An object recognition ingestion system is presented. The object ingestion system captures image data of objects, possibly in an uncontrolled setting. The image data is analyzed to determine if one or more a priori know canonical shape objects match the object represented in the image data. The canonical shape object also includes one or more reference PoVs indicating perspectives from which to analyze objects having the corresponding shape. An object ingestion engine combines the canonical shape object along with the image data to create a model of the object. The engine generates a desirable set of model PoVs from the reference PoVs, and then generates recognition descriptors from each of the model PoVs. The descriptors, image data, model PoVs, or other contextually relevant information are combined into key frame bundles having sufficient information to allow other computing devices to recognize the object at a later time.

A device for transporting waste or recyclable material is disclosed. The device can include a base with at least one temporary attachment mechanism to secure a collapsible sleeve in an open state to the base. The device may further include a collapsible sleeve movable between an open state and a collapsed state, the collapsible sleeve including at least one opening for interfacing with the at least one temporary attachment mechanism to secure the collapsible sleeve in an open state to the base, thus forming a bin for receiving and transporting waste or recyclable material.

A device for transporting waste or recyclable material is disclosed. The device can include a base with at least one temporary attachment mechanism to secure a collapsible sleeve in an open state to the base. The device may further include a collapsible sleeve movable between an open state and a collapsed state, the collapsible sleeve including at least one opening for interfacing with the at least one temporary attachment mechanism to secure the collapsible sleeve in an open state to the base, thus forming a bin for receiving and transporting waste or recyclable material.

A method for resolving out of stock products in online shopping using image classification is disclosed. Product images are processed to determine feature descriptors to generate object classifiers to associated image similarities. A product is determined to be unavailable from a retailer. The product identifier is then provided to a hierarchical database containing indexed product images to determine therefrom other products whose images have classified similarities to images of the product. Similar products can then be presented to the user based upon their visual characteristics providing an improved product correlation.

Among other things, embodiments of the present disclosure improve the functionality of electronic messaging software and systems by generating customized images with avatars of different users within electronic messages. For example, users of different mobile computing devices can exchange electronic communications with images generated to include avatars representing themselves as well as their friends, colleagues, and other acquaintances.

An electronic device comprising circuitry configured to associate first information and at least a first portion of a first image, and circuitry configured to use a second image that includes a portion corresponding to at least the first portion of the first image to access the associated first information.

An electronic device comprising circuitry configured to associate first information and at least a first portion of a first image, and circuitry configured to use a second image that includes a portion corresponding to at least the first portion of the first image to access the associated first information.

A photo distribution method and a terminal are disclosed. In an embodiment a method for distributing photos include obtaining, by a first terminal in a photo sharing group, user portrait information and address information of a second terminal in the photo sharing group, obtaining, by the first terminal, first index information created by a third terminal in the photo sharing group, segmenting, by the first terminal, the first index information to obtain second index information, and allocating the second index information to a fourth terminal in the photo sharing group and sending, by the first terminal, the user portrait information and the address information of the second terminal to the fourth terminal.

A method includes, determining a portion of metadata of a media file associated with a first user matches a portion of metadata search parameters, wherein the metadata search parameters are associated with sending targeted notifications. Identifying, a targeted notification to send the first user based at least on the portion of the metadata of the media file matching the portion of the metadata search parameters. The method sends, the targeted notification to the first user, wherein the targeted notification is viewable on the first user's electronic device.

Digital image search training techniques and machine-learning architectures are described. In one example, a query digital image is received by service provider system, which is then used to select at least one positive sample digital image, e.g., having a same product ID. A plurality of negative sample digital images is also selected by the service provider system based on the query digital image, e.g., having different product IDs. The at least one positive sample digital image and the plurality of negative samples are then aggregated by the service provider system into a single aggregated digital image. At least one neural network is then trained by the service provider system using a loss function based on a feature comparison between the query digital image and samples from the aggregated digital image in a single pass.