| Headline | A short description of the main activity or objects in the image or video. Returned when supplied by Ahoy | Text (Short) | No | Forklift moving across a warehouse floor |
| Object counts | How many of each type of object were detected. For example, 3 people and 1 truck | Text (Long) | No | {"person": 2, "truck": 1} |
| Report summary | A brief written summary of the scene. Returned when supplied by Ahoy | Text (Long) | No | A forklift operating in a warehouse aisle |
| Report description | A more detailed written description of what appears in the media. Returned when supplied by Ahoy | Text (Long) | No | Workers and a forklift move through the aisle. |
| Media width | Width of the media in pixels | Number | No | 1280 |
| Media height | Height of the media in pixels | Number | No | 720 |
| Frames per second | Number of frames shown per second in the video | Number | No | 30 |
| Duration | Length of the video in seconds | Number | No | 12.5 |
| Annotated media | A copy of the media with boxes and labels showing detected objects. Images return as JPEG; videos as H.264 MP4. Uncertain detections may be left out | File | No | annotated_input-forklift.mp4 |