Publication | Closed Access

Tell and guess: cooperative learning for natural image caption generation with hierarchical refined attention

Artificial IntelligenceNatural Language ProcessingMultimodal LlmEngineeringMachine LearningData ScienceText-to-image RetrievalVisual GroundingVision Language ModelVisual Question AnsweringComputer ScienceDeep LearningCooperative LearningComputer VisionMachine Translation