mlsanityData to 7 Oct 2026

Answer Them All! Toward Universal Visual Question Answering Models

arXiv 1903.00366 ↗First posted 1 Mar 2019cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Visual Question Answering (VQA) research is split into two camps: the first focuses on VQA datasets that require natural image understanding and the second focuses on synthetic datasets that test reasoning. A good VQA algorithm should be capable of both, but only a few VQA algorithms are tested in this manner. We compare five state-of-the-art VQA algorithms across eight VQA datasets covering both domains. To make the comparison fair, all of the models are standardized as much as possible, e.g., they use the same visual features, answer vocabularies, etc. We find that methods do not generalize across the two domains. To address this problem, we propose a new VQA algorithm that rivals or exceeds the state-of-the-art for both domains.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 4; 2023: 3; 2024: 3.

17 papers.

Sort:

By area:

  1. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  2. 2024CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoningcited by 64
  3. 2021Multimodal Integration of Human-Like Attention in Visual Question Answeringcited by 20
  4. 2021Towards Language-guided Visual Recognition via Dynamic Convolutionscited by 17
  5. 2024Improving Generalization in Visual Reasoning via Self-Ensemblecited by 15
  6. 2021Are Bias Mitigation Techniques for Deep Learning Effective?cited by 14
  7. 2021Cognitive Visual Commonsense Reasoning Using Dynamic Working Memorycited by 14
  8. 2021Interpretable Visual Understanding with Cognitive Attention Networkcited by 12
  9. 2022QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoningcited by 5
  10. 2021A Picture May Be Worth a Hundred Words for Visual Question Answeringcited by 3
  11. 2023LOIS: Looking Out of Instance Semantics for Visual Question Answeringcited by 3
  12. 2024VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Taskscited by 3
5 more
  1. 2022SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answeringcited by 2
  2. 2021Improved RAMEN: Towards Domain Generalization for Visual Question Answeringcited by 1
  3. 2022Question-Driven Graph Fusion Network For Visual Question Answeringcited by 1
  4. 2022Attention Mechanism based Cognition-level Scene Understandingcited by 0
  5. 2023VQA with Cascade of Self- and Co-Attention Blockscited by 0