X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers Article Swipe

PDF

Jaemin Cho , Jiasen Lu , Dustin Schwenk , Hannaneh Hajishirzi , Aniruddha Kembhavi ·

YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.18653/v1/2020.emnlp-main.707

Mirroring the success of masked language models, vision-and-language counterparts like VILBERT, LXMERT and UNITER have achieved state of the art performance on a variety of multimodal discriminative tasks like visual question answering and visual grounding. Recent work has also successfully adapted such models towards the generative task of image captioning. This begs the question: Can these models go the other way and generate images from pieces of text? Our analysis of a popular representative from this model family – LXMERT – finds that it is unable to generate rich and semantically meaningful imagery with its current training setup. We introduce X-LXMERT, an extension to LXMERT with training refinements including: discretizing visual representations, using uniform masking with a large range of masking ratios and aligning the right pre-training datasets to the right objectives which enables it to paint. X-LXMERT’s image generation capabilities rival state of the art generative models while its question answering and captioning abilities remains comparable to LXMERT. Finally, we demonstrate the generality of these training refinements by adding image generation capabilities into UNITER to produce X-UNITER.

Related Topics

Computer Science

Artificial Intelligence

Concepts

Closed captioning Computer science Discriminative model Generality Question answering Artificial intelligence Generative grammar Generative model Modal Mirroring Natural language processing Transformer Image (mathematics) Psychology Quantum mechanics Physics Psychotherapist Chemistry Sociology Voltage Polymer chemistry Communication

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.18653/v1/2020.emnlp-main.707
PDF: https://www.aclweb.org/anthology/2020.emnlp-main.707.pdf
OA Status: gold
Cited By: 79
References: 94
Related Works: 10
OpenAlex ID: https://openalex.org/W3104152799

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W3104152799

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.18653/v1/2020.emnlp-main.707

Digital Object Identifier
Title: X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2020

Year of publication
Publication date: 2020-01-01

Full publication date if available
Authors: Jaemin Cho, Jiasen Lu, Dustin Schwenk, Hannaneh Hajishirzi, Aniruddha Kembhavi

List of authors in order
Landing page: https://doi.org/10.18653/v1/2020.emnlp-main.707

Publisher landing page
PDF URL: https://www.aclweb.org/anthology/2020.emnlp-main.707.pdf

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://www.aclweb.org/anthology/2020.emnlp-main.707.pdf

Direct OA link when available
Concepts: Closed captioning, Computer science, Discriminative model, Generality, Question answering, Artificial intelligence, Generative grammar, Generative model, Modal, Mirroring, Natural language processing, Transformer, Image (mathematics), Psychology, Quantum mechanics, Physics, Psychotherapist, Chemistry, Sociology, Voltage, Polymer chemistry, Communication

Top concepts (fields/topics) attached by OpenAlex
Cited by: 79

Total citation count in OpenAlex
Citations by year (recent): 2025: 8, 2024: 16, 2023: 21, 2022: 16, 2021: 18

