Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason? Article Swipe

PDF

Monika Wysoczańska , Tom Monnier , T. P. Trzcinski , David Picard ·

YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2212.10292

Recent advances in visual representation learning allowed to build an abundance of powerful off-the-shelf features that are ready-to-use for numerous downstream tasks. This work aims to assess how well these features preserve information about the objects, such as their spatial location, their visual properties and their relative relationships. We propose to do so by evaluating them in the context of visual reasoning, where multiple objects with complex relationships and different attributes are at play. More specifically, we introduce a protocol to evaluate visual representations for the task of Visual Question Answering. In order to decouple visual feature extraction from reasoning, we design a specific attention-based reasoning module which is trained on the frozen visual representations to be evaluated, in a spirit similar to standard feature evaluations relying on shallow networks. We compare two types of visual representations, densely extracted local features and object-centric ones, against the performances of a perfect image representation using ground truth. Our main findings are two-fold. First, despite excellent performances on classical proxy tasks, such representations fall short for solving complex reasoning problem. Second, object-centric features better preserve the critical information necessary to perform visual reasoning. In our proposed framework we show how to methodologically approach this evaluation.

Related Topics

Computer Science

Artificial Intelligence

Visualization (Graphics)

Concepts

Computer science Visual reasoning Artificial intelligence Representation (politics) Context (archaeology) Object (grammar) Cognitive neuroscience of visual object recognition Spatial intelligence Visualization Task (project management) Feature (linguistics) Visual Objects Analytic reasoning Machine learning Natural language processing Reasoning system Perception Psychology Philosophy Biology Political science Law Management Linguistics Neuroscience Politics Economics Paleontology

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2212.10292
PDF: https://arxiv.org/pdf/2212.10292
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4312091344

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4312091344

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2212.10292

Digital Object Identifier
Title: Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2022

Year of publication
Publication date: 2022-12-20

Full publication date if available
Authors: Monika Wysoczańska, Tom Monnier, T. P. Trzcinski, David Picard

List of authors in order
Landing page: https://arxiv.org/abs/2212.10292

Publisher landing page
PDF URL: https://arxiv.org/pdf/2212.10292

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/2212.10292

Direct OA link when available
Concepts: Computer science, Visual reasoning, Artificial intelligence, Representation (politics), Context (archaeology), Object (grammar), Cognitive neuroscience of visual object recognition, Spatial intelligence, Visualization, Task (project management), Feature (linguistics), Visual Objects, Analytic reasoning, Machine learning, Natural language processing, Reasoning system, Perception, Psychology, Philosophy, Biology, Political science, Law, Management, Linguistics, Neuroscience, Politics, Economics, Paleontology

