Connexion
Idée - Zero-Shot Visual Question Answering
Leveraging Question-Driven Image Captions to Enhance Zero-Shot Visual Question Answering
Incorporating question-driven image captions into a zero-shot visual question answering pipeline can enhance performance across various question types compared to using general-purpose image captions.
Improving Zero-Shot Visual Question Answering by Rephrasing and Augmenting Questions with Visually-Grounded Details
Addressing underspecification in visual question inputs can improve zero-shot performance of large vision-language models by incorporating relevant visual details and commonsense reasoning.
Multi-Agent VQA: Exploring Zero-Shot Visual Question Answering with Specialized Agents
Foundation models in VQA can achieve zero-shot performance using specialized agents within a multi-agent system.
Produits
© 2024 by Linnk AI