The detection of the video is done in detail. The tool is used for the detailed study of content present in the video. Whereas BOD segments stand with a very slight difference from the Metadata Detection. The only difference that the BOD segment consists of is that it defines the type of content resented in the video.
Covered: Activities, Emotions, Face, Objects, shoppable products, locations, blur detection, and brands
Method Used: Vision Models, OCR, Audio