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4312091344
doi	https://doi.org/10.48550/arxiv.2212.10292
ids.doi	https://doi.org/10.48550/arxiv.2212.10292
ids.openalex	https://openalex.org/W4312091344
fwci
type	preprint
title	Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?
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	0.9987999796867371
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/T10627
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9818000197410583
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1707
topics[1].subfield.display_name	Computer Vision and Pattern Recognition
topics[1].display_name	Advanced Image and Video Retrieval Techniques
topics[2].id	https://openalex.org/T11605
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9674999713897705
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	Visual Attention and Saliency Detection
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.73170006275177
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C2777508537
concepts[1].level	2
concepts[1].score	0.6414449214935303
concepts[1].wikidata	https://www.wikidata.org/wiki/Q7936620
concepts[1].display_name	Visual reasoning
concepts[2].id	https://openalex.org/C154945302
concepts[2].level	1
concepts[2].score	0.6281846761703491
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[2].display_name	Artificial intelligence
concepts[3].id	https://openalex.org/C2776359362
concepts[3].level	3
concepts[3].score	0.5452573299407959
concepts[3].wikidata	https://www.wikidata.org/wiki/Q2145286
concepts[3].display_name	Representation (politics)
concepts[4].id	https://openalex.org/C2779343474
concepts[4].level	2
concepts[4].score	0.5371452569961548
concepts[4].wikidata	https://www.wikidata.org/wiki/Q3109175
concepts[4].display_name	Context (archaeology)
concepts[5].id	https://openalex.org/C2781238097
concepts[5].level	2
concepts[5].score	0.5160760283470154
concepts[5].wikidata	https://www.wikidata.org/wiki/Q175026
concepts[5].display_name	Object (grammar)
concepts[6].id	https://openalex.org/C64876066
concepts[6].level	3
concepts[6].score	0.4759865999221802
concepts[6].wikidata	https://www.wikidata.org/wiki/Q5141226
concepts[6].display_name	Cognitive neuroscience of visual object recognition
concepts[7].id	https://openalex.org/C155911833
concepts[7].level	2
concepts[7].score	0.46874549984931946
concepts[7].wikidata	https://www.wikidata.org/wiki/Q3817354
concepts[7].display_name	Spatial intelligence
concepts[8].id	https://openalex.org/C36464697
concepts[8].level	2
concepts[8].score	0.45052653551101685
concepts[8].wikidata	https://www.wikidata.org/wiki/Q451553
concepts[8].display_name	Visualization
concepts[9].id	https://openalex.org/C2780451532
concepts[9].level	2
concepts[9].score	0.4503372013568878
concepts[9].wikidata	https://www.wikidata.org/wiki/Q759676
concepts[9].display_name	Task (project management)
concepts[10].id	https://openalex.org/C2776401178
concepts[10].level	2
concepts[10].score	0.4319611191749573
concepts[10].wikidata	https://www.wikidata.org/wiki/Q12050496
concepts[10].display_name	Feature (linguistics)
concepts[11].id	https://openalex.org/C2780103172
concepts[11].level	3
concepts[11].score	0.4199483096599579
concepts[11].wikidata	https://www.wikidata.org/wiki/Q1309721
concepts[11].display_name	Visual Objects
concepts[12].id	https://openalex.org/C103057564
concepts[12].level	3
concepts[12].score	0.4173809587955475
concepts[12].wikidata	https://www.wikidata.org/wiki/Q4751139
concepts[12].display_name	Analytic reasoning
concepts[13].id	https://openalex.org/C119857082
concepts[13].level	1
concepts[13].score	0.39615508913993835
concepts[13].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[13].display_name	Machine learning
concepts[14].id	https://openalex.org/C204321447
concepts[14].level	1
concepts[14].score	0.3257433772087097
concepts[14].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[14].display_name	Natural language processing
concepts[15].id	https://openalex.org/C89288958
concepts[15].level	2
concepts[15].score	0.30707812309265137
concepts[15].wikidata	https://www.wikidata.org/wiki/Q7301504
concepts[15].display_name	Reasoning system
concepts[16].id	https://openalex.org/C26760741
concepts[16].level	2
