Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats Article Swipe
István Sárándi
,
Alexander Hermans
,
Bastian Leibe
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2212.14474
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2212.14474
Deep learning-based 3D human pose estimation performs best when trained on large amounts of labeled data, making combined learning from many datasets an important research direction. One obstacle to this endeavor are the different skeleton formats provided by different datasets, i.e., they do not label the same set of anatomical landmarks. There is little prior research on how to best supervise one model with such discrepant labels. We show that simply using separate output heads for different skeletons results in inconsistent depth estimates and insufficient information sharing across skeletons. As a remedy, we propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. The discovered latent 3D points capture the redundancy among skeletons, enabling enhanced information sharing when used for consistency regularization. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model, which outperforms prior work on a range of benchmarks, including the challenging 3D Poses in the Wild (3DPW) dataset. Our code and models are available for research purposes.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2212.14474
- https://arxiv.org/pdf/2212.14474
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4313447138
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4313447138Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2212.14474Digital Object Identifier
- Title
-
Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton FormatsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-12-29Full publication date if available
- Authors
-
István Sárándi, Alexander Hermans, Bastian LeibeList of authors in order
- Landing page
-
https://arxiv.org/abs/2212.14474Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2212.14474Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2212.14474Direct OA link when available
- Concepts
-
Computer science, Autoencoder, Artificial intelligence, Pose, Consistency (knowledge bases), Dimensionality reduction, Deep learning, Redundancy (engineering), Regularization (linguistics), Affine transformation, Machine learning, Pattern recognition (psychology), Mathematics, Operating system, Pure mathematicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4313447138 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2212.14474 |
| ids.doi | https://doi.org/10.48550/arxiv.2212.14474 |
| ids.openalex | https://openalex.org/W4313447138 |
| fwci | |
| type | preprint |
| title | Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10812 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9994999766349792 |
| 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 | Human Pose and Action Recognition |
| topics[1].id | https://openalex.org/T12740 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9761000275611877 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2204 |
| topics[1].subfield.display_name | Biomedical Engineering |
| topics[1].display_name | Gait Recognition and Analysis |
| topics[2].id | https://openalex.org/T12994 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.9611999988555908 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2741 |
| topics[2].subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| topics[2].display_name | Infrared Thermography in Medicine |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7289488315582275 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C101738243 |
| concepts[1].level | 3 |
| concepts[1].score | 0.7248331308364868 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q786435 |
| concepts[1].display_name | Autoencoder |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.684380829334259 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C52102323 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5661715269088745 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1671968 |
| concepts[3].display_name | Pose |
| concepts[4].id | https://openalex.org/C2776436953 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5619887113571167 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q5163215 |
| concepts[4].display_name | Consistency (knowledge bases) |
| concepts[5].id | https://openalex.org/C70518039 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5213695168495178 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q16000077 |
| concepts[5].display_name | Dimensionality reduction |
| concepts[6].id | https://openalex.org/C108583219 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5032584071159363 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[6].display_name | Deep learning |
| concepts[7].id | https://openalex.org/C152124472 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4869990944862366 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1204361 |
| concepts[7].display_name | Redundancy (engineering) |
| concepts[8].id | https://openalex.org/C2776135515 |
| concepts[8].level | 2 |
| concepts[8].score | 0.45122379064559937 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q17143721 |
| concepts[8].display_name | Regularization (linguistics) |
| concepts[9].id | https://openalex.org/C92757383 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4426334500312805 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q382497 |
| concepts[9].display_name | Affine transformation |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.4115604758262634 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C153180895 |
| concepts[11].level | 2 |
| concepts[11].score | 0.3799136281013489 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[11].display_name | Pattern recognition (psychology) |
| concepts[12].id | https://openalex.org/C33923547 |
| concepts[12].level | 0 |
| concepts[12].score | 0.1224856972694397 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[12].display_name | Mathematics |
| concepts[13].id | https://openalex.org/C111919701 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[13].display_name | Operating system |
| concepts[14].id | https://openalex.org/C202444582 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q837863 |
| concepts[14].display_name | Pure mathematics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7289488315582275 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/autoencoder |
| keywords[1].score | 0.7248331308364868 |
| keywords[1].display_name | Autoencoder |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.684380829334259 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/pose |
| keywords[3].score | 0.5661715269088745 |
| keywords[3].display_name | Pose |
| keywords[4].id | https://openalex.org/keywords/consistency |
| keywords[4].score | 0.5619887113571167 |
| keywords[4].display_name | Consistency (knowledge bases) |
| keywords[5].id | https://openalex.org/keywords/dimensionality-reduction |
| keywords[5].score | 0.5213695168495178 |
| keywords[5].display_name | Dimensionality reduction |
| keywords[6].id | https://openalex.org/keywords/deep-learning |
| keywords[6].score | 0.5032584071159363 |
| keywords[6].display_name | Deep learning |
| keywords[7].id | https://openalex.org/keywords/redundancy |
| keywords[7].score | 0.4869990944862366 |
| keywords[7].display_name | Redundancy (engineering) |
| keywords[8].id | https://openalex.org/keywords/regularization |
| keywords[8].score | 0.45122379064559937 |
| keywords[8].display_name | Regularization (linguistics) |
| keywords[9].id | https://openalex.org/keywords/affine-transformation |
| keywords[9].score | 0.4426334500312805 |
| keywords[9].display_name | Affine transformation |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.4115604758262634 |
| keywords[10].display_name | Machine learning |
| keywords[11].id | https://openalex.org/keywords/pattern-recognition |
| keywords[11].score | 0.3799136281013489 |
| keywords[11].display_name | Pattern recognition (psychology) |
| keywords[12].id | https://openalex.org/keywords/mathematics |
| keywords[12].score | 0.1224856972694397 |
| keywords[12].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2212.14474 |
| 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/2212.14474 |
| 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/2212.14474 |
| locations[1].id | doi:10.48550/arxiv.2212.14474 |
| 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 | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2212.14474 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5003174716 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5686-3214 |
| authorships[0].author.display_name | István Sárándi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Sárándi, István |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5071563379 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2127-0782 |
| authorships[1].author.display_name | Alexander Hermans |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Hermans, Alexander |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5071006649 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4225-0051 |
| authorships[2].author.display_name | Bastian Leibe |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Leibe, Bastian |
| authorships[2].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2212.14474 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-01-06T00:00:00 |
| display_name | Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10812 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9994999766349792 |
| 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 | Human Pose and Action Recognition |
| related_works | https://openalex.org/W3013693939, https://openalex.org/W2159052453, https://openalex.org/W2566616303, https://openalex.org/W3131327266, https://openalex.org/W2734887215, https://openalex.org/W4297051394, https://openalex.org/W2752972570, https://openalex.org/W4310873165, https://openalex.org/W2355395139, https://openalex.org/W4285596704 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2212.14474 |
| 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/2212.14474 |
| 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/2212.14474 |
| primary_location.id | pmh:oai:arXiv.org:2212.14474 |
| 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/2212.14474 |
| 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/2212.14474 |
| publication_date | 2022-12-29 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 90, 94, 153 |
| abstract_inverted_index.28 | 139 |
| abstract_inverted_index.3D | 2, 112, 140, 160 |
| abstract_inverted_index.As | 89 |
| abstract_inverted_index.We | 67 |
| abstract_inverted_index.an | 22, 132 |
| abstract_inverted_index.by | 37 |
| abstract_inverted_index.do | 42 |
| abstract_inverted_index.in | 79, 162 |
| abstract_inverted_index.is | 52 |
| abstract_inverted_index.of | 13, 48, 107, 155 |
| abstract_inverted_index.on | 10, 56, 104, 152 |
| abstract_inverted_index.to | 28, 58, 100, 131, 144 |
| abstract_inverted_index.we | 92, 137 |
| abstract_inverted_index.One | 26 |
| abstract_inverted_index.Our | 128, 167 |
| abstract_inverted_index.The | 109 |
| abstract_inverted_index.and | 83, 169 |
| abstract_inverted_index.are | 31, 171 |
| abstract_inverted_index.for | 75, 125, 173 |
| abstract_inverted_index.how | 57 |
| abstract_inverted_index.not | 43 |
| abstract_inverted_index.one | 61, 146 |
| abstract_inverted_index.set | 47 |
| abstract_inverted_index.the | 32, 45, 105, 115, 158, 163 |
| abstract_inverted_index.use | 138 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.Wild | 164 |
| abstract_inverted_index.best | 7, 59 |
| abstract_inverted_index.code | 168 |
| abstract_inverted_index.from | 19 |
| abstract_inverted_index.many | 20 |
| abstract_inverted_index.pose | 4, 142 |
| abstract_inverted_index.same | 46 |
| abstract_inverted_index.show | 68 |
| abstract_inverted_index.such | 64 |
| abstract_inverted_index.that | 69 |
| abstract_inverted_index.they | 41 |
| abstract_inverted_index.this | 29 |
| abstract_inverted_index.used | 124 |
| abstract_inverted_index.when | 8, 123 |
| abstract_inverted_index.with | 63 |
| abstract_inverted_index.work | 151 |
| abstract_inverted_index.Poses | 161 |
| abstract_inverted_index.There | 51 |
| abstract_inverted_index.among | 117 |
| abstract_inverted_index.data, | 15 |
| abstract_inverted_index.depth | 81 |
| abstract_inverted_index.heads | 74 |
| abstract_inverted_index.human | 3, 141 |
| abstract_inverted_index.i.e., | 40 |
| abstract_inverted_index.label | 44 |
| abstract_inverted_index.large | 11 |
| abstract_inverted_index.model | 62 |
| abstract_inverted_index.novel | 95 |
| abstract_inverted_index.prior | 54, 150 |
| abstract_inverted_index.range | 154 |
| abstract_inverted_index.using | 71 |
| abstract_inverted_index.where | 136 |
| abstract_inverted_index.which | 148 |
| abstract_inverted_index.(3DPW) | 165 |
| abstract_inverted_index.(ACAE) | 98 |
| abstract_inverted_index.across | 87 |
| abstract_inverted_index.latent | 111 |
| abstract_inverted_index.little | 53 |
| abstract_inverted_index.making | 16 |
| abstract_inverted_index.method | 99 |
| abstract_inverted_index.model, | 147 |
| abstract_inverted_index.models | 170 |
| abstract_inverted_index.number | 106 |
| abstract_inverted_index.output | 73 |
| abstract_inverted_index.points | 113 |
| abstract_inverted_index.scales | 130 |
| abstract_inverted_index.simply | 70 |
| abstract_inverted_index.amounts | 12 |
| abstract_inverted_index.capture | 114 |
| abstract_inverted_index.extreme | 133 |
| abstract_inverted_index.formats | 35 |
| abstract_inverted_index.labeled | 14 |
| abstract_inverted_index.labels. | 66 |
| abstract_inverted_index.perform | 101 |
| abstract_inverted_index.propose | 93 |
| abstract_inverted_index.regime, | 135 |
| abstract_inverted_index.remedy, | 91 |
| abstract_inverted_index.results | 78 |
| abstract_inverted_index.sharing | 86, 122 |
| abstract_inverted_index.trained | 9 |
| abstract_inverted_index.approach | 129 |
| abstract_inverted_index.combined | 17 |
| abstract_inverted_index.dataset. | 166 |
| abstract_inverted_index.datasets | 21, 143 |
| abstract_inverted_index.enabling | 119 |
| abstract_inverted_index.endeavor | 30 |
| abstract_inverted_index.enhanced | 120 |
| abstract_inverted_index.learning | 18 |
| abstract_inverted_index.obstacle | 27 |
| abstract_inverted_index.performs | 6 |
| abstract_inverted_index.provided | 36 |
| abstract_inverted_index.research | 24, 55, 174 |
| abstract_inverted_index.separate | 72 |
| abstract_inverted_index.skeleton | 34 |
| abstract_inverted_index.available | 172 |
| abstract_inverted_index.datasets, | 39 |
| abstract_inverted_index.different | 33, 38, 76 |
| abstract_inverted_index.estimates | 82 |
| abstract_inverted_index.important | 23 |
| abstract_inverted_index.including | 157 |
| abstract_inverted_index.purposes. | 175 |
| abstract_inverted_index.reduction | 103 |
| abstract_inverted_index.skeletons | 77 |
| abstract_inverted_index.supervise | 60, 145 |
| abstract_inverted_index.anatomical | 49 |
| abstract_inverted_index.direction. | 25 |
| abstract_inverted_index.discovered | 110 |
| abstract_inverted_index.discrepant | 65 |
| abstract_inverted_index.estimation | 5 |
| abstract_inverted_index.landmarks. | 50, 108 |
| abstract_inverted_index.redundancy | 116 |
| abstract_inverted_index.skeletons, | 118 |
| abstract_inverted_index.skeletons. | 88 |
| abstract_inverted_index.autoencoder | 97 |
| abstract_inverted_index.benchmarks, | 156 |
| abstract_inverted_index.challenging | 159 |
| abstract_inverted_index.consistency | 126 |
| abstract_inverted_index.information | 85, 121 |
| abstract_inverted_index.outperforms | 149 |
| abstract_inverted_index.inconsistent | 80 |
| abstract_inverted_index.insufficient | 84 |
| abstract_inverted_index.multi-dataset | 134 |
| abstract_inverted_index.dimensionality | 102 |
| abstract_inverted_index.learning-based | 1 |
| abstract_inverted_index.regularization. | 127 |
| abstract_inverted_index.affine-combining | 96 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |