Abstract: Systems and methods for a dynamic visual search engine are provided. In one example method, a criteria used to partition a set of compressed image descriptors into multiple database shards may be determined. Additionally, a size of a dynamic index may be determined. The dynamic index may represent a dynamic number of images and may be configured to accept insertion of reference images into the dynamic index that can be search against immediately. According to the method, an instruction to merge the uncompressed image descriptors of the dynamic index into the database shards of the compressed image descriptors may be received, and the uncompressed image descriptors of the dynamic index may be responsively merged into the database shards of the compressed image descriptors based on the criteria.

Abstract: Methods and systems for selecting a representative image of an entity are disclosed. According to one embodiment, a computer-implemented method for selecting a representative image of an entity is disclosed. The method includes: accessing a collection of images of the entity; clustering, based on similarity of one or more similarity features, images from the collection to form a plurality of similarity clusters; and selecting the representative image from one of said similarity clusters. Further, based on cluster size of said similarity clusters popular clusters can be determined, and the selection of the representative image can be from the popular clusters. In addition, the method can further include assigning a headshot score based upon a portion of the respective image covered by the entity to respective images in said popular clusters, and further selecting the representative image based upon the headshot score.

Abstract: Systems and methods for a dynamic visual search engine are provided. In one example method, a criteria used to partition a set of compressed image descriptors into multiple database shards may be determined. Additionally, a size of a dynamic index may be determined. The dynamic index may represent a dynamic number of images and may be configured to accept insertion of reference images into the dynamic index that can be search against immediately. According to the method, an instruction to merge the uncompressed image descriptors of the dynamic index into the database shards of the compressed image descriptors may be received, and the uncompressed image descriptors of the dynamic index may be responsively merged into the database shards of the compressed image descriptors based on the criteria.

Abstract: Methods and systems for selecting a representative image of an entity are disclosed. According to one embodiment, a computer-implemented method for selecting a representative image of an entity is disclosed. The method includes: accessing a collection of images of the entity; clustering, based on similarity of one or more similarity features, images from the collection to form a plurality of similarity clusters; and selecting the representative image from one of said similarity clusters. Further, based on cluster size of said similarity clusters popular clusters can be determined, and the selection of the representative image can be from the popular clusters. In addition, the method can further include assigning a headshot score based upon a portion of the respective image covered by the entity to respective images in said popular clusters, and further selecting the representative image based upon the headshot score.

Abstract: Systems and methods for a dynamic visual search engine are provided. In one example method, a criteria used to partition a set of compressed image descriptors into multiple database shards may be determined. Additionally, a size of a dynamic index may be determined. The dynamic index may represent a dynamic number of images and may be configured to accept insertion of reference images into the dynamic index that can be search against immediately. According to the method, an instruction to merge the uncompressed image descriptors of the dynamic index into the database shards of the compressed image descriptors may be received, and the uncompressed image descriptors of the dynamic index may be responsively merged into the database shards of the compressed image descriptors based on the criteria.

Abstract: Methods and systems for selecting a representative image of an entity are disclosed. The representative image can be, but is not limited to, that of a person, a corporate logo, other symbol associated with a person or corporation. According to one embodiment, a computer-implemented method for selecting a representative image of an entity is disclosed. The method includes: accessing a collection of images of the entity; clustering, based on similarity of one or more similarity features, images from the collection to form a plurality of similarity clusters; and selecting the representative image from one of said similarity clusters. Further, based on cluster size of said similarity clusters popular clusters can be determined, and the selection of the representative image can be from the popular clusters.

Abstract: A method and apparatus for enabling virtual tags is described. The method may include receiving a first digital image data and virtual tag data to be associated with a real-world object in the first digital image data, wherein the first digital image data is captured by a first mobile device, and the virtual tag data includes metadata received from a user of the first mobile device. The method may also include generating a first digital signature from the first digital image data that describes the real-world object, and in response to the generation, inserting in substantially real-time the first digital signature into a searchable index of digital images. The method may also include storing, in a tag database, the virtual tag data and an association between the virtual tag data and the first digital signature inserted into the index of digital images.

Abstract: Methods and systems for automated identification of celebrity face images are provided that generate a name list of prominent celebrities, obtain a set of images and corresponding feature vectors for each name, detect faces within the set of images, and remove non-face images. An analysis of the images is performed using an intra-model analysis, an inter-model analysis, and a spectral analysis to return highly accurate biometric models for each of the individuals present in the name list. Recognition is then performed based on precision and recall to identify the face images as belonging to a celebrity or indicate that the face is unknown.

