OK VQA
Related Papers
Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering
AbstractKnowledge-based visual question answering (VQA) requires answering questions with external knowledge in addition to the content of images. One dataset that is mostly used in evaluating knowledge-based VQA is OK-VQA, …...
Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answering
AbstractMost Outside-Knowledge Visual Question Answering (OK-VQA) systems employ a two-stage framework that first retrieves external knowledge given the visual question and then predicts the answer based on the retrieved content. …...
Retrieval Augmented Visual Question Answering with Outside Knowledge
AbstractOutside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQA task that requires retrieval of external knowledge to answer questions about images. Recent OK-VQA systems use Dense Passage Retrieval (DPR) to …...
End-to-end Knowledge Retrieval with Multi-modal Queries
AbstractWe investigate knowledge retrieval with multi-modal queries, i.e. queries containing information split across image and text inputs, a challenging task that differs from previous work on cross-modal retrieval. We curate …...
Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering
AbstractThe field of visual question answering (VQA) has recently seen a surge in research focused on providing explanations for predicted answers. However, current systems mostly rely on separate models to …...