VideoRecognition - Uma proposta de serviço para reconhecimento de elementos de vídeo em larga escala

Deep Learning research has allowed significant advancement of various segments of multimedia, especially in tasks related to speech processing, hearing and computational vision. However, some video services are still focused only on the traditional use of media (capture, storage, transmission and presentation). In this paper, we discuss our ongoing research towards a DLaS, i.e. Deep Learning as a Service. This way, we present the state of art in video classification and recognition. Then we propose the VideoRecognition as DLaS to support the tasks such as: image classification and video scenes, object detection and facial recognition. We discuss the usage of the proposed service in the context of the video@RNP repository. Our main contributions consist on dicussussions over the state of art and it usage in nowdays multimedia services.