Achieving Human Parity on Visual Question Answering

Achieving Human Parity on Visual Question Answering

The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image. It has been a popular research topic with an increasing number of real-world applications in the last decade. This paper introduces a novel hierarchical in...

Full description

Bibliographic Details
Main Authors: Bi, B. (Author), Huang, F. (Author), Huang, S. (Author), Jin, R. (Author), Li, C. (Author), Si, L. (Author), Tian, J. (Author), Wang, W. (Author), Xu, H. (Author), Xu, X. (Author), Yan, M. (Author), Zhang, J. (Author)
Format: Article
Language:English
Published: Association for Computing Machinery 2023
Subjects:
cross-modal interaction
Cross-modal interaction
Image analysis
Image content analysis
Image enhancement
Multi-modal
multi-modal pre-training
Multi-modal pre-training
Pre-training
Question Answering
Semantics
Text and image content analyse
text and image content analysis
Text content
Visual languages
Visual question answering
Visual Question Answering
visual reasoning
Visual reasoning
Online Access:View Fulltext in Publisher
View in Scopus

Internet

View Fulltext in Publisher
View in Scopus

Similar Items