Per-year citation counts (last 5 years)
References (count): 94

Number of works referenced by this work
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W3104152799
doi	https://doi.org/10.18653/v1/2020.emnlp-main.707
ids.doi	https://doi.org/10.18653/v1/2020.emnlp-main.707
ids.mag	3104152799
ids.openalex	https://openalex.org/W3104152799
fwci	5.77320248
type	article
title	X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
biblio.issue
biblio.volume
biblio.last_page	8805
biblio.first_page	8785
topics[0].id	https://openalex.org/T11714
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	1.0
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Multimodal Machine Learning Applications
topics[1].id	https://openalex.org/T11307
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9975000023841858
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Domain Adaptation and Few-Shot Learning
topics[2].id	https://openalex.org/T10028
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9970999956130981
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1702
topics[2].subfield.display_name	Artificial Intelligence
topics[2].display_name	Topic Modeling
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C157657479
concepts[0].level	3
concepts[0].score	0.8941240906715393
concepts[0].wikidata	https://www.wikidata.org/wiki/Q2367247
concepts[0].display_name	Closed captioning
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.8169131278991699
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C97931131
concepts[2].level	2
concepts[2].score	0.6484506726264954
concepts[2].wikidata	https://www.wikidata.org/wiki/Q5282087
concepts[2].display_name	Discriminative model
concepts[3].id	https://openalex.org/C2780767217
concepts[3].level	2
concepts[3].score	0.6284142732620239
concepts[3].wikidata	https://www.wikidata.org/wiki/Q5532421
concepts[3].display_name	Generality
concepts[4].id	https://openalex.org/C44291984
concepts[4].level	2
concepts[4].score	0.5565876364707947
concepts[4].wikidata	https://www.wikidata.org/wiki/Q1074173
concepts[4].display_name	Question answering
concepts[5].id	https://openalex.org/C154945302
concepts[5].level	1
concepts[5].score	0.546334445476532
concepts[5].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[5].display_name	Artificial intelligence
concepts[6].id	https://openalex.org/C39890363
concepts[6].level	2
concepts[6].score	0.5320390462875366
concepts[6].wikidata	https://www.wikidata.org/wiki/Q36108
concepts[6].display_name	Generative grammar
concepts[7].id	https://openalex.org/C167966045
concepts[7].level	3
concepts[7].score	0.531093955039978
concepts[7].wikidata	https://www.wikidata.org/wiki/Q5532625
concepts[7].display_name	Generative model
concepts[8].id	https://openalex.org/C71139939
concepts[8].level	2
concepts[8].score	0.5184635519981384
concepts[8].wikidata	https://www.wikidata.org/wiki/Q910194
concepts[8].display_name	Modal
concepts[9].id	https://openalex.org/C189645446
concepts[9].level	2
concepts[9].score	0.5054473876953125
concepts[9].wikidata	https://www.wikidata.org/wiki/Q350865
concepts[9].display_name	Mirroring
concepts[10].id	https://openalex.org/C204321447
concepts[10].level	1
concepts[10].score	0.49033308029174805
concepts[10].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[10].display_name	Natural language processing
concepts[11].id	https://openalex.org/C66322947
concepts[11].level	3
concepts[11].score	0.45259642601013184
concepts[11].wikidata	https://www.wikidata.org/wiki/Q11658
concepts[11].display_name	Transformer
concepts[12].id	https://openalex.org/C115961682
concepts[12].level	2
concepts[12].score	0.30973243713378906
concepts[12].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[12].display_name	Image (mathematics)
concepts[13].id	https://openalex.org/C15744967
concepts[13].level	0
concepts[13].score	0.0
concepts[13].wikidata	https://www.wikidata.org/wiki/Q9418
concepts[13].display_name	Psychology
concepts[14].id	https://openalex.org/C62520636
concepts[14].level	1
concepts[14].score	0.0
concepts[14].wikidata	https://www.wikidata.org/wiki/Q944
