Paper Info
Title
Accuracy vs. complexity: A trade-off in visual question answering models
Abstract
•Systematic investigation of Accuracy vs. Complexity trade-off for VQA Models.•Often additional complexity does not guarantee higher VQA accuracy.•SeNet features are more generalizable than ResNet features.•Superior bilinear fusion with visual attention results in higher VQA accuracy.
Year
DOI
Venue
2021
10.1016/j.patcog.2021.108106
Pattern Recognition
Keywords
DocType
Volume
Visual question answering,Visual feature extraction,Language features,Multi-modal fusion,Speed-accuracy trade-off
Journal
120
Issue
ISSN
Citations 
1
0031-3203
0
PageRank 
References 
Authors
0.34
15
3
Name
Order
Citations
PageRank
Farazi Moshiur R.100.34
Salman Khan238741.05
Nick Barnes357768.68