Visual question answering with attention transfer and a cross-modal gating mechanism
Wei Li, Jianhui Sun, Ge Liu, Linglan Zhao, Xiangzhong Fang
Topics & Concepts
Computer scienceModalQuestion answeringArtificial intelligenceRepresentation (politics)Mechanism (biology)Filter (signal processing)Object (grammar)Visual reasoningGatingMachine learningNatural language processingComputer visionPhysiologyPhilosophyChemistryPolitical sciencePolymer chemistryLawBiologyPoliticsEpistemologyMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning