@inproceedings{gatti-etal-2022-cofar,
title = "{COFAR}: Commonsense and Factual Reasoning in Image Search",
author = "Gatti, Prajwal and
Penamakuri, Abhirama Subramanyam and
Teotia, Revant and
Mishra, Anand and
Sengupta, Shubhashis and
Ramnani, Roshni",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-main.87",
pages = "1185--1199",
abstract = "One characteristic that makes humans superior to modern artificially intelligent models is the ability to interpret images beyond what is visually apparent. Consider the following two natural language search queries {--} (i) {``}a queue of customers patiently waiting to buy ice cream{''} and (ii) {``}a queue of tourists going to see a famous Mughal architecture in India{''}. Interpreting these queries requires one to reason with (i) Commonsense such as interpreting people as customers or tourists, actions as waiting to buy or going to see; and (ii) Fact or world knowledge associated with named visual entities, for example, whether the store in the image sells ice cream or whether the landmark in the image is a Mughal architecture located in India. Such reasoning goes beyond just visual recognition. To enable both commonsense and factual reasoning in the image search, we present a unified framework namely Knowledge Retrieval-Augmented Multimodal Transformer (KRAMT) that treats the named visual entities in an image as a gateway to encyclopedic knowledge and leverages them along with natural language query to ground relevant knowledge. Further, KRAMT seamlessly integrates visual content and grounded knowledge to learn alignment between images and search queries. This unified framework is then used to perform image search requiring commonsense and factual reasoning. The retrieval performance of KRAMT is evaluated and compared with related approaches on a new dataset we introduce {--} namely COFAR.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gatti-etal-2022-cofar">
<titleInfo>
<title>COFAR: Commonsense and Factual Reasoning in Image Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prajwal</namePart>
<namePart type="family">Gatti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhirama</namePart>
<namePart type="given">Subramanyam</namePart>
<namePart type="family">Penamakuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Revant</namePart>
<namePart type="family">Teotia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubhashis</namePart>
<namePart type="family">Sengupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roshni</namePart>
<namePart type="family">Ramnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One characteristic that makes humans superior to modern artificially intelligent models is the ability to interpret images beyond what is visually apparent. Consider the following two natural language search queries – (i) “a queue of customers patiently waiting to buy ice cream” and (ii) “a queue of tourists going to see a famous Mughal architecture in India”. Interpreting these queries requires one to reason with (i) Commonsense such as interpreting people as customers or tourists, actions as waiting to buy or going to see; and (ii) Fact or world knowledge associated with named visual entities, for example, whether the store in the image sells ice cream or whether the landmark in the image is a Mughal architecture located in India. Such reasoning goes beyond just visual recognition. To enable both commonsense and factual reasoning in the image search, we present a unified framework namely Knowledge Retrieval-Augmented Multimodal Transformer (KRAMT) that treats the named visual entities in an image as a gateway to encyclopedic knowledge and leverages them along with natural language query to ground relevant knowledge. Further, KRAMT seamlessly integrates visual content and grounded knowledge to learn alignment between images and search queries. This unified framework is then used to perform image search requiring commonsense and factual reasoning. The retrieval performance of KRAMT is evaluated and compared with related approaches on a new dataset we introduce – namely COFAR.</abstract>
<identifier type="citekey">gatti-etal-2022-cofar</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-main.87</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>1185</start>
<end>1199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COFAR: Commonsense and Factual Reasoning in Image Search
%A Gatti, Prajwal
%A Penamakuri, Abhirama Subramanyam
%A Teotia, Revant
%A Mishra, Anand
%A Sengupta, Shubhashis
%A Ramnani, Roshni
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F gatti-etal-2022-cofar
%X One characteristic that makes humans superior to modern artificially intelligent models is the ability to interpret images beyond what is visually apparent. Consider the following two natural language search queries – (i) “a queue of customers patiently waiting to buy ice cream” and (ii) “a queue of tourists going to see a famous Mughal architecture in India”. Interpreting these queries requires one to reason with (i) Commonsense such as interpreting people as customers or tourists, actions as waiting to buy or going to see; and (ii) Fact or world knowledge associated with named visual entities, for example, whether the store in the image sells ice cream or whether the landmark in the image is a Mughal architecture located in India. Such reasoning goes beyond just visual recognition. To enable both commonsense and factual reasoning in the image search, we present a unified framework namely Knowledge Retrieval-Augmented Multimodal Transformer (KRAMT) that treats the named visual entities in an image as a gateway to encyclopedic knowledge and leverages them along with natural language query to ground relevant knowledge. Further, KRAMT seamlessly integrates visual content and grounded knowledge to learn alignment between images and search queries. This unified framework is then used to perform image search requiring commonsense and factual reasoning. The retrieval performance of KRAMT is evaluated and compared with related approaches on a new dataset we introduce – namely COFAR.
%U https://aclanthology.org/2022.aacl-main.87
%P 1185-1199
Markdown (Informal)
[COFAR: Commonsense and Factual Reasoning in Image Search](https://aclanthology.org/2022.aacl-main.87) (Gatti et al., AACL-IJCNLP 2022)
ACL
- Prajwal Gatti, Abhirama Subramanyam Penamakuri, Revant Teotia, Anand Mishra, Shubhashis Sengupta, and Roshni Ramnani. 2022. COFAR: Commonsense and Factual Reasoning in Image Search. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1185–1199, Online only. Association for Computational Linguistics.