Hierarchical multimodal transformers for Multipage DocVQA
Rubèn Tito, Dìmosthenis Karatzas, Ernest Valveny
Topics & Concepts
Computer scienceEncoderTransformerGranularityInformation retrievalFocus (optics)Representation (politics)Artificial intelligenceData miningProgramming languageOpticsOperating systemVoltageLawPoliticsPolitical sciencePhysicsQuantum mechanicsMultimodal Machine Learning ApplicationsTopic ModelingNatural Language Processing Techniques