MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization

Alexander Kunitsyn, Maksim Kalashnikov, Maksim Dzabraev +1

In this work we present a new State-of-The-Art on the text-to-video retrieval task on MSR-VTT, LSMDC, MSVD, YouCook2 and TGIF obtained by a single model. Three different data sourc…