Systems and methods are described for disambiguating user input based on a physical location of items in a vicinity of a user. The system determines that a query received from a user contains an ambiguity. In response, the system identifies several items in the physical vicinity of the user. Then, the system analyzes the identified plurality of items to determine whether the plurality of items forms a first ensemble of items or a second ensemble of items. If the plurality of items forms a first ensemble of items, the system performs a search using the search query and a first keyword related to the first ensemble of items. If the plurality of items forms a second ensemble of items, the system performs a search using the search query and a second keyword related to the second ensemble of items. The system then outputs results of the performed search.

An information delivery system has a computational device connected over a network with a server and associated storage device. The computational device is configured with functionality that generates a message requesting information relating to a particular geolocation that is stored in association with the server. The server identifies one or more files corresponding to the location information in the message and delivers them to the computational device, which compares information in the files with a visual image relating to an object selected by a computational device user and with an object type relating to the visual image, and displays information in a file if the visual image selected by the user matches visual image information in the file.

An information delivery system has a computational device connected over a network with a server and associated storage device. The computational device is configured with functionality that generates a message requesting information relating to a particular geolocation that is stored in association with the server. The server identifies one or more files corresponding to the location information in the message and delivers them to the computational device, which compares information in the files with a visual image relating to an object selected by a computational device user and with an object type relating to the visual image, and displays information in a file if the visual image selected by the user matches visual image information in the file.

A neural network for automatically tagging an input image is provided. The neural network includes a residual attention network configured to extract features of the input image and generate a first feature map including the features of the input image; a first tagging network configured to receive the first feature map and generate a predicted probability of a first tag of the input image; a second tagging network configured to receive the first feature map and generate a predicted probability of a second tag of the input image; and a third tagging network configured to receive the first feature map and generate a predicted probability of a third tag of the input image.

A query image is obtained. In a database including a plurality of reference image graphs, at least one of the reference image graphs, with feature vectors similar to the query image, is identified. Image querying is carried out by graph traversal on the at least one of the reference image graphs with the feature vectors similar to the query image. An image from the at least one of the reference image graphs having a highest matching score in the graph traversal is returned as a response to the query image. techniques for building the database are also disclosed.

A query image is obtained. In a database including a plurality of reference image graphs, at least one of the reference image graphs, with feature vectors similar to the query image, is identified. Image querying is carried out by graph traversal on the at least one of the reference image graphs with the feature vectors similar to the query image. An image from the at least one of the reference image graphs having a highest matching score in the graph traversal is returned as a response to the query image. techniques for building the database are also disclosed.

Entities such as hotels, restaurants, resorts, houses, vehicles, and other places and things, are associated with images of each entity. The images are tagged using machine learning to identify what aspects of the associated entity are captured by each image. When a user is requested to select an entity from a set of entities, a user preference model is used to determine what tags the user is interested in. The tags are used to select images associated with the entities from the set of entities, and the selected images are displayed to the user. The user can then provide indicators that show which of the displayed images the user likes or dislikes. Based on the indicators, one or more entities from the set of entities is presented to the user. The model may also be updated based on the indicators.

Entities such as hotels, restaurants, resorts, houses, vehicles, and other places and things, are associated with images of each entity. The images are tagged using machine learning to identify what aspects of the associated entity are captured by each image. When a user is requested to select an entity from a set of entities, a user preference model is used to determine what tags the user is interested in. The tags are used to select images associated with the entities from the set of entities, and the selected images are displayed to the user. The user can then provide indicators that show which of the displayed images the user likes or dislikes. Based on the indicators, one or more entities from the set of entities is presented to the user. The model may also be updated based on the indicators.

In one aspect, an example method to be performed by a computing device includes (a) receiving a request to use a camera of the computing device; (b) in response to receiving the request, (i) using a microphone of the computing device to capture audio content and (ii) using the camera of the computing device to capture an image; (c) identifying reference audio content that has at least a threshold extent of similarity with the captured audio content; and (d) outputting an indication of the identified reference audio content while displaying the captured image.

An image file generation apparatus for storing one or more images in an image file according to a predetermined image file format, the apparatus obtains a plurality of pieces of metadata to be stored in the image file, groups the plurality of pieces of metadata by a type of the metadata, and stores, in the image file, the metadata that has been grouped.