Abstract

This disclosure describes techniques that enable a user to identify a video or a movie by capturing a video snippet of a screen on which the video or movie is being displayed with a camera, e.g., a smartphone or other camera. The captured video snippet is cropped to the content of the screen. An embedding (fingerprint) is generated for the video and is matched to stored embeddings of video content to identify the video or the movie. Information regarding the identified movie, e.g., options to purchase or stream the movie, read reviews, etc. are provided to the user.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS