a technology by which a user hums, sings or otherwise plays a user-provided rendition of a ringtone (or ringback tone) through a mobile telephone to a ringtone search service (e.g., a WAP, interactive voice response or SMS-based search platform). The service matches features of the user's rendition against features of actual ringtones to determine one or more matching candidate ringtones for downloading. Features may include pitch contours (up or down), pitch intervals and durations of notes. Matching candidates may be ranked based on the determined similarity, possibly in conjunction with weighting criterion such as the popularity of the ringtone and/or the importance of the matched part. The candidate set may be augmented with other ringtones independent of the matching, such as the most popular ones downloaded by other users, ringtones from similar artists, and so forth.

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: 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: Techniques for providing a trajectory route to multiple geographical locations of interest are described. This disclosure describes receiving global position system (GPS) logs associated with respective individual devices, each of the GPS logs including trajectories connecting a set of geographical locations previously visited by an individual of a respective individual device. A trajectory route service receives a request for a trajectory connecting a set of geographical locations of interest specified by a user. The trajectory route service calculates a proximal similarity between (1) the set of geographical locations of interest specified by the user, and (2) respective sets of geographical locations from the GPS logs. The trajectory route service constructs the requested trajectory with use of at least one of the trajectories from the GPS logs determined at least in part according to the calculated proximal similarities.

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: 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 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: Method for making a recommendation to a first user in a computing network, including calculating one or more similarity scores between the first user and one or more remaining users in the network, identifying a portion of the remaining users having a highest similarity scores, identifying one or more locations visited by the portion of the remaining users but not by the first user, determining an interest level of the first user in each location, ranking the locations based on the interest levels, and displaying the locations based on the ranking as a first recommendation.

Abstract: Techniques describe constructing a location and activity recommendation model to identify relationships between locations and activities. To construct the model, the process obtains global positioning system (GPS) logs of geographical locations collected over time and identifies stay points representing locations visited by an individual user. The process also identifies points of interest in a region using a database and correlates a relationship between activity to activity by submitting queries to a search engine. The information gathered is used to fill locations and activities in a location-activity matrix. Recommendations may be made for a location and/or activity when given a user query, based on a user's present geographical location, or a prediction of a user's interest.