Apparatus and methods for content description

A method comprising:

• receiving an input comprising a video image associated with video game content, the video image showing an object in motion in the video game content;
• receiving controller data associated with the object in motion;
• detecting, utilizing a model, a predetermined motion of the object in motion;
• mapping, utilizing the model, the predetermined motion to a plurality of captions based at least in part on the controller data associated with the object in motion, the model having been trained at least in part on a plurality of controller data associated with a plurality of objects in motion;
• detect an object type represented in the video image, the object type associated with the predetermined motion;
• and
• determining, utilizing the model, a caption of the plurality of captions based at least in part on the mapping and the object type, the caption describing the predetermined motion.

A non-transitory, computer readable storage medium containing computer software which, when executed, causes one or more computers to, at least:

• receive an input comprising a video image associated with video game content, the video image showing an object in motion in the video game content;
• receive controller data associated with the object in motion;
• detect, utilizing a model, a predetermined motion of the object in motion;
• map, utilizing the model, the predetermined motion to a plurality of captions based at least in part on the controller data associated with the object in motion, the model having been trained at least in part on a plurality of controller data associated with a plurality of objects in motion;
• detect an object type represented in the video image, the object type associated with the predetermined motion;
• and
• determine, utilizing the model, a caption of the plurality of captions based at least in part on the mapping and the object type, the caption describing the predetermined motion.