Visual Question Generation Answering (VQG-VQA) using Machine Learning Models
WSEAS TRANSACTIONS ON SYSTEMS · 28.06.2023 · 22 · 663-670
DOI: 10.37394/23202.2023.22.67 ↗Kurz gefasst
Fachartikel in der Zeitschrift WSEAS TRANSACTIONS ON SYSTEMS, online erschienen am 28.06.2023. Verfasst von Atul Kachare und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 28 Literaturangaben.
Abstract (Originalsprache)
Presented automated visual question-answer system generates graphics-based question-answer pairs. The system consists of the Visual Query Generation (VQG) and Visual Question Answer (VQA) modules. VQG generates questions based on visual cues, and VQA provides matching answers to the VQG modules. VQG system generates questions using LSTM and VGG19 model, training parameters, and predicting words with the highest probability for output. VQA uses VGG-19 convolutional neural network for image encoding, embedding, and multilayer perceptron for high-quality responses. The proposed system reduces the need for human annotation and thus supports the traditional education sector by significantly reducing the human intervention required to generate text queries. The system can be used in interactive interfaces to help young children learn.
Zitieren
APA
Kachare, A., Kalla, M., & Gupta, A. (2023). Visual Question Generation Answering (VQG-VQA) using Machine Learning Models. WSEAS TRANSACTIONS ON SYSTEMS, 22, 663-670. https://doi.org/10.37394/23202.2023.22.67
Vancouver
Kachare A, Kalla M, Gupta A. Visual Question Generation Answering (VQG-VQA) using Machine Learning Models. WSEAS TRANSACTIONS ON SYSTEMS. 2023;22:663-670. doi:10.37394/23202.2023.22.67
BibTeX
@article{Kachare2023,
author = {Kachare, Atul and Kalla, Mukesh and Gupta, Ashutosh},
title = {Visual Question Generation Answering (VQG-VQA) using Machine Learning Models},
journal = {WSEAS TRANSACTIONS ON SYSTEMS},
year = {2023},
volume = {22},
pages = {663--670},
doi = {10.37394/23202.2023.22.67}
}
EUVIMED