concepts[16].score	0.2572935223579407
concepts[16].wikidata	https://www.wikidata.org/wiki/Q160402
concepts[16].display_name	Perception
concepts[17].id	https://openalex.org/C15744967
concepts[17].level	0
concepts[17].score	0.07543793320655823
concepts[17].wikidata	https://www.wikidata.org/wiki/Q9418
concepts[17].display_name	Psychology
concepts[18].id	https://openalex.org/C138885662
concepts[18].level	0
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[18].display_name	Philosophy
concepts[19].id	https://openalex.org/C86803240
concepts[19].level	0
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q420
concepts[19].display_name	Biology
concepts[20].id	https://openalex.org/C17744445
concepts[20].level	0
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q36442
concepts[20].display_name	Political science
concepts[21].id	https://openalex.org/C199539241
concepts[21].level	1
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q7748
concepts[21].display_name	Law
concepts[22].id	https://openalex.org/C187736073
concepts[22].level	1
concepts[22].score	0.0
concepts[22].wikidata	https://www.wikidata.org/wiki/Q2920921
concepts[22].display_name	Management
concepts[23].id	https://openalex.org/C41895202
concepts[23].level	1
concepts[23].score	0.0
concepts[23].wikidata	https://www.wikidata.org/wiki/Q8162
concepts[23].display_name	Linguistics
concepts[24].id	https://openalex.org/C169760540
concepts[24].level	1
concepts[24].score	0.0
concepts[24].wikidata	https://www.wikidata.org/wiki/Q207011
concepts[24].display_name	Neuroscience
concepts[25].id	https://openalex.org/C94625758
concepts[25].level	2
concepts[25].score	0.0
concepts[25].wikidata	https://www.wikidata.org/wiki/Q7163
concepts[25].display_name	Politics
concepts[26].id	https://openalex.org/C162324750
concepts[26].level	0
concepts[26].score	0.0
concepts[26].wikidata	https://www.wikidata.org/wiki/Q8134
concepts[26].display_name	Economics
concepts[27].id	https://openalex.org/C151730666
concepts[27].level	1
concepts[27].score	0.0
concepts[27].wikidata	https://www.wikidata.org/wiki/Q7205
concepts[27].display_name	Paleontology
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.73170006275177
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/visual-reasoning
keywords[1].score	0.6414449214935303
keywords[1].display_name	Visual reasoning
keywords[2].id	https://openalex.org/keywords/artificial-intelligence
keywords[2].score	0.6281846761703491
keywords[2].display_name	Artificial intelligence
keywords[3].id	https://openalex.org/keywords/representation
keywords[3].score	0.5452573299407959
keywords[3].display_name	Representation (politics)
keywords[4].id	https://openalex.org/keywords/context
keywords[4].score	0.5371452569961548
keywords[4].display_name	Context (archaeology)
keywords[5].id	https://openalex.org/keywords/object
keywords[5].score	0.5160760283470154
keywords[5].display_name	Object (grammar)
keywords[6].id	https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition
keywords[6].score	0.4759865999221802
keywords[6].display_name	Cognitive neuroscience of visual object recognition
keywords[7].id	https://openalex.org/keywords/spatial-intelligence
keywords[7].score	0.46874549984931946
keywords[7].display_name	Spatial intelligence
keywords[8].id	https://openalex.org/keywords/visualization
keywords[8].score	0.45052653551101685
keywords[8].display_name	Visualization
keywords[9].id	https://openalex.org/keywords/task
keywords[9].score	0.4503372013568878
keywords[9].display_name	Task (project management)
keywords[10].id	https://openalex.org/keywords/feature
keywords[10].score	0.4319611191749573
keywords[10].display_name	Feature (linguistics)
keywords[11].id	https://openalex.org/keywords/visual-objects
keywords[11].score	0.4199483096599579
keywords[11].display_name	Visual Objects
keywords[12].id	https://openalex.org/keywords/analytic-reasoning
keywords[12].score	0.4173809587955475
keywords[12].display_name	Analytic reasoning
keywords[13].id	https://openalex.org/keywords/machine-learning
keywords[13].score	0.39615508913993835
keywords[13].display_name	Machine learning
keywords[14].id	https://openalex.org/keywords/natural-language-processing
keywords[14].score	0.3257433772087097