concepts[14].display_name	Quantum mechanics
concepts[15].id	https://openalex.org/C121332964
concepts[15].level	0
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q413
concepts[15].display_name	Physics
concepts[16].id	https://openalex.org/C542102704
concepts[16].level	1
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q183257
concepts[16].display_name	Psychotherapist
concepts[17].id	https://openalex.org/C185592680
concepts[17].level	0
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q2329
concepts[17].display_name	Chemistry
concepts[18].id	https://openalex.org/C144024400
concepts[18].level	0
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q21201
concepts[18].display_name	Sociology
concepts[19].id	https://openalex.org/C165801399
concepts[19].level	2
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q25428
concepts[19].display_name	Voltage
concepts[20].id	https://openalex.org/C188027245
concepts[20].level	1
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q750446
concepts[20].display_name	Polymer chemistry
concepts[21].id	https://openalex.org/C46312422
concepts[21].level	1
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q11024
concepts[21].display_name	Communication
keywords[0].id	https://openalex.org/keywords/closed-captioning
keywords[0].score	0.8941240906715393
keywords[0].display_name	Closed captioning
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.8169131278991699
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/discriminative-model
keywords[2].score	0.6484506726264954
keywords[2].display_name	Discriminative model
keywords[3].id	https://openalex.org/keywords/generality
keywords[3].score	0.6284142732620239
keywords[3].display_name	Generality
keywords[4].id	https://openalex.org/keywords/question-answering
keywords[4].score	0.5565876364707947
keywords[4].display_name	Question answering
keywords[5].id	https://openalex.org/keywords/artificial-intelligence
keywords[5].score	0.546334445476532
keywords[5].display_name	Artificial intelligence
keywords[6].id	https://openalex.org/keywords/generative-grammar
keywords[6].score	0.5320390462875366
keywords[6].display_name	Generative grammar
keywords[7].id	https://openalex.org/keywords/generative-model
keywords[7].score	0.531093955039978
keywords[7].display_name	Generative model
keywords[8].id	https://openalex.org/keywords/modal
keywords[8].score	0.5184635519981384
keywords[8].display_name	Modal
keywords[9].id	https://openalex.org/keywords/mirroring
keywords[9].score	0.5054473876953125
keywords[9].display_name	Mirroring
keywords[10].id	https://openalex.org/keywords/natural-language-processing
keywords[10].score	0.49033308029174805
keywords[10].display_name	Natural language processing
keywords[11].id	https://openalex.org/keywords/transformer
keywords[11].score	0.45259642601013184
keywords[11].display_name	Transformer
keywords[12].id	https://openalex.org/keywords/image
keywords[12].score	0.30973243713378906
keywords[12].display_name	Image (mathematics)
language	en
locations[0].id	doi:10.18653/v1/2020.emnlp-main.707
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by
locations[0].pdf_url	https://www.aclweb.org/anthology/2020.emnlp-main.707.pdf
locations[0].version	publishedVersion
locations[0].raw_type	proceedings-article
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
locations[0].landing_page_url	https://doi.org/10.18653/v1/2020.emnlp-main.707
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5101760065
authorships[0].author.orcid	https://orcid.org/0000-0003-1148-5413
authorships[0].author.display_name	Jaemin Cho
authorships[0].countries	US
authorships[0].affiliations[0].institution_ids	https://openalex.org/I201448701
authorships[0].affiliations[0].raw_affiliation_string	University of Washington
authorships[0].affiliations[1].institution_ids	https://openalex.org/I114027177, https://openalex.org/I1333535994
authorships[0].affiliations[1].raw_affiliation_string	UNC Chapel Hill
authorships[0].institutions[0].id	https://openalex.org/I1333535994
authorships[0].institutions[0].ror	https://ror.org/00qz24g20
authorships[0].institutions[0].type	healthcare
