作者: David Harrison , Ashwin Navin , Josh Smallman
DOI:
关键词:
摘要: A method, apparatus and system annotation of meta-data through a capture infrastructure are disclosed. In one embodiment, method client device includes applying an automatic content recognition algorithm to determine identifier audio-visual data. The then associates the with advertisement data based on semantic correlation between provided by provider and/or identifier. annotates brand name product comparing entries in master database closed captioning application optical character may involve music identification, object facial voice identification. minimal functionality including accessing tuner stream decoder that identifies channel be found networked media device. produce audio fingerprint video is communicated infrastructure.