CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models Article Swipe
Yuan Yao
,
Ao Zhang
,
Zhengyan Zhang
,
Zhiyuan Liu
,
Tat‐Seng Chua
,
Maosong Sun
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2109.11797
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2109.11797
Pre-Trained Vision-Language Models (VL-PTMs) have shown promising capabilities in grounding natural language in image data, facilitating a broad variety of cross-modal tasks. However, we note that there exists a significant gap between the objective forms of model pre-training and fine-tuning, resulting in a need for large amounts of labeled data to stimulate the visual grounding capability of VL-PTMs for downstream tasks. To address the challenge, we present Cross-modal Prompt Tuning (CPT, alternatively, Colorful Prompt Tuning), a novel paradigm for tuning VL-PTMs, which reformulates visual grounding into a fill-in-the-blank problem with color-based co-referential markers in image and text, maximally mitigating the gap. In this way, CPT enables strong few-shot and even zero-shot visual grounding capabilities of VL-PTMs. Comprehensive experimental results show that the prompt-tuned VL-PTMs outperform their fine-tuned counterparts by a large margin (e.g., 17.3% absolute accuracy improvement, and 73.8% relative standard deviation reduction on average with one shot in RefCOCO evaluation). We make the data and code for this paper publicly available at https://github.com/thunlp/CPT.
Related Topics
Concepts
Computer science
Modal
Margin (machine learning)
Code (set theory)
Shot (pellet)
Contrast (vision)
Image (mathematics)
Variety (cybernetics)
One shot
Artificial intelligence
Pattern recognition (psychology)
Machine learning
Engineering
Chemistry
Programming language
Organic chemistry
Set (abstract data type)
Polymer chemistry
Mechanical engineering
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2109.11797
- https://arxiv.org/pdf/2109.11797
- OA Status
- green
- Cited By
- 86
- References
- 45
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3204250462
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3204250462Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2109.11797Digital Object Identifier
- Title
-
CPT: Colorful Prompt Tuning for Pre-trained Vision-Language ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-09-24Full publication date if available
- Authors
-
Yuan Yao, Ao Zhang, Zhengyan Zhang, Zhiyuan Liu, Tat‐Seng Chua, Maosong SunList of authors in order
- Landing page
-
https://arxiv.org/abs/2109.11797Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2109.11797Direct 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/2109.11797Direct OA link when available
- Concepts
-
Computer science, Modal, Margin (machine learning), Code (set theory), Shot (pellet), Contrast (vision), Image (mathematics), Variety (cybernetics), One shot, Artificial intelligence, Pattern recognition (psychology), Machine learning, Engineering, Chemistry, Programming language, Organic chemistry, Set (abstract data type), Polymer chemistry, Mechanical engineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
86Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2, 2024: 19, 2023: 51, 2022: 12, 2021: 2Per-year citation counts (last 5 years)
- References (count)
-
45Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3204250462 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2109.11797 |
| ids.doi | https://doi.org/10.48550/arxiv.2109.11797 |
| ids.mag | 3204250462 |
| ids.openalex | https://openalex.org/W3204250462 |
| fwci | |
| type | preprint |
| title | CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models |
| 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 | 1.0 |
| 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/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9988999962806702 |
| 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 | Domain Adaptation and Few-Shot Learning |
| topics[2].id | https://openalex.org/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9812999963760376 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Topic Modeling |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6882343292236328 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C71139939 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6723951101303101 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q910194 |
| concepts[1].display_name | Modal |
| concepts[2].id | https://openalex.org/C774472 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6035102009773254 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q6760393 |
| concepts[2].display_name | Margin (machine learning) |
| concepts[3].id | https://openalex.org/C2776760102 |
| concepts[3].level | 3 |
| concepts[3].score | 0.584287166595459 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q5139990 |
| concepts[3].display_name | Code (set theory) |
