Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning Article Swipe
Chun-Mei Feng
,
Kai Yu
,
Xinxing Xu
,
Salman Khan
,
Rick Siow Mong Goh
,
Wangmeng Zuo
,
Yong Liu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1109/tpami.2025.3573852
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1109/tpami.2025.3573852
Benefited from image-text contrastive learning, pre-trained vision-language models, e.g., CLIP, allow to direct leverage texts as images (TaI) for parameter-efficient fine-tuning (PEFT). While CLIP is capable of making image features to be similar to the corresponding text features, the modality gap remains a nontrivial issue and limits image recognition performance of TaI. Using multi-label image recognition (MLR) as an example, we present a novel method, called T2I-PAL to tackle the modality gap issue when using only text captions for PEFT. The core design of T2I-PAL is to leverage pre-trained text-to-image generation models to generate photo-realistic and diverse images from text captions, thereby reducing the modality gap. To further enhance MLR, T2I-PAL incorporates a class-wise heatmap and learnable prototypes. This aggregates local similarities, making the representation of local visual features more robust and informative for multi-label recognition. For better PEFT, we further combine both prompt tuning and adapter learning to enhance classification performance. T2I-PAL offers significant advantages: it eliminates the need for fully semantically annotated training images, thereby reducing the manual annotation workload, and it preserves the intrinsic mode of the CLIP model, allowing for seamless integration with any existing CLIP framework. Extensive experiments on multiple benchmarks, including MS-COCO, VOC2007, and NUS-WIDE, show that our T2I-PAL can boost recognition performance by 3.47% in average above the top-ranked state-of-the-art methods.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/tpami.2025.3573852
- OA Status
- green
- References
- 50
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4410738163
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4410738163Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/tpami.2025.3573852Digital Object Identifier
- Title
-
Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter LearningWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-05-26Full publication date if available
- Authors
-
Chun-Mei Feng, Kai Yu, Xinxing Xu, Salman Khan, Rick Siow Mong Goh, Wangmeng Zuo, Yong LiuList of authors in order
- Landing page
-
https://doi.org/10.1109/tpami.2025.3573852Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2506.10575Direct OA link when available
- Concepts
-
Artificial intelligence, Computer science, Computer vision, Adapter (computing), Pattern recognition (psychology), Image (mathematics), Joint (building), Engineering, Operating system, Architectural engineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
50Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4410738163 |
|---|---|
| doi | https://doi.org/10.1109/tpami.2025.3573852 |
| ids.doi | https://doi.org/10.1109/tpami.2025.3573852 |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/40418601 |
| ids.openalex | https://openalex.org/W4410738163 |
| fwci | 0.0 |
| type | article |
| title | Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning |
| biblio.issue | 9 |
| biblio.volume | 47 |
| biblio.last_page | 7674 |
| biblio.first_page | 7660 |
| topics[0].id | https://openalex.org/T10601 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9883000254631042 |
| 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 | Handwritten Text Recognition Techniques |
| topics[1].id | https://openalex.org/T11550 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9782000184059143 |
| 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 | Text and Document Classification Technologies |
| topics[2].id | https://openalex.org/T10824 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9541000127792358 |
| 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 | Image Retrieval and Classification Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C154945302 |
| concepts[0].level | 1 |
| concepts[0].score | 0.7488757967948914 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[0].display_name | Artificial intelligence |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6760144233703613 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C31972630 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5637234449386597 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[2].display_name | Computer vision |
| concepts[3].id | https://openalex.org/C177284502 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5500687956809998 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1005390 |
| concepts[3].display_name | Adapter (computing) |
| concepts[4].id | https://openalex.org/C153180895 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5480650663375854 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[4].display_name | Pattern recognition (psychology) |
| concepts[5].id | https://openalex.org/C115961682 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4972393810749054 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[5].display_name | Image (mathematics) |
| concepts[6].id | https://openalex.org/C18555067 |
| concepts[6].level | 2 |
| concepts[6].score | 0.49505415558815 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q8375051 |
| concepts[6].display_name | Joint (building) |
| concepts[7].id | https://openalex.org/C127413603 |
| concepts[7].level | 0 |
| concepts[7].score | 0.1289784014225006 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[7].display_name | Engineering |
| concepts[8].id | https://openalex.org/C111919701 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[8].display_name | Operating system |
| concepts[9].id | https://openalex.org/C170154142 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q150737 |
| concepts[9].display_name | Architectural engineering |
| keywords[0].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[0].score | 0.7488757967948914 |
| keywords[0].display_name | Artificial intelligence |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6760144233703613 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/computer-vision |
| keywords[2].score | 0.5637234449386597 |
| keywords[2].display_name | Computer vision |
| keywords[3].id | https://openalex.org/keywords/adapter |
| keywords[3].score | 0.5500687956809998 |
| keywords[3].display_name | Adapter (computing) |
| keywords[4].id | https://openalex.org/keywords/pattern-recognition |
| keywords[4].score | 0.5480650663375854 |
| keywords[4].display_name | Pattern recognition (psychology) |
| keywords[5].id | https://openalex.org/keywords/image |
| keywords[5].score | 0.4972393810749054 |
| keywords[5].display_name | Image (mathematics) |
| keywords[6].id | https://openalex.org/keywords/joint |
| keywords[6].score | 0.49505415558815 |
| keywords[6].display_name | Joint (building) |
| keywords[7].id | https://openalex.org/keywords/engineering |
| keywords[7].score | 0.1289784014225006 |
| keywords[7].display_name | Engineering |
| language | en |
| locations[0].id | doi:10.1109/tpami.2025.3573852 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S199944782 |
| locations[0].source.issn | 0162-8828, 1939-3539, 2160-9292 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 0162-8828 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320439 |
| locations[0].source.host_organization_name | IEEE Computer Society |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320439, https://openalex.org/P4310319808 |
| locations[0].source.host_organization_lineage_names | IEEE Computer Society, Institute of Electrical and Electronics Engineers |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1109/tpami.2025.3573852 |
| locations[1].id | pmid:40418601 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306525036 |
| 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 |
| 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 | publishedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | IEEE transactions on pattern analysis and machine intelligence |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/40418601 |
| locations[2].id | pmh:oai:arXiv.org:2506.10575 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | |
| locations[2].pdf_url | https://arxiv.org/pdf/2506.10575 |
| locations[2].version | submittedVersion |
| locations[2].raw_type | text |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | http://arxiv.org/abs/2506.10575 |
| indexed_in | arxiv, crossref, pubmed |
| authorships[0].author.id | https://openalex.org/A5049444898 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3025-8964 |
| authorships[0].author.display_name | Chun-Mei Feng |
| authorships[0].countries | SG |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I115228651, https://openalex.org/I3004594783 |
| authorships[0].affiliations[0].raw_affiliation_string | Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore |
| authorships[0].institutions[0].id | https://openalex.org/I115228651 |
| authorships[0].institutions[0].ror | https://ror.org/036wvzt09 |
| authorships[0].institutions[0].type | government |
| authorships[0].institutions[0].lineage | https://openalex.org/I115228651 |
| authorships[0].institutions[0].country_code | SG |
| authorships[0].institutions[0].display_name | Agency for Science, Technology and Research |
| authorships[0].institutions[1].id | https://openalex.org/I3004594783 |
| authorships[0].institutions[1].ror | https://ror.org/02n0ejh50 |
| authorships[0].institutions[1].type | facility |
| authorships[0].institutions[1].lineage | https://openalex.org/I115228651, https://openalex.org/I3004594783, https://openalex.org/I91275662 |
| authorships[0].institutions[1].country_code | SG |
| authorships[0].institutions[1].display_name | Institute of High Performance Computing |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Chun-Mei Feng |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore |
| authorships[1].author.id | https://openalex.org/A5100692616 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6752-6216 |
| authorships[1].author.display_name | Kai Yu |
| authorships[1].countries | SG |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I115228651, https://openalex.org/I3004594783 |
| authorships[1].affiliations[0].raw_affiliation_string | Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore |
| authorships[1].institutions[0].id | https://openalex.org/I115228651 |
| authorships[1].institutions[0].ror | https://ror.org/036wvzt09 |
| authorships[1].institutions[0].type | government |
| authorships[1].institutions[0].lineage | https://openalex.org/I115228651 |
| authorships[1].institutions[0].country_code | SG |
| authorships[1].institutions[0].display_name | Agency for Science, Technology and Research |
| authorships[1].institutions[1].id | https://openalex.org/I3004594783 |
| authorships[1].institutions[1].ror | https://ror.org/02n0ejh50 |
| authorships[1].institutions[1].type | facility |
| authorships[1].institutions[1].lineage | https://openalex.org/I115228651, https://openalex.org/I3004594783, https://openalex.org/I91275662 |
| authorships[1].institutions[1].country_code | SG |
| authorships[1].institutions[1].display_name | Institute of High Performance Computing |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Kai Yu |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore |
| authorships[2].author.id | https://openalex.org/A5067953198 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1449-3072 |
| authorships[2].author.display_name | Xinxing Xu |
| authorships[2].affiliations[0].raw_affiliation_string | Microsoft Research Asia Singapore, Singapore |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xinxing Xu |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Microsoft Research Asia Singapore, Singapore |
| authorships[3].author.id | https://openalex.org/A5000300751 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-9502-1749 |
| authorships[3].author.display_name | Salman Khan |
| authorships[3].countries | AE |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I4210113480 |
| authorships[3].affiliations[0].raw_affiliation_string | Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), UAE |
| authorships[3].institutions[0].id | https://openalex.org/I4210113480 |
| authorships[3].institutions[0].ror | https://ror.org/0258gkt32 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I4210113480 |
| authorships[3].institutions[0].country_code | AE |
| authorships[3].institutions[0].display_name | Mohamed bin Zayed University of Artificial Intelligence |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Salman Khan |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), UAE |
| authorships[4].author.id | https://openalex.org/A5001599295 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-9116-1595 |
| authorships[4].author.display_name | Rick Siow Mong Goh |
| authorships[4].countries | SG |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I115228651, https://openalex.org/I3004594783 |
| authorships[4].affiliations[0].raw_affiliation_string | Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore |
| authorships[4].institutions[0].id | https://openalex.org/I115228651 |
| authorships[4].institutions[0].ror | https://ror.org/036wvzt09 |
| authorships[4].institutions[0].type | government |
| authorships[4].institutions[0].lineage | https://openalex.org/I115228651 |
| authorships[4].institutions[0].country_code | SG |
| authorships[4].institutions[0].display_name | Agency for Science, Technology and Research |
| authorships[4].institutions[1].id | https://openalex.org/I3004594783 |
| authorships[4].institutions[1].ror | https://ror.org/02n0ejh50 |
| authorships[4].institutions[1].type | facility |
| authorships[4].institutions[1].lineage | https://openalex.org/I115228651, https://openalex.org/I3004594783, https://openalex.org/I91275662 |
| authorships[4].institutions[1].country_code | SG |
| authorships[4].institutions[1].display_name | Institute of High Performance Computing |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Rick Siow Mong Goh |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore |
| authorships[5].author.id | https://openalex.org/A5100636655 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-3330-783X |
| authorships[5].author.display_name | Wangmeng Zuo |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I204983213 |
| authorships[5].affiliations[0].raw_affiliation_string | Harbin Institute of Technology, Harbin, China |
| authorships[5].institutions[0].id | https://openalex.org/I204983213 |
| authorships[5].institutions[0].ror | https://ror.org/01yqg2h08 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I204983213 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | Harbin Institute of Technology |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Wangmeng Zuo |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Harbin Institute of Technology, Harbin, China |
| authorships[6].author.id | https://openalex.org/A5006207459 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-1590-2029 |
| authorships[6].author.display_name | Yong Liu |
| authorships[6].countries | SG |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I115228651, https://openalex.org/I3004594783 |
| authorships[6].affiliations[0].raw_affiliation_string | Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore |
| authorships[6].institutions[0].id | https://openalex.org/I115228651 |
| authorships[6].institutions[0].ror | https://ror.org/036wvzt09 |
| authorships[6].institutions[0].type | government |
| authorships[6].institutions[0].lineage | https://openalex.org/I115228651 |
| authorships[6].institutions[0].country_code | SG |
| authorships[6].institutions[0].display_name | Agency for Science, Technology and Research |
| authorships[6].institutions[1].id | https://openalex.org/I3004594783 |
| authorships[6].institutions[1].ror | https://ror.org/02n0ejh50 |
| authorships[6].institutions[1].type | facility |
| authorships[6].institutions[1].lineage | https://openalex.org/I115228651, https://openalex.org/I3004594783, https://openalex.org/I91275662 |
| authorships[6].institutions[1].country_code | SG |
| authorships[6].institutions[1].display_name | Institute of High Performance Computing |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Yong Liu |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore |
| 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/2506.10575 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10601 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9883000254631042 |
| 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 | Handwritten Text Recognition Techniques |
| related_works | https://openalex.org/W2133028525, https://openalex.org/W4229060448, https://openalex.org/W4306381730, https://openalex.org/W2981692913, https://openalex.org/W3044188621, https://openalex.org/W3184035966, https://openalex.org/W2485605994, https://openalex.org/W2160602540, https://openalex.org/W4385571108, https://openalex.org/W4200251711 |
| cited_by_count | 0 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:arXiv.org:2506.10575 |
| 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/2506.10575 |
| 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/2506.10575 |
| primary_location.id | doi:10.1109/tpami.2025.3573852 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S199944782 |
| primary_location.source.issn | 0162-8828, 1939-3539, 2160-9292 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 0162-8828 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320439 |
| primary_location.source.host_organization_name | IEEE Computer Society |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320439, https://openalex.org/P4310319808 |
| primary_location.source.host_organization_lineage_names | IEEE Computer Society, Institute of Electrical and Electronics Engineers |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1109/tpami.2025.3573852 |
| publication_date | 2025-05-26 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W6810334672, https://openalex.org/W2917792613, https://openalex.org/W4225930680, https://openalex.org/W2963676620, https://openalex.org/W2982112268, https://openalex.org/W2932399282, https://openalex.org/W3034600949, https://openalex.org/W2007972815, https://openalex.org/W2969792713, https://openalex.org/W2031489346, https://openalex.org/W6630792627, https://openalex.org/W3096831136, https://openalex.org/W4386113259, https://openalex.org/W6845281891, https://openalex.org/W4407937652, https://openalex.org/W6631190155, https://openalex.org/W6640963894, https://openalex.org/W1861492603, https://openalex.org/W4312824283, https://openalex.org/W2890153145, https://openalex.org/W6757817989, https://openalex.org/W4393148714, https://openalex.org/W3202858701, https://openalex.org/W6810940779, https://openalex.org/W4385567053, https://openalex.org/W6854511533, https://openalex.org/W4226342448, https://openalex.org/W6791353385, https://openalex.org/W6809885388, https://openalex.org/W4409262898, https://openalex.org/W4312933868, https://openalex.org/W4386072096, https://openalex.org/W6838639034, https://openalex.org/W4212944375, https://openalex.org/W6803272276, https://openalex.org/W6839546733, https://openalex.org/W4312884055, https://openalex.org/W6850625674, https://openalex.org/W6846260888, https://openalex.org/W2963745697, https://openalex.org/W2521365688, https://openalex.org/W2998420437, https://openalex.org/W2963300078, https://openalex.org/W4401024541, https://openalex.org/W3034472074, https://openalex.org/W4313175608, https://openalex.org/W3202884348, https://openalex.org/W4312310776, https://openalex.org/W3198377975, https://openalex.org/W4390873714 |
| referenced_works_count | 50 |
| abstract_inverted_index.a | 42, 62, 112 |
| abstract_inverted_index.To | 106 |
| abstract_inverted_index.an | 58 |
| abstract_inverted_index.as | 15, 57 |
| abstract_inverted_index.be | 31 |
| abstract_inverted_index.by | 209 |
| abstract_inverted_index.in | 211 |
| abstract_inverted_index.is | 24, 85 |
| abstract_inverted_index.it | 156, 173 |
| abstract_inverted_index.of | 26, 50, 83, 125, 178 |
| abstract_inverted_index.on | 193 |
| abstract_inverted_index.to | 11, 30, 33, 67, 86, 92, 148 |
| abstract_inverted_index.we | 60, 139 |
| abstract_inverted_index.For | 136 |
| abstract_inverted_index.The | 80 |
| abstract_inverted_index.and | 45, 95, 115, 131, 145, 172, 199 |
| abstract_inverted_index.any | 187 |
| abstract_inverted_index.can | 205 |
| abstract_inverted_index.for | 18, 78, 133, 160, 183 |
| abstract_inverted_index.gap | 40, 71 |
| abstract_inverted_index.our | 203 |
| abstract_inverted_index.the | 34, 38, 69, 103, 123, 158, 168, 175, 179, 214 |
| abstract_inverted_index.CLIP | 23, 180, 189 |
| abstract_inverted_index.MLR, | 109 |
| abstract_inverted_index.TaI. | 51 |
| abstract_inverted_index.This | 118 |
| abstract_inverted_index.both | 142 |
| abstract_inverted_index.core | 81 |
| abstract_inverted_index.from | 1, 98 |
| abstract_inverted_index.gap. | 105 |
| abstract_inverted_index.mode | 177 |
| abstract_inverted_index.more | 129 |
| abstract_inverted_index.need | 159 |
| abstract_inverted_index.only | 75 |
| abstract_inverted_index.show | 201 |
| abstract_inverted_index.text | 36, 76, 99 |
| abstract_inverted_index.that | 202 |
| abstract_inverted_index.when | 73 |
| abstract_inverted_index.with | 186 |
| abstract_inverted_index.(MLR) | 56 |
| abstract_inverted_index.(TaI) | 17 |
| abstract_inverted_index.3.47% | 210 |
| abstract_inverted_index.CLIP, | 9 |
| abstract_inverted_index.PEFT, | 138 |
| abstract_inverted_index.PEFT. | 79 |
| abstract_inverted_index.Using | 52 |
| abstract_inverted_index.While | 22 |
| abstract_inverted_index.above | 213 |
| abstract_inverted_index.allow | 10 |
| abstract_inverted_index.boost | 206 |
| abstract_inverted_index.e.g., | 8 |
| abstract_inverted_index.fully | 161 |
| abstract_inverted_index.image | 28, 47, 54 |
| abstract_inverted_index.issue | 44, 72 |
| abstract_inverted_index.local | 120, 126 |
| abstract_inverted_index.novel | 63 |
| abstract_inverted_index.texts | 14 |
| abstract_inverted_index.using | 74 |
| abstract_inverted_index.better | 137 |
| abstract_inverted_index.called | 65 |
| abstract_inverted_index.design | 82 |
| abstract_inverted_index.direct | 12 |
| abstract_inverted_index.images | 16, 97 |
| abstract_inverted_index.limits | 46 |
| abstract_inverted_index.making | 27, 122 |
| abstract_inverted_index.manual | 169 |
| abstract_inverted_index.model, | 181 |
| abstract_inverted_index.models | 91 |
| abstract_inverted_index.offers | 153 |
| abstract_inverted_index.prompt | 143 |
| abstract_inverted_index.robust | 130 |
| abstract_inverted_index.tackle | 68 |
| abstract_inverted_index.tuning | 144 |
| abstract_inverted_index.visual | 127 |
| abstract_inverted_index.(PEFT). | 21 |
| abstract_inverted_index.T2I-PAL | 66, 84, 110, 152, 204 |
| abstract_inverted_index.adapter | 146 |
| abstract_inverted_index.average | 212 |
| abstract_inverted_index.capable | 25 |
| abstract_inverted_index.combine | 141 |
| abstract_inverted_index.diverse | 96 |
| abstract_inverted_index.enhance | 108, 149 |
| abstract_inverted_index.further | 107, 140 |
| abstract_inverted_index.heatmap | 114 |
| abstract_inverted_index.images, | 165 |
| abstract_inverted_index.method, | 64 |
| abstract_inverted_index.models, | 7 |
| abstract_inverted_index.present | 61 |
| abstract_inverted_index.remains | 41 |
| abstract_inverted_index.similar | 32 |
| abstract_inverted_index.thereby | 101, 166 |
| abstract_inverted_index.MS-COCO, | 197 |
| abstract_inverted_index.VOC2007, | 198 |
| abstract_inverted_index.allowing | 182 |
| abstract_inverted_index.captions | 77 |
| abstract_inverted_index.example, | 59 |
| abstract_inverted_index.existing | 188 |
| abstract_inverted_index.features | 29, 128 |
| abstract_inverted_index.generate | 93 |
| abstract_inverted_index.learning | 147 |
| abstract_inverted_index.leverage | 13, 87 |
| abstract_inverted_index.methods. | 217 |
| abstract_inverted_index.modality | 39, 70, 104 |
| abstract_inverted_index.multiple | 194 |
| abstract_inverted_index.reducing | 102, 167 |
| abstract_inverted_index.seamless | 184 |
| abstract_inverted_index.training | 164 |
| abstract_inverted_index.Benefited | 0 |
| abstract_inverted_index.Extensive | 191 |
| abstract_inverted_index.NUS-WIDE, | 200 |
| abstract_inverted_index.annotated | 163 |
| abstract_inverted_index.captions, | 100 |
| abstract_inverted_index.features, | 37 |
| abstract_inverted_index.including | 196 |
| abstract_inverted_index.intrinsic | 176 |
| abstract_inverted_index.learnable | 116 |
| abstract_inverted_index.learning, | 4 |
| abstract_inverted_index.preserves | 174 |
| abstract_inverted_index.workload, | 171 |
| abstract_inverted_index.aggregates | 119 |
| abstract_inverted_index.annotation | 170 |
| abstract_inverted_index.class-wise | 113 |
| abstract_inverted_index.eliminates | 157 |
| abstract_inverted_index.framework. | 190 |
| abstract_inverted_index.generation | 90 |
| abstract_inverted_index.image-text | 2 |
| abstract_inverted_index.nontrivial | 43 |
| abstract_inverted_index.top-ranked | 215 |
| abstract_inverted_index.advantages: | 155 |
| abstract_inverted_index.benchmarks, | 195 |
| abstract_inverted_index.contrastive | 3 |
| abstract_inverted_index.experiments | 192 |
| abstract_inverted_index.fine-tuning | 20 |
| abstract_inverted_index.informative | 132 |
| abstract_inverted_index.integration | 185 |
| abstract_inverted_index.multi-label | 53, 134 |
| abstract_inverted_index.performance | 49, 208 |
| abstract_inverted_index.pre-trained | 5, 88 |
| abstract_inverted_index.prototypes. | 117 |
| abstract_inverted_index.recognition | 48, 55, 207 |
| abstract_inverted_index.significant | 154 |
| abstract_inverted_index.incorporates | 111 |
| abstract_inverted_index.performance. | 151 |
| abstract_inverted_index.recognition. | 135 |
| abstract_inverted_index.semantically | 162 |
| abstract_inverted_index.corresponding | 35 |
| abstract_inverted_index.similarities, | 121 |
| abstract_inverted_index.text-to-image | 89 |
| abstract_inverted_index.classification | 150 |
| abstract_inverted_index.representation | 124 |
| abstract_inverted_index.photo-realistic | 94 |
| abstract_inverted_index.vision-language | 6 |
| abstract_inverted_index.state-of-the-art | 216 |
| abstract_inverted_index.parameter-efficient | 19 |
| cited_by_percentile_year | |
| countries_distinct_count | 3 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile.value | 0.18302579 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |