Explaining VQA predictions using visual grounding and a knowledge base
Authors:
- Felipe RiquelmeFRFelipe Riquelme
- Alfredo De GoyenecheAGAlfredo De Goyeneche
- Yundong ZhangYZYundong Zhang
- Juan Carlos NieblesJNJuan Carlos Niebles
- Alvaro SotoASAlvaro Soto
- 1 September 2020
- journal article
- research article
- Published by Elsevier in Image and Vision Computing
- Vol. 101
Abstract
No abstract availableKeywords
Funding Information
- FONDECYT Grant (1181739)
- Millennium Institute for Foundational Research on Data
This publication has 6 references indexed in Scilit:
- Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question AnsweringInternational Journal of Computer Vision, 2018
- Beyond Bilinear: Generalized Multimodal Factorized High-Order Pooling for Visual Question AnsweringIEEE Transactions on Neural Networks and Learning Systems, 2018
- FVQA: Fact-Based Visual Question AnsweringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- WordNetCommunications of the ACM, 1995
- The Proof and Measurement of Association between Two ThingsThe American Journal of Psychology, 1904