Radiology Reports Improve Visual Representations Learned from Radiographs. Article Swipe
Although human's ability to visually understand the structure of the World plays a crucial role in perceiving the World and making appropriate decisions, human perception does not solely rely on vision but amalgamates the information from acoustic, verbal, and visual stimuli. An active area of research has been revolving around designing an efficient framework that adapts to multiple modalities and ideally improves the performance of existing tasks. While numerous frameworks have proved effective on natural datasets like ImageNet, a limited number of studies have been carried out in the biomedical domain. In this work, we extend the available frameworks for natural data to biomedical data by leveraging the abundant, unstructured multi-modal data available as radiology images and reports. We attempt to answer the question, "For multi-modal learning, self-supervised learning and joint learning using both learning strategies, which one improves the visual representation for downstream chest radiographs classification tasks the most?". Our experiments indicated that in limited labeled data settings with 1% and 10% labeled data, the joint learning with multi-modal and self-supervised models outperforms self-supervised learning and is at par with multi-modal learning. Additionally, we found that multi-modal learning is generally more robust on out-of-distribution datasets. The code is publicly available online.
Related Topics
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://pubmed.ncbi.nlm.nih.gov/38988725
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4400573112
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4400573112Canonical identifier for this work in OpenAlex
- Title
-
Radiology Reports Improve Visual Representations Learned from Radiographs.Work title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-07-01Full publication date if available
- Authors
-
Haoxu Huang, Samyak Rawlekar, Sumit Chopra, Cem M. DenizList of authors in order
- Landing page
-
https://pubmed.ncbi.nlm.nih.gov/38988725Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://www.ncbi.nlm.nih.gov/pmc/articles/11234265Direct OA link when available
- Concepts
-
Radiography, Medical physics, Radiology, Computer science, Medicine, Artificial intelligenceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4400573112 |
|---|---|
| doi | |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/38988725 |
| ids.openalex | https://openalex.org/W4400573112 |
| fwci | 0.0 |
| type | article |
| title | Radiology Reports Improve Visual Representations Learned from Radiographs. |
| biblio.issue | |
| biblio.volume | 227 |
| biblio.last_page | 1405 |
| biblio.first_page | 1385 |
| topics[0].id | https://openalex.org/T11894 |
| topics[0].field.id | https://openalex.org/fields/27 |
| topics[0].field.display_name | Medicine |
| topics[0].score | 0.9973000288009644 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2741 |
| topics[0].subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| topics[0].display_name | Radiology practices and education |
| topics[1].id | https://openalex.org/T10862 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9560999870300293 |
| 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 | AI in cancer detection |
| topics[2].id | https://openalex.org/T13953 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.9552000164985657 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2739 |
| topics[2].subfield.display_name | Public Health, Environmental and Occupational Health |
| topics[2].display_name | Digital Imaging in Medicine |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C36454342 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7087148427963257 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q245341 |
| concepts[0].display_name | Radiography |
| concepts[1].id | https://openalex.org/C19527891 |
| concepts[1].level | 1 |
| concepts[1].score | 0.45661821961402893 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1120908 |
| concepts[1].display_name | Medical physics |
| concepts[2].id | https://openalex.org/C126838900 |
| concepts[2].level | 1 |
| concepts[2].score | 0.4343167245388031 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q77604 |
| concepts[2].display_name | Radiology |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.42800551652908325 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C71924100 |
| concepts[4].level | 0 |
| concepts[4].score | 0.37525296211242676 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[4].display_name | Medicine |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3644452691078186 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| keywords[0].id | https://openalex.org/keywords/radiography |
| keywords[0].score | 0.7087148427963257 |
| keywords[0].display_name | Radiography |
| keywords[1].id | https://openalex.org/keywords/medical-physics |