keywords[14].display_name	Natural language processing
keywords[15].id	https://openalex.org/keywords/reasoning-system
keywords[15].score	0.30707812309265137
keywords[15].display_name	Reasoning system
keywords[16].id	https://openalex.org/keywords/perception
keywords[16].score	0.2572935223579407
keywords[16].display_name	Perception
keywords[17].id	https://openalex.org/keywords/psychology
keywords[17].score	0.07543793320655823
keywords[17].display_name	Psychology
language	en
locations[0].id	pmh:oai:arXiv.org:2212.10292
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/2212.10292
locations[0].version	submittedVersion
locations[0].raw_type
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/2212.10292
locations[1].id	doi:10.48550/arxiv.2212.10292
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.2212.10292
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5057907139
authorships[0].author.orcid	https://orcid.org/0000-0001-7785-2277
authorships[0].author.display_name	Monika Wysoczańska
authorships[0].author_position	first
authorships[0].raw_author_name	Wysoczańska, Monika
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5075666099
authorships[1].author.orcid	https://orcid.org/0009-0008-1937-6506
authorships[1].author.display_name	Tom Monnier
authorships[1].author_position	middle
authorships[1].raw_author_name	Monnier, Tom
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5070627781
authorships[2].author.orcid	https://orcid.org/0000-0002-1486-8906
authorships[2].author.display_name	T. P. Trzcinski
authorships[2].author_position	middle
authorships[2].raw_author_name	Trzciński, Tomasz
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5002574498
authorships[3].author.orcid	https://orcid.org/0000-0002-6296-4222
authorships[3].author.display_name	David Picard
authorships[3].author_position	last
authorships[3].raw_author_name	Picard, David
authorships[3].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/2212.10292
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2023-01-04T00:00:00
display_name	Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?
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	0.9987999796867371
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/W3081308103, https://openalex.org/W2113245685, https://openalex.org/W2395908292, https://openalex.org/W1574950926, https://openalex.org/W2376002020, https://openalex.org/W2142763871, https://openalex.org/W607204158, https://openalex.org/W4385571345, https://openalex.org/W94330105, https://openalex.org/W2039143072
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2212.10292
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/2212.10292
best_oa_location.version	submittedVersion
best_oa_location.raw_type
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/2212.10292
primary_location.id	pmh:oai:arXiv.org:2212.10292
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/2212.10292
primary_location.version	submittedVersion
primary_location.raw_type
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/2212.10292
publication_date	2022-12-20
publication_year	2022
referenced_works_count	0
abstract_inverted_index.a	78, 102, 119, 148
abstract_inverted_index.In	91, 190
abstract_inverted_index.We	48, 130
abstract_inverted_index.an	9
abstract_inverted_index.as	37
abstract_inverted_index.at	72
abstract_inverted_index.be	116
abstract_inverted_index.by	53
abstract_inverted_index.do	51
abstract_inverted_index.in	2, 56, 118
abstract_inverted_index.is	108
abstract_inverted_index.of	11, 59, 87, 134, 147
abstract_inverted_index.on	110, 127, 164
abstract_inverted_index.so	52
abstract_inverted_index.to	7, 25, 50, 80, 93, 115, 122, 186, 197
abstract_inverted_index.we	76, 100, 194
abstract_inverted_index.Our	155
abstract_inverted_index.and	44, 68, 141
abstract_inverted_index.are	16, 71, 158
abstract_inverted_index.for	18, 84, 172
abstract_inverted_index.how	27, 196
abstract_inverted_index.our	191
abstract_inverted_index.the	34, 57, 85, 111, 145, 182
abstract_inverted_index.two	132
abstract_inverted_index.More	74
abstract_inverted_index.This	22
abstract_inverted_index.aims	24
abstract_inverted_index.fall	170
abstract_inverted_index.from	98
abstract_inverted_index.main	156
abstract_inverted_index.show	195
