Knowledge-Based VQA

Publication typeBook Chapter
Publication date2022-05-13
SJR
CiteScore2.7
Impact factor
ISSN21916586, 21916594
Abstract
Tasks such as VQA often require common sense and factual information in addition to the information learned from a task-specific dataset. Therefore, a knowledge-based VQA task is established. In this chapter, we first introduce the main datasets proposed for knowledge-based VQA and knowledge bases such as DBpediaDBpedia and ConceptNetConceptNet. Subsequently, we classify methods from three aspects: knowledge embedding, question-to-query translation and querying knowledge base methods.
Found 
Found 

Top-30

Journals

1
Pattern Recognition
1 publication, 50%
Big Data Mining and Analytics
1 publication, 50%
1

Publishers

1
Elsevier
1 publication, 50%
Tsinghua University Press
1 publication, 50%
1
  • We do not take into account publications without a DOI.
  • Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Metrics
2
Share
Cite this
GOST |
Cite this
GOST Copy
Wu Q. et al. Knowledge-Based VQA // Advances in Computer Vision and Pattern Recognition. 2022. pp. 73-90.
GOST all authors (up to 50) Copy
Wu Q., Wang P., Wang X., He X., Zhu W. Knowledge-Based VQA // Advances in Computer Vision and Pattern Recognition. 2022. pp. 73-90.
RIS |
Cite this
RIS Copy
TY - GENERIC
DO - 10.1007/978-981-19-0964-1_5
UR - https://doi.org/10.1007/978-981-19-0964-1_5
TI - Knowledge-Based VQA
T2 - Advances in Computer Vision and Pattern Recognition
AU - Wu, Qiang
AU - Wang, Peng
AU - Wang, Xin
AU - He, Xiaodong
AU - Zhu, Wenwu
PY - 2022
DA - 2022/05/13
PB - Springer Nature
SP - 73-90
SN - 2191-6586
SN - 2191-6594
ER -
BibTex
Cite this
BibTex (up to 50 authors) Copy
@incollection{2022_Wu,
author = {Qiang Wu and Peng Wang and Xin Wang and Xiaodong He and Wenwu Zhu},
title = {Knowledge-Based VQA},
publisher = {Springer Nature},
year = {2022},
pages = {73--90},
month = {may}
}