authorships[0].institutions[0].lineage	https://openalex.org/I1333535994
authorships[0].institutions[0].country_code	US
authorships[0].institutions[0].display_name	University of North Carolina Health Care
authorships[0].institutions[1].id	https://openalex.org/I114027177
authorships[0].institutions[1].ror	https://ror.org/0130frc33
authorships[0].institutions[1].type	education
authorships[0].institutions[1].lineage	https://openalex.org/I114027177
authorships[0].institutions[1].country_code	US
authorships[0].institutions[1].display_name	University of North Carolina at Chapel Hill
authorships[0].institutions[2].id	https://openalex.org/I201448701
authorships[0].institutions[2].ror	https://ror.org/00cvxb145
authorships[0].institutions[2].type	education
authorships[0].institutions[2].lineage	https://openalex.org/I201448701
authorships[0].institutions[2].country_code	US
authorships[0].institutions[2].display_name	University of Washington
authorships[0].author_position	first
authorships[0].raw_author_name	Jaemin Cho
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	UNC Chapel Hill, University of Washington
authorships[1].author.id	https://openalex.org/A5101055775
authorships[1].author.orcid
authorships[1].author.display_name	Jiasen Lu
authorships[1].countries	US
authorships[1].affiliations[0].institution_ids	https://openalex.org/I114027177, https://openalex.org/I1333535994
authorships[1].affiliations[0].raw_affiliation_string	UNC Chapel Hill
authorships[1].institutions[0].id	https://openalex.org/I1333535994
authorships[1].institutions[0].ror	https://ror.org/00qz24g20
authorships[1].institutions[0].type	healthcare
authorships[1].institutions[0].lineage	https://openalex.org/I1333535994
authorships[1].institutions[0].country_code	US
authorships[1].institutions[0].display_name	University of North Carolina Health Care
authorships[1].institutions[1].id	https://openalex.org/I114027177
authorships[1].institutions[1].ror	https://ror.org/0130frc33
authorships[1].institutions[1].type	education
authorships[1].institutions[1].lineage	https://openalex.org/I114027177
authorships[1].institutions[1].country_code	US
authorships[1].institutions[1].display_name	University of North Carolina at Chapel Hill
authorships[1].author_position	middle
authorships[1].raw_author_name	Jiasen Lu
authorships[1].is_corresponding	False
authorships[1].raw_affiliation_strings	UNC Chapel Hill
authorships[2].author.id	https://openalex.org/A5007645100
authorships[2].author.orcid	https://orcid.org/0000-0003-1666-6889
authorships[2].author.display_name	Dustin Schwenk
authorships[2].countries	US
authorships[2].affiliations[0].institution_ids	https://openalex.org/I114027177, https://openalex.org/I1333535994
authorships[2].affiliations[0].raw_affiliation_string	UNC Chapel Hill
authorships[2].institutions[0].id	https://openalex.org/I1333535994
authorships[2].institutions[0].ror	https://ror.org/00qz24g20
authorships[2].institutions[0].type	healthcare
authorships[2].institutions[0].lineage	https://openalex.org/I1333535994
authorships[2].institutions[0].country_code	US
authorships[2].institutions[0].display_name	University of North Carolina Health Care
authorships[2].institutions[1].id	https://openalex.org/I114027177
authorships[2].institutions[1].ror	https://ror.org/0130frc33
authorships[2].institutions[1].type	education
authorships[2].institutions[1].lineage	https://openalex.org/I114027177
authorships[2].institutions[1].country_code	US
authorships[2].institutions[1].display_name	University of North Carolina at Chapel Hill
authorships[2].author_position	middle
authorships[2].raw_author_name	Dustin Schwenk
authorships[2].is_corresponding	False
authorships[2].raw_affiliation_strings	UNC Chapel Hill
authorships[3].author.id	https://openalex.org/A5082305994
authorships[3].author.orcid	https://orcid.org/0000-0002-1055-6657
authorships[3].author.display_name	Hannaneh Hajishirzi
authorships[3].countries	US
authorships[3].affiliations[0].institution_ids	https://openalex.org/I114027177, https://openalex.org/I1333535994
authorships[3].affiliations[0].raw_affiliation_string	UNC Chapel Hill