| keywords[1].score | 0.45661821961402893 |
| keywords[1].display_name | Medical physics |
| keywords[2].id | https://openalex.org/keywords/radiology |
| keywords[2].score | 0.4343167245388031 |
| keywords[2].display_name | Radiology |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.42800551652908325 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/medicine |
| keywords[4].score | 0.37525296211242676 |
| keywords[4].display_name | Medicine |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.3644452691078186 |
| keywords[5].display_name | Artificial intelligence |
| language | en |
| locations[0].id | pmid:38988725 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S4306525036 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | PubMed |
| locations[0].source.host_organization | https://openalex.org/I1299303238 |
| locations[0].source.host_organization_name | National Institutes of Health |
| locations[0].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of machine learning research |
| locations[0].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/38988725 |
| locations[1].id | pmh:oai:pubmedcentral.nih.gov:11234265 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S2764455111 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | PubMed Central |
| locations[1].source.host_organization | https://openalex.org/I1299303238 |
| locations[1].source.host_organization_name | National Institutes of Health |
| locations[1].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | Text |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | Proc Mach Learn Res |
| locations[1].landing_page_url | https://www.ncbi.nlm.nih.gov/pmc/articles/11234265 |
| indexed_in | pubmed |
| authorships[0].author.id | https://openalex.org/A5022918672 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Haoxu Huang |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[0].affiliations[0].raw_affiliation_string | Courant Institute of Mathematical Sciences, New York University, USA. |
| authorships[0].institutions[0].id | https://openalex.org/I36672615 |
| authorships[0].institutions[0].ror | https://ror.org/037tm7f56 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Courant Institute of Mathematical Sciences |
| authorships[0].institutions[1].id | https://openalex.org/I57206974 |
| authorships[0].institutions[1].ror | https://ror.org/0190ak572 |
| authorships[0].institutions[1].type | education |
| authorships[0].institutions[1].lineage | https://openalex.org/I57206974 |
| authorships[0].institutions[1].country_code | US |
| authorships[0].institutions[1].display_name | New York University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Haoxu Huang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Courant Institute of Mathematical Sciences, New York University, USA. |
| authorships[1].author.id | https://openalex.org/A5020509971 |
| authorships[1].author.orcid | https://orcid.org/0009-0000-7513-3797 |
| authorships[1].author.display_name | Samyak Rawlekar |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[1].affiliations[0].raw_affiliation_string | Courant Institute of Mathematical Sciences, New York University, USA. |
| authorships[1].institutions[0].id | https://openalex.org/I36672615 |
| authorships[1].institutions[0].ror | https://ror.org/037tm7f56 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Courant Institute of Mathematical Sciences |
| authorships[1].institutions[1].id | https://openalex.org/I57206974 |
| authorships[1].institutions[1].ror | https://ror.org/0190ak572 |
| authorships[1].institutions[1].type | education |
| authorships[1].institutions[1].lineage | https://openalex.org/I57206974 |
| authorships[1].institutions[1].country_code | US |
| authorships[1].institutions[1].display_name | New York University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Samyak Rawlekar |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Courant Institute of Mathematical Sciences, New York University, USA. |
| authorships[2].author.id | https://openalex.org/A5078511139 |
| authorships[2].author.orcid | https://orcid.org/0009-0009-6637-2230 |
| authorships[2].author.display_name | Sumit Chopra |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[2].affiliations[0].raw_affiliation_string | Courant Institute of Mathematical Sciences, New York University, USA. |
| authorships[2].institutions[0].id | https://openalex.org/I36672615 |
| authorships[2].institutions[0].ror | https://ror.org/037tm7f56 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Courant Institute of Mathematical Sciences |
| authorships[2].institutions[1].id | https://openalex.org/I57206974 |
| authorships[2].institutions[1].ror | https://ror.org/0190ak572 |
| authorships[2].institutions[1].type | education |
| authorships[2].institutions[1].lineage | https://openalex.org/I57206974 |
| authorships[2].institutions[1].country_code | US |
| authorships[2].institutions[1].display_name | New York University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Sumit Chopra |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Courant Institute of Mathematical Sciences, New York University, USA. |
| authorships[3].author.id | https://openalex.org/A5050471723 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8809-5945 |
| authorships[3].author.display_name | Cem M. Deniz |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[3].affiliations[0].raw_affiliation_string | Courant Institute of Mathematical Sciences, New York University, USA. |
| authorships[3].institutions[0].id | https://openalex.org/I36672615 |
| authorships[3].institutions[0].ror | https://ror.org/037tm7f56 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I36672615, https://openalex.org/I57206974 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Courant Institute of Mathematical Sciences |
| authorships[3].institutions[1].id | https://openalex.org/I57206974 |
| authorships[3].institutions[1].ror | https://ror.org/0190ak572 |
| authorships[3].institutions[1].type | education |
| authorships[3].institutions[1].lineage | https://openalex.org/I57206974 |
| authorships[3].institutions[1].country_code | US |
| authorships[3].institutions[1].display_name | New York University |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Cem M Deniz |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Courant Institute of Mathematical Sciences, New York University, USA. |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.ncbi.nlm.nih.gov/pmc/articles/11234265 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Radiology Reports Improve Visual Representations Learned from Radiographs. |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T04:12:42.849631 |
| primary_topic.id | https://openalex.org/T11894 |
| primary_topic.field.id | https://openalex.org/fields/27 |
| primary_topic.field.display_name | Medicine |
| primary_topic.score | 0.9973000288009644 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2741 |
| primary_topic.subfield.display_name | Radiology, Nuclear Medicine and Imaging |
| primary_topic.display_name | Radiology practices and education |
| related_works | https://openalex.org/W2748952813, https://openalex.org/W3031052312, https://openalex.org/W4389568370, https://openalex.org/W3032375762, https://openalex.org/W1995515455, https://openalex.org/W2080531066, https://openalex.org/W3108674512, https://openalex.org/W1506200166, https://openalex.org/W1489783725, https://openalex.org/W2148612803 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:pubmedcentral.nih.gov:11234265 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2764455111 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | False |
| 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 | PubMed Central |
| best_oa_location.source.host_organization | https://openalex.org/I1299303238 |
| best_oa_location.source.host_organization_name | National Institutes of Health |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I1299303238 |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| 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 | Proc Mach Learn Res |
| best_oa_location.landing_page_url | https://www.ncbi.nlm.nih.gov/pmc/articles/11234265 |
| primary_location.id | pmid:38988725 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S4306525036 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | PubMed |
| primary_location.source.host_organization | https://openalex.org/I1299303238 |
| primary_location.source.host_organization_name | National Institutes of Health |
| primary_location.source.host_organization_lineage | https://openalex.org/I1299303238 |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of machine learning research |
| primary_location.landing_page_url | https://pubmed.ncbi.nlm.nih.gov/38988725 |
| publication_date | 2023-07-01 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 12, 78 |
| abstract_inverted_index.1% | 160 |
| abstract_inverted_index.An | 41 |
| abstract_inverted_index.In | 91 |
| abstract_inverted_index.We | 118 |
| abstract_inverted_index.an | 51 |
| abstract_inverted_index.as | 113 |
| abstract_inverted_index.at | 178 |
| abstract_inverted_index.by | 105 |
| abstract_inverted_index.in | 15, 87, 154 |
| abstract_inverted_index.is | 177, 189, 198 |
| abstract_inverted_index.of | 8, 44, 64, 81 |
| abstract_inverted_index.on | 29, 73, 193 |
| abstract_inverted_index.to | 3, 56, 102, 120 |
| abstract_inverted_index.we | 94, 184 |
| abstract_inverted_index.10% | 162 |
| abstract_inverted_index.Our | 150 |
| abstract_inverted_index.The | 196 |
| abstract_inverted_index.and | 19, 38, 59, 116, 129, 161, 170, 176 |
| abstract_inverted_index.but | 31 |
| abstract_inverted_index.for | 99, 142 |
| abstract_inverted_index.has | 46 |
| abstract_inverted_index.not | 26 |
| abstract_inverted_index.one | 137 |
| abstract_inverted_index.out | 86 |
| abstract_inverted_index.par | 179 |
