A set of partial words is received. At least one partial word in the set of partial words is completed. The set of partial words with the at least one completed partial word is run through a trained deep neural network, the trained deep neural network inferring a word embedding associated with an unfinished word in the set of partial words. An inferred word is determined based on the inferred word embedding associated with the unfinished word. A sentence may be output, which includes at least the completed partial word and the inferred word.

Devices, systems, and methods are provided for enhancing delivery option user interfaces. A method may include receiving, at a first device and at a first time, a delivery request from a second device, and determining a location for the delivery request. The method may include determining, based on the first time and the location, a first available delivery time window and a second available delivery time window, each having respective start and end times. The method may include facilitating presentation of first interface data and second interface data at the second device, including a first indication that a third available delivery time window associated with a no-charge delivery begins at the first time and ends at the second end time, and including a second indication of the first available delivery time window.

Devices, systems, and methods are provided for enhancing delivery option user interfaces. A method may include receiving, at a first device and at a first time, a delivery request from a second device, and determining a location for the delivery request. The method may include determining, based on the first time and the location, a first available delivery time window and a second available delivery time window, each having respective start and end times. The method may include facilitating presentation of first interface data and second interface data at the second device, including a first indication that a third available delivery time window associated with a no-charge delivery begins at the first time and ends at the second end time, and including a second indication of the first available delivery time window.

An interactive 3D cursor facilitates selection and manipulation of a three-dimensional volume from a three-dimensional image. The selected volume image may be transparency-adjusted and filtered to remove selected tissues from view. Qualitative and quantitative analysis of tissues in a selected volume may be performed. Location indicators, annotations, and registration markers may be overlaid on selected volume images.

An interactive 3D cursor facilitates selection and manipulation of a three-dimensional volume from a three-dimensional image. The selected volume image may be transparency-adjusted and filtered to remove selected tissues from view. Qualitative and quantitative analysis of tissues in a selected volume may be performed. Location indicators, annotations, and registration markers may be overlaid on selected volume images.

Techniques for cursor position based on focus of a glasses device are described and are implementable to enable cursor positioning and repositioning between different visual regions displayed by a glasses device. The described implementations, for example, track changes in focus orientation of a user of a glasses device and reposition and/or activate a cursor based on the changes.

Techniques for cursor position based on focus of a glasses device are described and are implementable to enable cursor positioning and repositioning between different visual regions displayed by a glasses device. The described implementations, for example, track changes in focus orientation of a user of a glasses device and reposition and/or activate a cursor based on the changes.

Techniques are generally described for predicting text relevant to image data. In various examples, the techniques may include receiving image data comprising a first portion. The first portion of the image data may correspond to a first plurality of pixels when rendered on the display. Text data comprising a first text related to the first portion of the image data may be received. A first vector representation of the first portion of the image data may be determined. In some examples, a correspondence between the first portion of the image data and the first text may be determined based at least in part on the first vector representation. A first identifier of the first portion of image data may be stored in a data structure in association with a second identifier of the first text.

Techniques are generally described for predicting text relevant to image data. In various examples, the techniques may include receiving image data comprising a first portion. The first portion of the image data may correspond to a first plurality of pixels when rendered on the display. Text data comprising a first text related to the first portion of the image data may be received. A first vector representation of the first portion of the image data may be determined. In some examples, a correspondence between the first portion of the image data and the first text may be determined based at least in part on the first vector representation. A first identifier of the first portion of image data may be stored in a data structure in association with a second identifier of the first text.

A method and apparatus for writing a report is described herein. During the process an officer will acquire an image of an incident scene. The image may comprise a live image, a video, or a still image (picture). Potential objects of interest will be highlighted within the image for selection by the officer. When an object of interest is selected (e.g., touched on a touch screen), a description of the object of interest will be inserted at a point in a report where a cursor lies. The user will also be allowed to transcribe (via speech to text) their report, and have text representing their speech inserted where the cursor lies.