Abstract: Retrieval of images of objects from a large-scale database of object images, based on a query image. The database may, for example, contain images of objects such as faces, vehicles, people and luggage. Semantic attributes such as doors or windows in the case of vehicles are used as high level semantic cues to determine identities of objects in the images. Salient visual characteristics of the images are labeled with attribute information, and a transformation is learned so as to transform the labeled visual characteristics into a discrimination vector that discriminates between the labels. A similarity metric is learned using the discrimination vectors, such that different images depicting the same object are determined to be close while those having different objects are determined to be far apart. Candidates are retrieved based on a query image, and a re-ranking step may be applied to improve results. Validation experiments are described.

Abstract: Systems and methods for learning a high-level visual vocabulary generate inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, map the visual words to a vector space based on the inter-visual word relationships, and generate high-level visual words in the vector space.

Abstract: Systems and methods for generating visual words define initial inter-visual word relationships between a plurality of visual words; define visual word-image relationships between the plurality of visual words and a plurality of images; define inter-image relationships between the plurality of images; generate revised inter-visual word relationships in a vector space based on the initial inter-visual word relationships, the inter-image relationships, and the visual word-image relationships; and generate higher-level visual words in the vector space based on the revised inter-visual word relationships.

Abstract: Retrieval of images of objects from a large-scale database of object images, based on a query image. The database may, for example, contain images of objects such as faces, vehicles, people and luggage. Semantic attributes such as doors or windows in the case of vehicles are used as high level semantic cues to determine identities of objects in the images. Salient visual characteristics of the images are labeled with attribute information, and a transformation is learned so as to transform the labeled visual characteristics into a discrimination vector that discriminates between the labels. A similarity metric is learned using the discrimination vectors, such that different images depicting the same object are determined to be close while those having different objects are determined to be far apart. Candidates are retrieved based on a query image, and a re-ranking step may be applied to improve results. Validation experiments are described.

Abstract: A method for establishing communication between a plurality of devices, including obtaining communication protocols that the plurality of devices support, determining which of the communication protocols are common to each the plurality of devices, determining operational parameters that are associated with each of the common communication protocols, indicating which of the common communication protocols and associated operational parameters can be used to establish communication between the plurality of devices, determining whether the plurality of devices can communicate with each other using the common communication protocols, and establishing communication between the plurality of devices using at least one of the common communication protocols.

Abstract: Systems, devices, and methods for creating a visual vocabulary extract a plurality of descriptors from one or more labeled images; cluster the descriptors into augmented-space clusters in an augmented space, wherein the augmented space includes visual similarities and label similarities; generate a descriptor-space cluster in a descriptor space based on the augmented-space clusters, wherein one or more augmented-space clusters are associated with the descriptor-space cluster; and generate augmented-space classifiers for the augmented-space clusters that are associated with the descriptor-space cluster based on the augmented-space clusters.

Abstract: Systems and methods for learning a high-level visual vocabulary generate inter-visual-word relationships between a plurality of visual words based on visual word-label relationships, map the visual words to a vector space based on the inter-visual word relationships, and generate high-level visual words in the vector space.

Abstract: Systems and methods for generating visual words define initial inter-visual word relationships between a plurality of visual words; define visual word-image relationships between the plurality of visual words and a plurality of images; define inter-image relationships between the plurality of images; generate revised inter-visual word relationships in a vector space based on the initial inter-visual word relationships, the inter-image relationships, and the visual word-image relationships; and generate higher-level visual words in the vector space based on the revised inter-visual word relationships.

Abstract: Indexing a data set of objects, where the data set is partitioned into plural work units with plural objects and distributed to multiple data process nodes. Each data processing node maps the plural objects in corresponding work units into respective ones of given sub-indexes. A composite index is constructed for the objects in the data set by reducing the mapped objects, where reducing the mapped objects is distributed among multiple data processing nodes.

Abstract: The authentication of a device with a server over a network includes authenticating, by the device, the server so as to establish a secure connection with the server. The device communicates identification information of the device to the server, wherein the identification information uniquely identifies the device to the server. The server determines the credibility of the device using the identification information communicated by the device. In a case where the server determines that the device is credible, the server creates a first authentication token for the device, stores the first authentication token, and transfers the first authentication token to the device using the secure connection, and the device stores the first authentication token. The server authenticates the device using the first authentication token.

Abstract: A method for establishing communication between a plurality of devices, including obtaining communication protocols that the plurality of devices support, determining which of the communication protocols are common to each the plurality of devices, determining operational parameters that are associated with each of the common communication protocols, indicating which of the common communication protocols and associated operational parameters can be used to establish communication between the plurality of devices, determining whether the plurality of devices can communicate with each other using the common communication protocols, and establishing communication between the plurality of devices using at least one of the common communication protocols.

Abstract: Virtually extending the functionality of a network device to a server is provided. A virtual device which is in communication with the network device and which virtually represents functionality of the network device receives a function request from the server. The function request corresponds to a function for the network device to perform. A manner to perform the function for the network device based on the function request is determined. The function corresponding to the function request is performed based on the determined manner.

Abstract: A method and system for registering a card that is used to enable configurations of an application and/or a device. The method and system includes initializing into an administrative card setup mode, providing information for at least one card to be registered, storing the information for the at least one card to be registered, and exiting the administrative card setup mode.

Abstract: The authentication of a device with a server over a network includes authenticating, by the device, the server so as to establish a secure connection with the server. The device communicates identification information of the device to the server, wherein the identification information uniquely identifies the device to the server. The server determines the credibility of the device using the identification information communicated by the device. In a case where the server determines that the device is credible, the server creates a first authentication token for the device, stores the first authentication token, and transfers the first authentication token to the device using the secure connection, and the device stores the first authentication token. The server authenticates the device using the first authentication token.

Abstract: A method and system for registering a card that is used to enable configurations of an application and/or a device. The method and system includes initializing into an administrative card setup mode, providing information for at least one card to be registered, storing the information for the at least one card to be registered, and exiting the administrative card setup mode.