authorships[3].institutions[0].id	https://openalex.org/I1333535994
authorships[3].institutions[0].ror	https://ror.org/00qz24g20
authorships[3].institutions[0].type	healthcare
authorships[3].institutions[0].lineage	https://openalex.org/I1333535994
authorships[3].institutions[0].country_code	US
authorships[3].institutions[0].display_name	University of North Carolina Health Care
authorships[3].institutions[1].id	https://openalex.org/I114027177
authorships[3].institutions[1].ror	https://ror.org/0130frc33
authorships[3].institutions[1].type	education
authorships[3].institutions[1].lineage	https://openalex.org/I114027177
authorships[3].institutions[1].country_code	US
authorships[3].institutions[1].display_name	University of North Carolina at Chapel Hill
authorships[3].author_position	middle
authorships[3].raw_author_name	Hannaneh Hajishirzi
authorships[3].is_corresponding	False
authorships[3].raw_affiliation_strings	UNC Chapel Hill
authorships[4].author.id	https://openalex.org/A5018421415
authorships[4].author.orcid	https://orcid.org/0000-0002-7608-7443
authorships[4].author.display_name	Aniruddha Kembhavi
authorships[4].countries	US
authorships[4].affiliations[0].institution_ids	https://openalex.org/I114027177, https://openalex.org/I1333535994
authorships[4].affiliations[0].raw_affiliation_string	UNC Chapel Hill
authorships[4].institutions[0].id	https://openalex.org/I1333535994
authorships[4].institutions[0].ror	https://ror.org/00qz24g20
authorships[4].institutions[0].type	healthcare
authorships[4].institutions[0].lineage	https://openalex.org/I1333535994
authorships[4].institutions[0].country_code	US
authorships[4].institutions[0].display_name	University of North Carolina Health Care
authorships[4].institutions[1].id	https://openalex.org/I114027177
authorships[4].institutions[1].ror	https://ror.org/0130frc33
authorships[4].institutions[1].type	education
authorships[4].institutions[1].lineage	https://openalex.org/I114027177
authorships[4].institutions[1].country_code	US
authorships[4].institutions[1].display_name	University of North Carolina at Chapel Hill
authorships[4].author_position	last
authorships[4].raw_author_name	Aniruddha Kembhavi
authorships[4].is_corresponding	False
authorships[4].raw_affiliation_strings	UNC Chapel Hill
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://www.aclweb.org/anthology/2020.emnlp-main.707.pdf
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T11714
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	1.0
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Multimodal Machine Learning Applications
related_works	https://openalex.org/W2081134829, https://openalex.org/W2012196799, https://openalex.org/W2914953798, https://openalex.org/W2016936103, https://openalex.org/W4210416330, https://openalex.org/W1969752774, https://openalex.org/W2551163313, https://openalex.org/W2294049764, https://openalex.org/W2108584188, https://openalex.org/W1980969160
cited_by_count	79
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	8
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	16
counts_by_year[2].year	2023
counts_by_year[2].cited_by_count	21
counts_by_year[3].year	2022
counts_by_year[3].cited_by_count	16
counts_by_year[4].year	2021
counts_by_year[4].cited_by_count	18
locations_count	1
best_oa_location.id	doi:10.18653/v1/2020.emnlp-main.707
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://www.aclweb.org/anthology/2020.emnlp-main.707.pdf
best_oa_location.version	publishedVersion
best_oa_location.raw_type	proceedings-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
best_oa_location.landing_page_url	https://doi.org/10.18653/v1/2020.emnlp-main.707
primary_location.id	doi:10.18653/v1/2020.emnlp-main.707
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by
primary_location.pdf_url	https://www.aclweb.org/anthology/2020.emnlp-main.707.pdf
primary_location.version	publishedVersion
primary_location.raw_type	proceedings-article
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
primary_location.landing_page_url	https://doi.org/10.18653/v1/2020.emnlp-main.707
publication_date	2020-01-01
publication_year	2020
referenced_works	https://openalex.org/W2964216930, https://openalex.org/W2950776302, https://openalex.org/W2962754210, https://openalex.org/W4298289240, https://openalex.org/W2962974533, https://openalex.org/W3035574324, https://openalex.org/W4297730426, https://openalex.org/W2502312327, https://openalex.org/W3034727271, https://openalex.org/W2899771611, https://openalex.org/W2970869018, https://openalex.org/W4385245566, https://openalex.org/W4226348722, https://openalex.org/W2971074500, https://openalex.org/W3037695135, https://openalex.org/W2972328244, https://openalex.org/W3100427071, https://openalex.org/W2405756170, https://openalex.org/W2913129712, https://openalex.org/W2908510526, https://openalex.org/W2277195237, https://openalex.org/W4297606427, https://openalex.org/W2963518342, https://openalex.org/W2969876226, https://openalex.org/W2945260553, https://openalex.org/W2964121744, https://openalex.org/W3034878914, https://openalex.org/W3016211260, https://openalex.org/W2948433173, https://openalex.org/W2321533354, https://openalex.org/W2896457183, https://openalex.org/W2963981733, https://openalex.org/W2507319105, https://openalex.org/W2183341477, https://openalex.org/W2963836885, https://openalex.org/W2980282514, https://openalex.org/W2331128040, https://openalex.org/W2150333870, https://openalex.org/W3113747735, https://openalex.org/W2970608575, https://openalex.org/W2963403868, https://openalex.org/W2548275288, https://openalex.org/W2944828972, https://openalex.org/W2963163163, https://openalex.org/W2963373786, https://openalex.org/W4299585995, https://openalex.org/W2963341956, https://openalex.org/W2963530300, https://openalex.org/W4297808394, https://openalex.org/W3014611590, https://openalex.org/W2194775991, https://openalex.org/W3035497460, https://openalex.org/W2970127127, https://openalex.org/W2267126114, https://openalex.org/W2975501350, https://openalex.org/W2981721547, https://openalex.org/W2971274815, https://openalex.org/W2979672901, https://openalex.org/W2970231061, https://openalex.org/W2785678896, https://openalex.org/W2964024144, https://openalex.org/W2603777577, https://openalex.org/W2557449848, https://openalex.org/W3023745006, https://openalex.org/W2962770929, https://openalex.org/W2981851019, https://openalex.org/W2613718673, https://openalex.org/W2963800363, https://openalex.org/W2963966654, https://openalex.org/W2842511635, https://openalex.org/W3007759824, https://openalex.org/W2947898088, https://openalex.org/W2966715458, https://openalex.org/W4296979096, https://openalex.org/W2953318193, https://openalex.org/W2899663614, https://openalex.org/W3148140980, https://openalex.org/W2525778437, https://openalex.org/W1861492603, https://openalex.org/W2962749469, https://openalex.org/W3018265077, https://openalex.org/W2969035964, https://openalex.org/W2997591391, https://openalex.org/W2966792645, https://openalex.org/W2108598243, https://openalex.org/W2988975212, https://openalex.org/W2998356391, https://openalex.org/W3001555892, https://openalex.org/W2963799213, https://openalex.org/W639708223, https://openalex.org/W2787579267, https://openalex.org/W2998702515, https://openalex.org/W4301206121, https://openalex.org/W3088059392
referenced_works_count	94
abstract_inverted_index.a	22, 71, 116
abstract_inverted_index.We	98
abstract_inverted_index.an	101
abstract_inverted_index.by	168
abstract_inverted_index.go	57
abstract_inverted_index.is	84
abstract_inverted_index.it	83, 134
abstract_inverted_index.of	3, 17, 24, 47, 66, 70, 119, 143, 164
abstract_inverted_index.on	21
abstract_inverted_index.to	86, 103, 128, 135, 157, 175
abstract_inverted_index.we	160
abstract_inverted_index.Can	54
abstract_inverted_index.Our	68
abstract_inverted_index.and	12, 32, 61, 89, 122, 152
abstract_inverted_index.art	19, 145
abstract_inverted_index.has	37
abstract_inverted_index.its	94, 149
abstract_inverted_index.the	1, 18, 44, 52, 58, 124, 129, 144, 162
abstract_inverted_index.way	60
abstract_inverted_index.–	78, 80
abstract_inverted_index.This	50
abstract_inverted_index.also	38
abstract_inverted_index.begs	51
abstract_inverted_index.from	64, 74
abstract_inverted_index.have	14
abstract_inverted_index.into	173
abstract_inverted_index.like	9, 28
abstract_inverted_index.rich	88
abstract_inverted_index.such	41
abstract_inverted_index.task	46
abstract_inverted_index.that	82
abstract_inverted_index.this	75
abstract_inverted_index.with	93, 105, 115
abstract_inverted_index.work	36
abstract_inverted_index.finds	81
abstract_inverted_index.image	48, 138, 170
abstract_inverted_index.large	117
abstract_inverted_index.model	76
abstract_inverted_index.other	59
abstract_inverted_index.range	118
abstract_inverted_index.right	125, 130
abstract_inverted_index.rival	141
abstract_inverted_index.state	16, 142
abstract_inverted_index.tasks	27
abstract_inverted_index.text?	67
abstract_inverted_index.these	55, 165
abstract_inverted_index.using	112
abstract_inverted_index.which	132
abstract_inverted_index.while	148
abstract_inverted_index.LXMERT	11, 79, 104
abstract_inverted_index.Recent	35
abstract_inverted_index.UNITER	13, 174
abstract_inverted_index.adding	169
abstract_inverted_index.family	77
abstract_inverted_index.images	63
abstract_inverted_index.masked	4
abstract_inverted_index.models	42, 56, 147
abstract_inverted_index.paint.	136
abstract_inverted_index.pieces	65
abstract_inverted_index.ratios	121
abstract_inverted_index.setup.	97
abstract_inverted_index.unable	85
abstract_inverted_index.visual	29, 33, 110
abstract_inverted_index.LXMERT.	158
abstract_inverted_index.adapted	40
abstract_inverted_index.current	95
abstract_inverted_index.enables	133
abstract_inverted_index.imagery	92
abstract_inverted_index.masking	114, 120
abstract_inverted_index.models,	6
abstract_inverted_index.popular	72
abstract_inverted_index.produce	176
abstract_inverted_index.remains	155
abstract_inverted_index.success	2
abstract_inverted_index.towards	43
abstract_inverted_index.uniform	113
abstract_inverted_index.variety	23
abstract_inverted_index.Finally,	159
abstract_inverted_index.VILBERT,	10
abstract_inverted_index.achieved	15
abstract_inverted_index.aligning	123
abstract_inverted_index.analysis	69
abstract_inverted_index.datasets	127
abstract_inverted_index.generate	62, 87
abstract_inverted_index.language	5
abstract_inverted_index.question	30, 150
abstract_inverted_index.training	96, 106, 166
abstract_inverted_index.Mirroring	0
abstract_inverted_index.X-LXMERT,	100
abstract_inverted_index.X-UNITER.	177
abstract_inverted_index.abilities	154
abstract_inverted_index.answering	31, 151
abstract_inverted_index.extension	102
abstract_inverted_index.introduce	99
abstract_inverted_index.question:	53
abstract_inverted_index.captioning	153
abstract_inverted_index.comparable	156
abstract_inverted_index.generality	163
abstract_inverted_index.generation	139, 171
abstract_inverted_index.generative	45, 146
abstract_inverted_index.grounding.	34
abstract_inverted_index.including:	108
abstract_inverted_index.meaningful	91
abstract_inverted_index.multimodal	25
abstract_inverted_index.objectives	131
abstract_inverted_index.captioning.	49
abstract_inverted_index.demonstrate	161
abstract_inverted_index.performance	20
abstract_inverted_index.refinements	107, 167
abstract_inverted_index.X-LXMERT’s	137
abstract_inverted_index.capabilities	140, 172
abstract_inverted_index.counterparts	8
abstract_inverted_index.discretizing	109
abstract_inverted_index.pre-training	126
abstract_inverted_index.semantically	90
abstract_inverted_index.successfully	39
abstract_inverted_index.discriminative	26
abstract_inverted_index.representative	73
abstract_inverted_index.representations,	111
abstract_inverted_index.vision-and-language	7
cited_by_percentile_year.max	100
cited_by_percentile_year.min	99
countries_distinct_count	1
institutions_distinct_count	5
sustainable_development_goals[0].id	https://metadata.un.org/sdg/10
sustainable_development_goals[0].score	0.7799999713897705
sustainable_development_goals[0].display_name	Reduced inequalities
citation_normalized_percentile.value	0.96861101
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	True