发明名称 Method and apparatus for querying media based on media characteristics
摘要 An approach is provided for querying media based on media characteristics. A media platform processes and/or facilitates a processing of one or more images, one or more videos, or a combination thereof to determine one or more latent vectors associated with the one or more images, the one or more videos, or the combination thereof. The media platform further causes, at least in part, a comparison of the one or more latent vectors to one or more models. The media platform also causes, at least in part, an indexing of the one or more images, the one or more videos, or the combination thereof based, at least in part, on the one or more latent vectors, the one or more models, or a combination thereof.
申请公布号 US9477664(B2) 申请公布日期 2016.10.25
申请号 US201113285429 申请日期 2011.10.31
申请人 Nokia Technologies Oy 发明人 Sathish Sailesh Kumar;Curcio Igor Danilo Diego
分类号 G06F17/30;G06F7/00 主分类号 G06F17/30
代理机构 Ditthavong & Steiner, P.C. 代理人 Ditthavong & Steiner, P.C.
主权项 1. A method comprising facilitating a processing of or processing (1) data or (2) information or (3) at least one signal, the (1) data or (2) information or (3) at least one signal based, at least in part, on the following: a processing of one or more images, one or more videos, one or more segments of the one or more images, one or more segments of the one or more videos, or a combination thereof to determine one or more media latent vectors associated with the one or more images, the one or more videos, the one or more segments of the one or more images, the one or more segments of the one or more videos, or the combination thereof; a processing of the one or more images, the one or more videos, the one or more segments of the one or more images, the one or more segments of the one or more videos, or the combination thereof to determine metadata associated with the one or more images, the one or more videos, the one or more segments of the one or more images, the one or more segments of the one or more videos, or the combination thereof; an indexing of the one or more images, the one or more videos, the one or more segments of the one or more images, the one or more segments of the one or more videos, or the combination thereof based, at least in part, on the metadata; a comparison of the one or more media latent vectors to one or more model latent vectors associated with one or more models, wherein the one or more models are predetermined media,wherein the one or more model latent vectors are based on a factorization of the predetermined media using one or more predetermined latent parameters; and an indexing to determine an index of indexed latent vectors associated with the one or more images, the one or more videos, the one or more segments of the one or more images, the one or more segments of the one or more videos, or the combination thereof based, at least in part, on the comparison.
地址 Epsoo FI