Knowledge Acquisition for Visual Question Answering via Iterative Querying

41 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (2019, background): “Several knowledge bases have been created using visual data or for visual reasoning tasks [53, 9, 11, 39, 56, 55].”
Interpretable Visual Question Answering by Reasoning on Dependency Trees (2018, background): “[22] actively acquired predefined types of evidence to obtain external information and predict answers.”
KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA (2020, background): “There have been a number of knowledge bases proposed and used for knowledge-based reasoning, both for language-only and multi-modal tasks [88, 14, 17, 66, 91, 90, 10, 54, 37].”
Semantic bottleneck for computer vision tasks (2018, background): “of the global algorithm. differs in the separation between the question generator and semantic representation encoder, and is not applied to the same tasks. Our work builds on the observation made by [41,42] – questions that are asked about an image provide information regarding the image and can he”
Visual Question Reasoning on General Dependency Tree (2018, background): “[35] actively acquires pre-deﬁned types of evidence to obtain external information and predicted the answer.”