A method and device for identifying a main picture in a web page. The method comprises: picking out candidate main pictures based on a page attributes of each picture in a web page (210); cropping an original picture of each candidate main picture to obtain a corresponding picture composition (220); determining a candidate main picture having an information topic matching a topic of the web page (230); and identifying a picture composition corresponding to the matched candidate main picture as the main picture of the web page (240).

Provided are systems and techniques that provide an output phrase describing an image. An example method includes creating, with a convolutional neural network, feature maps describing image features in locations in the image. The method also includes providing a skeletal phrase for the image by processing the feature maps with a first long short-term memory (LSTM) neural network trained based on a first set of ground truth phrases which exclude attribute words. Then, attribute words are provided by processing the skeletal phrase and the feature maps with a second LSTM neural network trained based on a second set of ground truth phrases including words for attributes. Then, the method combines the skeletal phrase and the attribute words to form the output phrase.

An information processing system is configured to distribute account information for permitting setting for a service of a service providing system, to a content providing system, distribute, to the content providing system, a search module for causing the terminal device to perform a process of transmitting a search request to request a search for link information based on an environment of the terminal device, to a user environment identification device in association with identification information of the terminal device, transmit, to the terminal device, the link information that is retrieved from a databased based on the environment included in the search request that is transmitted from the terminal device in association with the identification information by the terminal device executing the search module, access the service providing system in accordance with the account information, perform setting for the service, and acquire the link information corresponding to the setting.

The present disclosure relates to systems and methods for retrieving image data. The systems may obtain a search request from a user device, the search request including at least one keyword. The systems may identify, in an image database, one or more target image archives associated with one or more target tags, respectively. The systems may retrieve, from the image database, the one or more target image archives, each of the one or more target image archives including a plurality of target images. The systems may transmit the one or more target image archives to the user device to be displayed via a user interface of the user device.

A visual search engine is described herein. The visual search engine is configured to return information to a client computing device based upon a multimodal query received from the client computing device (wherein the multimodal query comprises an image and text). The visual search engine is further configured to interact with a user of the client computing device to disambiguate information retrieval intent of the user.

Systems, methods, devices, media, and computer readable instructions are described for local image tagging in a resource constrained environment. One embodiment involves processing image data using a deep convolutional neural network (DCNN) comprising at least a first subgraph and a second subgraph, the first subgraph comprising at least a first layer and a second layer, processing, the image data using at least the first layer of the first subgraph to generate first intermediate output data; processing, by the mobile device, the first intermediate output data using at least the second layer of the first subgraph to generate first subgraph output data, and in response to a determination that each layer reliant on the first intermediate data have completed processing, deleting the first intermediate data from the mobile device. Additional embodiments involve convolving entire pixel resolutions of the image data against kernels in different layers if the DCNN.

A device can receive parking information for a set of street segments within a geographic region. The parking information can include metadata for a set of parking spaces within the set of street segments. The device can create a set of block-face objects that represent block-faces within the set of street segments. The device can generate a data structure that associates the parking information for the set of street segments with the set of block-face objects. The device can receive, from a user device, a request for parking information associated with a geographic area. The device can obtain the parking information associated with the geographic area by using location information included in the request to search the data structure. The device can provide the parking information associated with the geographic area for display on a user interface of the user device.

Aspects of the present invention disclose a method, computer program product, and system for identifying symptoms based on digital media. The method includes one or more processors receiving digital media and information associated with a first animal from a user. The method further includes one or more processors identifying data records, stored in a knowledge database, that are respectively associated with an animal that is similar to the first animal. The method further includes one or more processors determining symptom information corresponding to the first animal based on a comparison of the received digital media and information associated with the first animal and the identified data records. The method further includes presenting the determined symptom information to a user.

Techniques for distinguishing objects (e.g., an individual or an individual pushing a shopping cart) are disclosed. An object is detected in images of a scene. A height map is generated from the images, and the object is represented as height values in the height map. Based on height properties associated with another object, it is determined whether the other object is associated with the object. If so determined, the objects are classified separately.

A system provides access to previously unassociated cameras that are concurrently at different specific locations at a single event, sending the real-time video and audio stream of said cameras to a central processing entity, transcoding and serving the real-time content to consumers in a way that associates the content as different camera angles of the same event, along with additional data from each camera owner such as twitter feeds. Also disclosed is a system for providing a user, via a client device, the ability to choose a desired feed for viewing the event and the ability to change the selected feed based a number of user-selected criteria.