MoZuMa: A Model Zoo for Multimedia Applications

ABSTRACTLots of machine learning models with applications in Multimedia Search are released as Open Source Software. However, integrating these models into an application is not always an easy task due to the lack of a consistent interface to run, train or distribute models. With MoZuMa, we aim at reducing this effort by providing a model zoo for image similarity, text-to-image retrieval, face recognition, object similarity search, video key-frames detection and multilingual text search implemented in a generic interface with a modular architecture. The code is released as Open Source Software at https://github.com/mozuma/mozuma.