Autès, GabrielArpa, SamiSüsstrunk, Sabine2020-12-022020-12-022020-12-022020https://infoscience.epfl.ch/handle/20.500.14299/173803The present invention concerns a method of classifying a media item into a user profile suitability class in a classification system comprising a set of pre-trained artificial neural networks. The method comprising: receiving (101) a media file; extracting (103) a first data stream and a second data stream from the media file, the first media stream comprising first media content of a first media content form, the second data stream comprising second media content of a second, different media content form, the first and second data streams being comprised in the media item; generating (109, 111, 113) a first sequence of first feature vectors describing the first media content; generating (109, 111, 113) a second sequence of second feature vectors describing the second media content; generating (117) at least a first single feature vector representing the first sequence of first feature vectors and the second sequence of second feature vectors, or generating (117) at least a first single feature vector representing at least the first sequence of first feature vectors, and generating (119) a second feature vector representing at least the second sequence of second feature vectors; generating (123) a probability vector at least from the first single feature vector, or at least from the first and second single feature vectors; and assigning (125) a user profile suitability class to the media item based on the probability vector.patentUS11961300US2022207864EP3963503WO202022202766794039