3D captions with semantic graphical elements

A method comprising:

• receiving, by a messaging application, a video feed from a camera of a device that depicts an object;
• receiving a request to add a three-dimensional (3D) caption to the video feed;
• identifying a graphical element that is associated with context of the 3D caption;
• displaying the 3D caption and the identified graphical element in the video feed proximate to the object depicted in the video feed;
• and
• in response to determining that the object is no longer detected in the video feed, moving the 3D caption to a surface depicted in the video feed without displaying the graphical element.

A non-transitory machine-readable medium storing instructions which, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

• receiving, by a messaging application, a video feed from a camera of a device that depicts an object;
• receiving a request to add a three-dimensional (3D) caption to the video feed;
• identifying a graphical element that is associated with context of the 3D caption;
• displaying the 3D caption and the identified graphical element in the video feed proximate to the object depicted in the video feed;
• and
• in response to determining that the object is no longer detected in the video feed, moving the 3D caption to a surface depicted in the video feed without displaying the graphical element.