Abstract: Automated language translation often involves language translation resources of significant size (e.g., 50-gigabyte phrase tables) and significant computational power exceeding the capabilities of many mobile devices. Remotely accessible servers capable of near-realtime, automated translation may be inaccessible or prohibitively costly while traveling abroad. Presented herein are adaptations of language translation techniques for offline mobile devices involving reducing the size and raising the efficiency of the language modeling resources. A word index may be provided that stores respective string representations of the words of a language, and maps respective words to a location (e.g., address or offset) of respective word representations within the word index. Language translation resources (e.g., phrase tables) may then specify logical relationships using the word index addresses of the involved words, rather than the string equivalents.

Abstract: A system and related methods for a resource management in a head-mounted display device are provided. In one example, the head-mounted display device includes a plurality of sensors and a display system for presenting holographic objects. A resource management program is configured to operate a selected sensor in a default power mode to achieve a selected fidelity. The program receives user-related information from one or more of the sensors, and determines whether target information is detected. Where target information is detected, the program adjusts the selected sensor to operate in a reduced power mode that uses less power than the default power mode.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selectively providing images. In one aspect, a method includes receiving image data that specify feature values for a plurality of images. The image data include, for each image, location data that specify a geographic location for the image. A group of images in which each image has location data specifying a geographic location that is within a threshold distance of a reference location are selected. Pairs of matching images are selected from the group of images. A reference image for the geographic location is selected from the pairs of matching images. Data that cause presentation in a map space of a photo collection image that includes a visual representation of the reference image are provided. The photo collection image is presented in the map space and at a map position for the geographic location.

Abstract: Architecture that enables optical character recognition (OCR) of text in video frames at the rate at which the frames are received. Additionally, conflation is performed on multiple text recognition results in the frame sequence. The architecture comprises an OCR text recognition engine and a tracker system; the tracker system establishes a common coordinate system in which OCR results from different frames may be compared and/or combined. From a set of sequential video frames, a keyframe is chosen from which the reference coordinate system is established. An estimated transformation from keyframe coordinates to subsequent video frames is computed using the tracker system. When text recognition is completed for any subsequent frame, the result coordinates can be related to the keyframe using the inverse transformation from the processed frame to the reference keyframe. The results can be rendered for viewing as the results are obtained.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selectively providing images. In one aspect, a method includes receiving image data that specify feature values for a plurality of images. The image data include, for each image, location data that specify a geographic location for the image. A group of images in which each image has location data specifying a geographic location that is within a threshold distance of a reference location are selected. Pairs of matching images are selected from the group of images. A reference image for the geographic location is selected from the pairs of matching images. Data that cause presentation in a map space of a photo collection image that includes a visual representation of the reference image are provided. The photo collection image is presented in the map space and at a map position for the geographic location.

Abstract: A request may be received that includes an indicator associated with a geographic location and scope. A database search may be initiated, based on the geographic location and scope. A list of one or more tags may be received, the tags associated with the geographic location, ordered based on relevance within the geographic scope, based on tag locale rankings associated with each of the tags included in the list of tags, the tag locale rankings based on comparisons of relative frequencies of occurrence of the tags, based on first bounded geographic areas, compared with second relative frequencies of occurrence of the tags based on second bounded geographic areas that are respectively larger than the first bounded geographic areas, the request geographic scope indicating one of a plurality of hierarchical geographic analysis levels associated with a plurality of geographic locations.

Abstract: A request may be received that includes an indicator associated with a geographic location and scope. A database search may be initiated, based on the geographic location and scope. A list of one or more tags may be received, the tags associated with the geographic location, ordered based on relevance within the geographic scope, based on tag locale rankings associated with each of the tags included in the list of tags, the tag locale rankings based on comparisons of relative frequencies of occurrence of the tags, based on first bounded geographic areas, compared with second relative frequencies of occurrence of the tags based on second bounded geographic areas that are respectively larger than the first bounded geographic areas, the request geographic scope indicating one of a plurality of hierarchical geographic analysis levels associated with a plurality of geographic locations.

Abstract: A method of identifying a user-specified object contained in one or more images of a plurality of images that comprises the steps of defining regions of objects in the images, and computing a vector in respect of each of the regions based on the appearance of the respective region. The vector comprises a descriptor. The method further comprises vector quantizing the descriptors into clusters, storing the clusters as an index with the images in which they occur, defining regions of the user-specified object, computing a vector in respect of each of said regions based on the appearance of the regions, and vector quantizing the descriptors into one or more clusters. The index is searched and the clusters are compared with the contents of the index to identify which of the images contain the clusters so as to return the images containing the user-defined object.