Abstract: Current interfaces for displaying information about items appearing in videos are obtrusive and counterintuitive. They also rely on annotations, or metadata tags, added by hand to the frames in the video, limiting their ability to display information about items in the videos. In contrast, examples of the systems disclosed here use neural networks to identify items appearing on- and off-screen in response to intuitive user voice queries, touchscreen taps, and/or cursor movements. These systems display information about the on- and off-screen items dynamically and unobtrusively to avoid disrupting the viewing experience.

Abstract: The present invention relates generally to targeted molecular agents (TMAs) directed to a particular organism or group of organisms and uses thereof. More particularly, the present invention provides TMAs having a targeting moiety which comprises a natural or induced auxotrophic requirement of the particular organism as a vehicle for directing an agent linked to the moiety to be delivered to the target organism. The TMAs of the present invention are useful for targeting molecules such as antimicrobial agents and diagnostic agents to selected organisms.