Abstract: A method and apparatus for enabling virtual tags is described. The method may include receiving a first digital image data and virtual tag data to be associated with a real-world object in the first digital image data, wherein the first digital image data is captured by a first mobile device, and the virtual tag data includes metadata received from a user of the first mobile device. The method may also include generating a first digital signature from the first digital image data that describes the real-world object, and in response to the generation, inserting in substantially real-time the first digital signature into a searchable index of digital images. The method may also include storing, in a tag database, the virtual tag data and an association between the virtual tag data and the first digital signature inserted into the index of digital images.

Abstract: A method and apparatus for enabling virtual tags is described. The method may include receiving a first digital image data and virtual tag data to be associated with a real-world object in the first digital image data, wherein the first digital image data is captured by a first mobile device, and the virtual tag data includes metadata received from a user of the first mobile device. The method may also include generating a first digital signature from the first digital image data that describes the real-world object, and in response to the generation, inserting in substantially real-time the first digital signature into a searchable index of digital images. The method may also include storing, in a tag database, the virtual tag data and an association between the virtual tag data and the first digital signature inserted into the index of digital images.

Abstract: A method and apparatus for enabling virtual tags is described. The method may include receiving a first digital image data and virtual tag data to be associated with a real-world object in the first digital image data, wherein the first digital image data is captured by a first mobile device, and the virtual tag data includes metadata received from a user of the first mobile device. The method may also include generating a first digital signature from the first digital image data that describes the real-world object, and in response to the generation, inserting in substantially real-time the first digital signature into a searchable index of digital images. The method may also include storing, in a tag database, the virtual tag data and an association between the virtual tag data and the first digital signature inserted into the index of digital images.

Abstract: Methods, systems and apparatus, including computer program products, for generating a sitemap where a last modified time of website content is not available to a network crawler. A sitemap generator determines that a file has a previously stored version number, compares a current version number of the file to the previously stored version number of the file, generates a sitemap having an entry corresponding to the file if the current version number of the file is changed from the previously stored version number, and assigns a new last modified time to a last modified time value for the entry wherein an actual last modified time of the file is not available. A search engine receives the sitemap, determines that the entry was previously indexed at a time before the last modified time value, and accesses file information associated with the file to update an index with the file information.

Abstract: Methods, systems and apparatus, including computer program products, for generating a sitemap where a last modified time of website content is not available to a network crawler. A sitemap generator determines that a file has a previously stored version number, compares a current version number of the file to the previously stored version number of the file, generates a sitemap having an entry corresponding to the file if the current version number of the file is changed from the previously stored version number, and assigns a new last modified time to a last modified time value for the entry wherein an actual last modified time of the file is not available. A search engine receives the sitemap, determines that the entry was previously indexed at a time before the last modified time value, and accesses file information associated with the file to update an index with the file information.

Abstract: Methods and systems for automated identification of celebrity face images are provided that generate a name list of prominent celebrities, obtain a set of images and corresponding feature vectors for each name, detect faces within the set of images, and remove non-face images. An analysis of the images is performed using an intra-model analysis, an inter-model analysis, and a spectral analysis to return highly accurate biometric models for each of the individuals present in the name list. Recognition is then performed based on precision and recall to identify the face images as belonging to a celebrity or indicate that the face is unknown.

Abstract: Methods, systems and apparatus, including computer program products, for generating a sitemap where a last modified time of website content is not available to a network crawler. A current version number of a content item is compared to the version number of that content at the time sitemap for the website was generated. If the version number has changed the last modified time in a generated sitemap is set to the current time to cause the item to be revisited by a search engine.

Abstract: Methods and apparatus for reducing resource contention in parallel data backup processes that share a variety of resources in a computer environment to access target data to be backed-up. The target data is distributed among the backup processes based on an availability of one or more resources in the computer environment used by a backup storage system to access the target data. In one example, each data file of the target data is assigned to a particular backup process based on the availability of one or more resources and a total size of the target data. The data files of the target data are assigned to the backup processes such that each backup process backs-up a respective portion of the target data, and such that the collection of backup processes that make up a backup operation are completed in a shortened time as a result of reduced resource contention.