Monday, January 20, 2014
Friday, January 3, 2014
Patent: Automatic creation of thumbnails for music videos
US Grant
There is provided a method for automatically creating a music video thumbnail (50) from a music video signal (12). The music video signal is separated into amusic signal (16) and a video signal (18). The music signal is analysed by detecting similarity regions and the sections of the music signal corresponding to the chorus are extracted (20). The video signal is analysed by detecting repeated lyrics (34). The extracted chorus sections from the music signal and the sectionsof the video signal containing repeated lyrics are then matched. A matched pair is then selected for use in the music video thumbnail and the timing of the pair are aligned (42) to form the thumbnail.
There is provided a method for automatically creating a music video thumbnail (50) from a music video signal (12). The music video signal is separated into amusic signal (16) and a video signal (18). The music signal is analysed by detecting similarity regions and the sections of the music signal corresponding to the chorus are extracted (20). The video signal is analysed by detecting repeated lyrics (34). The extracted chorus sections from the music signal and the sectionsof the video signal containing repeated lyrics are then matched. A matched pair is then selected for use in the music video thumbnail and the timing of the pair are aligned (42) to form the thumbnail.
Thursday, January 2, 2014
Patent: Method and apparatus for indexing and retrieving images using visual keywords
SG Grant 30 June 2003
US Grant 3 June 2003
A method, an apparatus and a computer program product for indexing andretrieving image data using visual keywords (108) is disclosed. Visual keywords(108) are prototypical, visual tokens (104) and are extracted from samples ofvisual documents (100) in a visual-content domain via supervised and/or unsupervised learning processes. An image or a video-shot key frame is described and indexed by a signature (112) that registers the spatial distribution of the visual keywords (108) present in its visual content. Visual documents (100) are retrieved for a sample query (120) by comparing the similarities between the signature (112) of the query (120) and those of visual documents (100) in the database. The signatures (112) of visual documents (100) are generated based on spatial distributions of the visual keywords (108). Singular-value decomposition (114) is applied to the signatures (112) to obtain a coded description (116).
US Grant 3 June 2003
A method, an apparatus and a computer program product for indexing andretrieving image data using visual keywords (108) is disclosed. Visual keywords(108) are prototypical, visual tokens (104) and are extracted from samples ofvisual documents (100) in a visual-content domain via supervised and/or unsupervised learning processes. An image or a video-shot key frame is described and indexed by a signature (112) that registers the spatial distribution of the visual keywords (108) present in its visual content. Visual documents (100) are retrieved for a sample query (120) by comparing the similarities between the signature (112) of the query (120) and those of visual documents (100) in the database. The signatures (112) of visual documents (100) are generated based on spatial distributions of the visual keywords (108). Singular-value decomposition (114) is applied to the signatures (112) to obtain a coded description (116).
Subscribe to:
Posts (Atom)