abstract_inverted_index.such	36, 168
abstract_inverted_index.task	86
abstract_inverted_index.that	15
abstract_inverted_index.them	55
abstract_inverted_index.this	200
abstract_inverted_index.well	28
abstract_inverted_index.with	65
abstract_inverted_index.work	23
abstract_inverted_index.about	33
abstract_inverted_index.build	8
abstract_inverted_index.image	150
abstract_inverted_index.local	139
abstract_inverted_index.ones,	143
abstract_inverted_index.order	92
abstract_inverted_index.play.	73
abstract_inverted_index.proxy	166
abstract_inverted_index.short	171
abstract_inverted_index.their	38, 41, 45
abstract_inverted_index.these	29
abstract_inverted_index.types	133
abstract_inverted_index.using	152
abstract_inverted_index.where	62
abstract_inverted_index.which	107
abstract_inverted_index.First,	160
abstract_inverted_index.Recent	0
abstract_inverted_index.Visual	88
abstract_inverted_index.assess	26
abstract_inverted_index.better	180
abstract_inverted_index.design	101
abstract_inverted_index.frozen	112
abstract_inverted_index.ground	153
abstract_inverted_index.module	106
abstract_inverted_index.spirit	120
abstract_inverted_index.tasks,	167
abstract_inverted_index.tasks.	21
abstract_inverted_index.truth.	154
abstract_inverted_index.visual	3, 42, 60, 82, 95, 113, 135, 188
abstract_inverted_index.Second,	177
abstract_inverted_index.against	144
abstract_inverted_index.allowed	6
abstract_inverted_index.compare	131
abstract_inverted_index.complex	66, 174
abstract_inverted_index.context	58
abstract_inverted_index.densely	137
abstract_inverted_index.despite	161
abstract_inverted_index.feature	96, 124
abstract_inverted_index.objects	64
abstract_inverted_index.perfect	149
abstract_inverted_index.perform	187
abstract_inverted_index.propose	49
abstract_inverted_index.relying	126
abstract_inverted_index.shallow	128
abstract_inverted_index.similar	121
abstract_inverted_index.solving	173
abstract_inverted_index.spatial	39
abstract_inverted_index.trained	109
abstract_inverted_index.Question	89
abstract_inverted_index.advances	1
abstract_inverted_index.approach	199
abstract_inverted_index.critical	183
abstract_inverted_index.decouple	94
abstract_inverted_index.evaluate	81
abstract_inverted_index.features	14, 30, 140, 179
abstract_inverted_index.findings	157
abstract_inverted_index.learning	5
abstract_inverted_index.multiple	63
abstract_inverted_index.numerous	19
abstract_inverted_index.objects,	35
abstract_inverted_index.powerful	12
abstract_inverted_index.preserve	31, 181
abstract_inverted_index.problem.	176
abstract_inverted_index.proposed	192
abstract_inverted_index.protocol	79
abstract_inverted_index.relative	46
abstract_inverted_index.specific	103
abstract_inverted_index.standard	123
abstract_inverted_index.abundance	10
abstract_inverted_index.classical	165
abstract_inverted_index.different	69
abstract_inverted_index.excellent	162
abstract_inverted_index.extracted	138
abstract_inverted_index.framework	193
abstract_inverted_index.introduce	77
abstract_inverted_index.location,	40
abstract_inverted_index.necessary	185
abstract_inverted_index.networks.	129
abstract_inverted_index.reasoning	105, 175
abstract_inverted_index.two-fold.	159
abstract_inverted_index.Answering.	90
abstract_inverted_index.attributes	70
abstract_inverted_index.downstream	20
abstract_inverted_index.evaluated,	117
abstract_inverted_index.evaluating	54
abstract_inverted_index.extraction	97
abstract_inverted_index.properties	43
abstract_inverted_index.reasoning,	61, 99
abstract_inverted_index.reasoning.	189
abstract_inverted_index.evaluation.	201
abstract_inverted_index.evaluations	125
abstract_inverted_index.information	32, 184
abstract_inverted_index.performances	146, 163
abstract_inverted_index.ready-to-use	17
abstract_inverted_index.off-the-shelf	13
abstract_inverted_index.relationships	67
abstract_inverted_index.specifically,	75
abstract_inverted_index.object-centric	142, 178
abstract_inverted_index.relationships.	47
abstract_inverted_index.representation	4, 151
abstract_inverted_index.attention-based	104
abstract_inverted_index.representations	83, 114, 169
abstract_inverted_index.methodologically	198
abstract_inverted_index.representations,	136
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile