Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding Article Swipe

PDF

Kenton Lee , Mandar Joshi , Iulia Turc , Hexiang Hu , Fangyu Liu , Julian Martin Eisenschlos , Urvashi Khandelwal , Peter J. Shaw , Ming‐Wei Chang , Kristina Toutanova ·

YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2210.03347

Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms. Perhaps due to this diversity, previous work has typically relied on domain-specific recipes with limited sharing of the underlying data, model architectures, and objectives. We present Pix2Struct, a pretrained image-to-text model for purely visual language understanding, which can be finetuned on tasks containing visually-situated language. Pix2Struct is pretrained by learning to parse masked screenshots of web pages into simplified HTML. The web, with its richness of visual elements cleanly reflected in the HTML structure, provides a large source of pretraining data well suited to the diversity of downstream tasks. Intuitively, this objective subsumes common pretraining signals such as OCR, language modeling, image captioning. In addition to the novel pretraining strategy, we introduce a variable-resolution input representation and a more flexible integration of language and vision inputs, where language prompts such as questions are rendered directly on top of the input image. For the first time, we show that a single pretrained model can achieve state-of-the-art results in six out of nine tasks across four domains: documents, illustrations, user interfaces, and natural images.

Related Topics

Computer Science

Artificial Intelligence

Human–Computer Interaction

Mathematics

Law

Politics

Mathematical Analysis

Concepts

Computer science Parsing Closed captioning Natural language processing Artificial intelligence Natural language Situated Domain (mathematical analysis) Language model Representation (politics) Human–computer interaction Image (mathematics) Mathematics Law Political science Politics Mathematical analysis

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2210.03347
PDF: https://arxiv.org/pdf/2210.03347
OA Status: green
Cited By: 45
Related Works: 10
OpenAlex ID: https://openalex.org/W4304192731

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4304192731

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2210.03347

Digital Object Identifier
Title: Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2022

Year of publication
Publication date: 2022-10-07

Full publication date if available
Authors: Kenton Lee, Mandar Joshi, Iulia Turc, Hexiang Hu, Fangyu Liu, Julian Martin Eisenschlos, Urvashi Khandelwal, Peter J. Shaw, Ming‐Wei Chang, Kristina Toutanova

List of authors in order
Landing page: https://arxiv.org/abs/2210.03347

Publisher landing page
PDF URL: https://arxiv.org/pdf/2210.03347

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2210.03347

Direct OA link when available
Concepts: Computer science, Parsing, Closed captioning, Natural language processing, Artificial intelligence, Natural language, Situated, Domain (mathematical analysis), Language model, Representation (politics), Human–computer interaction, Image (mathematics), Mathematics, Law, Political science, Politics, Mathematical analysis

Top concepts (fields/topics) attached by OpenAlex
Cited by: 45

Total citation count in OpenAlex
Citations by year (recent): 2025: 5, 2024: 22, 2023: 18

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4304192731
doi	https://doi.org/10.48550/arxiv.2210.03347
ids.doi	https://doi.org/10.48550/arxiv.2210.03347
ids.openalex	https://openalex.org/W4304192731
fwci
type	preprint
title	Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
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	0.9998000264167786
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/T10181
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9878000020980835
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	Natural Language Processing Techniques
topics[2].id	https://openalex.org/T10627
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9732000231742859
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1707
topics[2].subfield.display_name	Computer Vision and Pattern Recognition
topics[2].display_name	Advanced Image and Video Retrieval Techniques
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.8644065260887146
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C186644900
concepts[1].level	2
concepts[1].score	0.7467710971832275
concepts[1].wikidata	https://www.wikidata.org/wiki/Q194152
concepts[1].display_name	Parsing
concepts[2].id	https://openalex.org/C157657479
concepts[2].level	3
concepts[2].score	0.685272753238678
concepts[2].wikidata	https://www.wikidata.org/wiki/Q2367247
concepts[2].display_name	Closed captioning
concepts[3].id	https://openalex.org/C204321447
concepts[3].level	1
concepts[3].score	0.5966121554374695
concepts[3].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[3].display_name	Natural language processing
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.5181930661201477
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C195324797
concepts[5].level	2
concepts[5].score	0.500176191329956
concepts[5].wikidata	https://www.wikidata.org/wiki/Q33742
concepts[5].display_name	Natural language
concepts[6].id	https://openalex.org/C132829578
concepts[6].level	2
concepts[6].score	0.4910585880279541
concepts[6].wikidata	https://www.wikidata.org/wiki/Q581151
concepts[6].display_name	Situated
concepts[7].id	https://openalex.org/C36503486
concepts[7].level	2
concepts[7].score	0.4809402823448181
concepts[7].wikidata	https://www.wikidata.org/wiki/Q11235244
concepts[7].display_name	Domain (mathematical analysis)
concepts[8].id	https://openalex.org/C137293760
concepts[8].level	2
concepts[8].score	0.47828564047813416
concepts[8].wikidata	https://www.wikidata.org/wiki/Q3621696
concepts[8].display_name	Language model
concepts[9].id	https://openalex.org/C2776359362
concepts[9].level	3
concepts[9].score	0.43287044763565063
concepts[9].wikidata	https://www.wikidata.org/wiki/Q2145286
concepts[9].display_name	Representation (politics)
concepts[10].id	https://openalex.org/C107457646
concepts[10].level	1
concepts[10].score	0.3254523277282715
concepts[10].wikidata	https://www.wikidata.org/wiki/Q207434
concepts[10].display_name	Human–computer interaction
concepts[11].id	https://openalex.org/C115961682
concepts[11].level	2
concepts[11].score	0.2771185040473938
concepts[11].wikidata	https://www.wikidata.org/wiki/Q860623
concepts[11].display_name	Image (mathematics)
concepts[12].id	https://openalex.org/C33923547
concepts[12].level	0
concepts[12].score	0.0
concepts[12].wikidata	https://www.wikidata.org/wiki/Q395
concepts[12].display_name	Mathematics
concepts[13].id	https://openalex.org/C199539241
concepts[13].level	1
concepts[13].score	0.0
concepts[13].wikidata	https://www.wikidata.org/wiki/Q7748
concepts[13].display_name	Law
concepts[14].id	https://openalex.org/C17744445
concepts[14].level	0
concepts[14].score	0.0
concepts[14].wikidata	https://www.wikidata.org/wiki/Q36442
concepts[14].display_name	Political science
concepts[15].id	https://openalex.org/C94625758
concepts[15].level	2
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q7163
concepts[15].display_name	Politics
concepts[16].id	https://openalex.org/C134306372
concepts[16].level	1
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q7754
concepts[16].display_name	Mathematical analysis
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.8644065260887146
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/parsing
keywords[1].score	0.7467710971832275
keywords[1].display_name	Parsing
keywords[2].id	https://openalex.org/keywords/closed-captioning
keywords[2].score	0.685272753238678
keywords[2].display_name	Closed captioning
keywords[3].id	https://openalex.org/keywords/natural-language-processing
keywords[3].score	0.5966121554374695
keywords[3].display_name	Natural language processing
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.5181930661201477
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/natural-language
keywords[5].score	0.500176191329956
keywords[5].display_name	Natural language
keywords[6].id	https://openalex.org/keywords/situated
keywords[6].score	0.4910585880279541
keywords[6].display_name	Situated
keywords[7].id	https://openalex.org/keywords/domain
keywords[7].score	0.4809402823448181
keywords[7].display_name	Domain (mathematical analysis)
keywords[8].id	https://openalex.org/keywords/language-model
keywords[8].score	0.47828564047813416
keywords[8].display_name	Language model
keywords[9].id	https://openalex.org/keywords/representation
keywords[9].score	0.43287044763565063
keywords[9].display_name	Representation (politics)
keywords[10].id	https://openalex.org/keywords/human–computer-interaction
keywords[10].score	0.3254523277282715
keywords[10].display_name	Human–computer interaction
keywords[11].id	https://openalex.org/keywords/image
keywords[11].score	0.2771185040473938
keywords[11].display_name	Image (mathematics)
language	en
locations[0].id	pmh:oai:arXiv.org:2210.03347
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2210.03347
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2210.03347
locations[1].id	doi:10.48550/arxiv.2210.03347
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2210.03347
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5081862885
authorships[0].author.orcid	https://orcid.org/0000-0002-9534-5970
authorships[0].author.display_name	Kenton Lee
authorships[0].author_position	first
authorships[0].raw_author_name	Lee, Kenton
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5108202364
authorships[1].author.orcid
authorships[1].author.display_name	Mandar Joshi
authorships[1].author_position	middle
authorships[1].raw_author_name	Joshi, Mandar
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5086294822
authorships[2].author.orcid
authorships[2].author.display_name	Iulia Turc
authorships[2].author_position	middle
authorships[2].raw_author_name	Turc, Iulia
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5065708799
authorships[3].author.orcid	https://orcid.org/0000-0002-4720-169X
authorships[3].author.display_name	Hexiang Hu
authorships[3].author_position	middle
authorships[3].raw_author_name	Hu, Hexiang
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5026154387
authorships[4].author.orcid	https://orcid.org/0000-0001-7038-3623
authorships[4].author.display_name	Fangyu Liu
authorships[4].author_position	middle
authorships[4].raw_author_name	Liu, Fangyu
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5000738730
authorships[5].author.orcid
authorships[5].author.display_name	Julian Martin Eisenschlos
authorships[5].author_position	middle
authorships[5].raw_author_name	Eisenschlos, Julian
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5088072227
authorships[6].author.orcid
authorships[6].author.display_name	Urvashi Khandelwal
authorships[6].author_position	middle
authorships[6].raw_author_name	Khandelwal, Urvashi
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5061827062
authorships[7].author.orcid	https://orcid.org/0000-0003-0101-4482
authorships[7].author.display_name	Peter J. Shaw
authorships[7].author_position	middle
authorships[7].raw_author_name	Shaw, Peter
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5076904467
authorships[8].author.orcid	https://orcid.org/0000-0002-0137-8895
authorships[8].author.display_name	Ming‐Wei Chang
authorships[8].author_position	middle
authorships[8].raw_author_name	Chang, Ming-Wei
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5053947885
authorships[9].author.orcid
authorships[9].author.display_name	Kristina Toutanova
authorships[9].author_position	last
authorships[9].raw_author_name	Toutanova, Kristina
authorships[9].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2210.03347
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
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	0.9998000264167786
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/W4210416330, https://openalex.org/W2775506363, https://openalex.org/W3088136942, https://openalex.org/W4290852288, https://openalex.org/W2949362007, https://openalex.org/W4386271066, https://openalex.org/W3009270862, https://openalex.org/W2066060456, https://openalex.org/W2293063786, https://openalex.org/W2911292476
cited_by_count	45
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	5
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	22
counts_by_year[2].year	2023
counts_by_year[2].cited_by_count	18
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2210.03347
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2210.03347
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2210.03347
primary_location.id	pmh:oai:arXiv.org:2210.03347
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2210.03347
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2210.03347
publication_date	2022-10-07
publication_year	2022
referenced_works_count	0
abstract_inverted_index.a	52, 100, 137, 142, 173
abstract_inverted_index.--	4
abstract_inverted_index.In	128
abstract_inverted_index.We	49
abstract_inverted_index.as	122, 155
abstract_inverted_index.be	63
abstract_inverted_index.by	73
abstract_inverted_index.in	95, 181
abstract_inverted_index.is	2, 71
abstract_inverted_index.of	41, 79, 90, 103, 111, 146, 162, 184
abstract_inverted_index.on	35, 65, 160
abstract_inverted_index.to	11, 18, 27, 75, 108, 130
abstract_inverted_index.we	135, 170
abstract_inverted_index.For	166
abstract_inverted_index.The	85
abstract_inverted_index.and	16, 23, 47, 141, 148, 194
abstract_inverted_index.are	157
abstract_inverted_index.can	62, 177
abstract_inverted_index.due	26
abstract_inverted_index.for	56
abstract_inverted_index.has	32
abstract_inverted_index.its	88
abstract_inverted_index.out	183
abstract_inverted_index.six	182
abstract_inverted_index.the	42, 96, 109, 131, 163, 167
abstract_inverted_index.top	161
abstract_inverted_index.web	12, 80
abstract_inverted_index.HTML	97
abstract_inverted_index.OCR,	123
abstract_inverted_index.apps	20
abstract_inverted_index.data	105
abstract_inverted_index.four	188
abstract_inverted_index.from	7
abstract_inverted_index.into	82
abstract_inverted_index.more	143
abstract_inverted_index.nine	185
abstract_inverted_index.show	171
abstract_inverted_index.such	121, 154
abstract_inverted_index.that	172
abstract_inverted_index.this	28, 115
abstract_inverted_index.user	192
abstract_inverted_index.web,	86
abstract_inverted_index.well	106
abstract_inverted_index.with	9, 14, 21, 38, 87
abstract_inverted_index.work	31
abstract_inverted_index.HTML.	84
abstract_inverted_index.data,	44
abstract_inverted_index.first	168
abstract_inverted_index.image	126
abstract_inverted_index.input	139, 164
abstract_inverted_index.large	101
abstract_inverted_index.model	45, 55, 176
abstract_inverted_index.novel	132
abstract_inverted_index.pages	13, 81
abstract_inverted_index.parse	76
abstract_inverted_index.range	6
abstract_inverted_index.tasks	66, 186
abstract_inverted_index.time,	169
abstract_inverted_index.where	151
abstract_inverted_index.which	61
abstract_inverted_index.across	187
abstract_inverted_index.common	118
abstract_inverted_index.forms.	24
abstract_inverted_index.image.	165
abstract_inverted_index.images	15
abstract_inverted_index.masked	77
abstract_inverted_index.mobile	19
abstract_inverted_index.purely	57
abstract_inverted_index.relied	34
abstract_inverted_index.single	174
abstract_inverted_index.source	102
abstract_inverted_index.suited	107
abstract_inverted_index.tasks.	113
abstract_inverted_index.vision	149
abstract_inverted_index.visual	58, 91
abstract_inverted_index.Perhaps	25
abstract_inverted_index.achieve	178
abstract_inverted_index.buttons	22
abstract_inverted_index.cleanly	93
abstract_inverted_index.images.	196
abstract_inverted_index.inputs,	150
abstract_inverted_index.limited	39
abstract_inverted_index.natural	195
abstract_inverted_index.present	50
abstract_inverted_index.prompts	153
abstract_inverted_index.recipes	37
abstract_inverted_index.results	180
abstract_inverted_index.sharing	40
abstract_inverted_index.signals	120
abstract_inverted_index.sources	5
abstract_inverted_index.tables,	17
abstract_inverted_index.addition	129
abstract_inverted_index.diagrams	10
abstract_inverted_index.directly	159
abstract_inverted_index.domains:	189
abstract_inverted_index.elements	92
abstract_inverted_index.flexible	144
abstract_inverted_index.language	1, 59, 124, 147, 152
abstract_inverted_index.learning	74
abstract_inverted_index.previous	30
abstract_inverted_index.provides	99
abstract_inverted_index.rendered	158
abstract_inverted_index.richness	89
abstract_inverted_index.subsumes	117
abstract_inverted_index.diversity	110
abstract_inverted_index.finetuned	64
abstract_inverted_index.introduce	136
abstract_inverted_index.language.	69
abstract_inverted_index.modeling,	125
abstract_inverted_index.objective	116
abstract_inverted_index.questions	156
abstract_inverted_index.reflected	94
abstract_inverted_index.strategy,	134
abstract_inverted_index.textbooks	8
abstract_inverted_index.typically	33
abstract_inverted_index.Pix2Struct	70
abstract_inverted_index.containing	67
abstract_inverted_index.diversity,	29
abstract_inverted_index.documents,	190
abstract_inverted_index.downstream	112
abstract_inverted_index.pretrained	53, 72, 175
abstract_inverted_index.simplified	83
abstract_inverted_index.structure,	98
abstract_inverted_index.ubiquitous	3
abstract_inverted_index.underlying	43
abstract_inverted_index.Pix2Struct,	51
abstract_inverted_index.captioning.	127
abstract_inverted_index.integration	145
abstract_inverted_index.interfaces,	193
abstract_inverted_index.objectives.	48
abstract_inverted_index.pretraining	104, 119, 133
abstract_inverted_index.screenshots	78
abstract_inverted_index.Intuitively,	114
abstract_inverted_index.image-to-text	54
abstract_inverted_index.architectures,	46
abstract_inverted_index.illustrations,	191
abstract_inverted_index.representation	140
abstract_inverted_index.understanding,	60
abstract_inverted_index.domain-specific	36
abstract_inverted_index.state-of-the-art	179
abstract_inverted_index.Visually-situated	0
abstract_inverted_index.visually-situated	68
abstract_inverted_index.variable-resolution	138
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	10
sustainable_development_goals[0].id	https://metadata.un.org/sdg/4
sustainable_development_goals[0].score	0.8100000023841858
sustainable_development_goals[0].display_name	Quality Education
citation_normalized_percentile