| abstract_inverted_index.the | 6, 9, 17, 33, 62, 88, 96, 107, 122, 139, 148, 165 |
| abstract_inverted_index."For | 124 |
| abstract_inverted_index.area | 43 |
| abstract_inverted_index.been | 47, 84 |
| abstract_inverted_index.both | 133 |
| abstract_inverted_index.code | 197 |
| abstract_inverted_index.data | 101, 104, 111, 157 |
| abstract_inverted_index.does | 25 |
| abstract_inverted_index.from | 35 |
| abstract_inverted_index.have | 70, 83 |
| abstract_inverted_index.like | 76 |
| abstract_inverted_index.more | 191 |
| abstract_inverted_index.rely | 28 |
| abstract_inverted_index.role | 14 |
| abstract_inverted_index.that | 54, 153, 186 |
| abstract_inverted_index.this | 92 |
| abstract_inverted_index.with | 159, 168, 180 |
| abstract_inverted_index.While | 67 |
| abstract_inverted_index.World | 10, 18 |
| abstract_inverted_index.chest | 144 |
| abstract_inverted_index.data, | 164 |
| abstract_inverted_index.found | 185 |
| abstract_inverted_index.human | 23 |
| abstract_inverted_index.joint | 130, 166 |
| abstract_inverted_index.plays | 11 |
| abstract_inverted_index.tasks | 147 |
| abstract_inverted_index.using | 132 |
| abstract_inverted_index.which | 136 |
| abstract_inverted_index.work, | 93 |
| abstract_inverted_index.active | 42 |
| abstract_inverted_index.adapts | 55 |
| abstract_inverted_index.answer | 121 |
| abstract_inverted_index.around | 49 |
| abstract_inverted_index.extend | 95 |
| abstract_inverted_index.images | 115 |
| abstract_inverted_index.making | 20 |
| abstract_inverted_index.models | 172 |
| abstract_inverted_index.number | 80 |
| abstract_inverted_index.proved | 71 |
| abstract_inverted_index.robust | 192 |
| abstract_inverted_index.solely | 27 |
| abstract_inverted_index.tasks. | 66 |
| abstract_inverted_index.vision | 30 |
| abstract_inverted_index.visual | 39, 140 |
| abstract_inverted_index.ability | 2 |
| abstract_inverted_index.attempt | 119 |
| abstract_inverted_index.carried | 85 |
| abstract_inverted_index.crucial | 13 |
| abstract_inverted_index.domain. | 90 |
| abstract_inverted_index.human's | 1 |
| abstract_inverted_index.ideally | 60 |
| abstract_inverted_index.labeled | 156, 163 |
| abstract_inverted_index.limited | 79, 155 |
| abstract_inverted_index.most?". | 149 |
| abstract_inverted_index.natural | 74, 100 |
| abstract_inverted_index.online. | 201 |
| abstract_inverted_index.studies | 82 |
| abstract_inverted_index.verbal, | 37 |
| abstract_inverted_index.Although | 0 |
| abstract_inverted_index.datasets | 75 |
| abstract_inverted_index.existing | 65 |
| abstract_inverted_index.improves | 61, 138 |
| abstract_inverted_index.learning | 128, 131, 134, 167, 175, 188 |
| abstract_inverted_index.multiple | 57 |
| abstract_inverted_index.numerous | 68 |
| abstract_inverted_index.publicly | 199 |
| abstract_inverted_index.reports. | 117 |
| abstract_inverted_index.research | 45 |
| abstract_inverted_index.settings | 158 |
| abstract_inverted_index.stimuli. | 40 |
| abstract_inverted_index.visually | 4 |
| abstract_inverted_index.ImageNet, | 77 |
| abstract_inverted_index.abundant, | 108 |
| abstract_inverted_index.acoustic, | 36 |
| abstract_inverted_index.available | 97, 112, 200 |
| abstract_inverted_index.datasets. | 195 |
| abstract_inverted_index.designing | 50 |
| abstract_inverted_index.effective | 72 |
| abstract_inverted_index.efficient | 52 |
| abstract_inverted_index.framework | 53 |
| abstract_inverted_index.generally | 190 |
| abstract_inverted_index.indicated | 152 |
| abstract_inverted_index.learning, | 126 |
| abstract_inverted_index.learning. | 182 |
| abstract_inverted_index.question, | 123 |
| abstract_inverted_index.radiology | 114 |
| abstract_inverted_index.revolving | 48 |
| abstract_inverted_index.structure | 7 |
| abstract_inverted_index.biomedical | 89, 103 |
| abstract_inverted_index.decisions, | 22 |
| abstract_inverted_index.downstream | 143 |
| abstract_inverted_index.frameworks | 69, 98 |
| abstract_inverted_index.leveraging | 106 |
| abstract_inverted_index.modalities | 58 |
| abstract_inverted_index.perceiving | 16 |
| abstract_inverted_index.perception | 24 |
| abstract_inverted_index.understand | 5 |
| abstract_inverted_index.amalgamates | 32 |
| abstract_inverted_index.appropriate | 21 |
| abstract_inverted_index.experiments | 151 |
| abstract_inverted_index.information | 34 |
| abstract_inverted_index.multi-modal | 110, 125, 169, 181, 187 |
| abstract_inverted_index.outperforms | 173 |
| abstract_inverted_index.performance | 63 |
| abstract_inverted_index.radiographs | 145 |
| abstract_inverted_index.strategies, | 135 |
| abstract_inverted_index.unstructured | 109 |
| abstract_inverted_index.Additionally, | 183 |
| abstract_inverted_index.classification | 146 |
| abstract_inverted_index.representation | 141 |
| abstract_inverted_index.self-supervised | 127, 171, 174 |
| abstract_inverted_index.out-of-distribution | 194 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile.value | 0.4419472 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |