@inproceedings{chowdhury-soni-2021-eavqa,
title = "ea{VQA}: An Experimental Analysis on Visual Question Answering Models",
author = "Chowdhury, Souvik and
Soni, Badal",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.67",
pages = "550--554",
abstract = "Visual Question Answering (VQA) has recently become a popular research area. VQA problem lies in the boundary of Computer Vision and Natural Language Processing research domains. In VQA research, the dataset is a very important aspect because of its variety in image types i.e. natural and synthetic and also question answer source i.e. originated from human source or computer-generated question answer. Various details about each dataset is given in this paper, which can help future researchers to a great extent. In this paper, we discussed and compared the experimental performance of Stacked Attention Network Model (SANM) and bidirectional LSTM and MUTAN based fusion models. As per the experimental results, MUTAN accuracy and loss are 29{\%} and 3.5 respectively. SANM model is giving 55{\%} accuracy and a loss of 2.2 whereas VQA model is giving 59{\%} accuracy and 1.9 loss.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chowdhury-soni-2021-eavqa">
<titleInfo>
<title>eaVQA: An Experimental Analysis on Visual Question Answering Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Souvik</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badal</namePart>
<namePart type="family">Soni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visual Question Answering (VQA) has recently become a popular research area. VQA problem lies in the boundary of Computer Vision and Natural Language Processing research domains. In VQA research, the dataset is a very important aspect because of its variety in image types i.e. natural and synthetic and also question answer source i.e. originated from human source or computer-generated question answer. Various details about each dataset is given in this paper, which can help future researchers to a great extent. In this paper, we discussed and compared the experimental performance of Stacked Attention Network Model (SANM) and bidirectional LSTM and MUTAN based fusion models. As per the experimental results, MUTAN accuracy and loss are 29% and 3.5 respectively. SANM model is giving 55% accuracy and a loss of 2.2 whereas VQA model is giving 59% accuracy and 1.9 loss.</abstract>
<identifier type="citekey">chowdhury-soni-2021-eavqa</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.67</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>550</start>
<end>554</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T eaVQA: An Experimental Analysis on Visual Question Answering Models
%A Chowdhury, Souvik
%A Soni, Badal
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F chowdhury-soni-2021-eavqa
%X Visual Question Answering (VQA) has recently become a popular research area. VQA problem lies in the boundary of Computer Vision and Natural Language Processing research domains. In VQA research, the dataset is a very important aspect because of its variety in image types i.e. natural and synthetic and also question answer source i.e. originated from human source or computer-generated question answer. Various details about each dataset is given in this paper, which can help future researchers to a great extent. In this paper, we discussed and compared the experimental performance of Stacked Attention Network Model (SANM) and bidirectional LSTM and MUTAN based fusion models. As per the experimental results, MUTAN accuracy and loss are 29% and 3.5 respectively. SANM model is giving 55% accuracy and a loss of 2.2 whereas VQA model is giving 59% accuracy and 1.9 loss.
%U https://aclanthology.org/2021.icon-main.67
%P 550-554
Markdown (Informal)
[eaVQA: An Experimental Analysis on Visual Question Answering Models](https://aclanthology.org/2021.icon-main.67) (Chowdhury & Soni, ICON 2021)
ACL