| concepts[4].id | https://openalex.org/C2778344882 |
| concepts[4].level | 2 |
| concepts[4].score | 0.578500509262085 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q278938 |
| concepts[4].display_name | Shot (pellet) |
| concepts[5].id | https://openalex.org/C2776502983 |
| concepts[5].level | 2 |
| concepts[5].score | 0.48831722140312195 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q690182 |
| concepts[5].display_name | Contrast (vision) |
| concepts[6].id | https://openalex.org/C115961682 |
| concepts[6].level | 2 |
| concepts[6].score | 0.46988821029663086 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[6].display_name | Image (mathematics) |
| concepts[7].id | https://openalex.org/C136197465 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4636380076408386 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1729295 |
| concepts[7].display_name | Variety (cybernetics) |
| concepts[8].id | https://openalex.org/C2992734406 |
| concepts[8].level | 2 |
| concepts[8].score | 0.45120182633399963 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q413267 |
| concepts[8].display_name | One shot |
| concepts[9].id | https://openalex.org/C154945302 |
| concepts[9].level | 1 |
| concepts[9].score | 0.443266898393631 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[9].display_name | Artificial intelligence |
| concepts[10].id | https://openalex.org/C153180895 |
| concepts[10].level | 2 |
| concepts[10].score | 0.3489796221256256 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[10].display_name | Pattern recognition (psychology) |
| concepts[11].id | https://openalex.org/C119857082 |
| concepts[11].level | 1 |
| concepts[11].score | 0.2966437339782715 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[11].display_name | Machine learning |
| concepts[12].id | https://openalex.org/C127413603 |
| concepts[12].level | 0 |
| concepts[12].score | 0.13637018203735352 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[12].display_name | Engineering |
| concepts[13].id | https://openalex.org/C185592680 |
| concepts[13].level | 0 |
| concepts[13].score | 0.09748134016990662 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[13].display_name | Chemistry |
| concepts[14].id | https://openalex.org/C199360897 |
| concepts[14].level | 1 |
| concepts[14].score | 0.08922946453094482 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[14].display_name | Programming language |
| concepts[15].id | https://openalex.org/C178790620 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q11351 |
| concepts[15].display_name | Organic chemistry |
| concepts[16].id | https://openalex.org/C177264268 |
| concepts[16].level | 2 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[16].display_name | Set (abstract data type) |
| concepts[17].id | https://openalex.org/C188027245 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q750446 |
| concepts[17].display_name | Polymer chemistry |
| concepts[18].id | https://openalex.org/C78519656 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q101333 |
| concepts[18].display_name | Mechanical engineering |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6882343292236328 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/modal |
| keywords[1].score | 0.6723951101303101 |
| keywords[1].display_name | Modal |
| keywords[2].id | https://openalex.org/keywords/margin |
| keywords[2].score | 0.6035102009773254 |
| keywords[2].display_name | Margin (machine learning) |
| keywords[3].id | https://openalex.org/keywords/code |
| keywords[3].score | 0.584287166595459 |
| keywords[3].display_name | Code (set theory) |
| keywords[4].id | https://openalex.org/keywords/shot |
| keywords[4].score | 0.578500509262085 |
| keywords[4].display_name | Shot (pellet) |
| keywords[5].id | https://openalex.org/keywords/contrast |
| keywords[5].score | 0.48831722140312195 |
| keywords[5].display_name | Contrast (vision) |
| keywords[6].id | https://openalex.org/keywords/image |
| keywords[6].score | 0.46988821029663086 |
| keywords[6].display_name | Image (mathematics) |
| keywords[7].id | https://openalex.org/keywords/variety |
| keywords[7].score | 0.4636380076408386 |
| keywords[7].display_name | Variety (cybernetics) |
| keywords[8].id | https://openalex.org/keywords/one-shot |
| keywords[8].score | 0.45120182633399963 |
| keywords[8].display_name | One shot |
| keywords[9].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[9].score | 0.443266898393631 |
| keywords[9].display_name | Artificial intelligence |
| keywords[10].id | https://openalex.org/keywords/pattern-recognition |
| keywords[10].score | 0.3489796221256256 |
| keywords[10].display_name | Pattern recognition (psychology) |
| keywords[11].id | https://openalex.org/keywords/machine-learning |
| keywords[11].score | 0.2966437339782715 |
| keywords[11].display_name | Machine learning |
| keywords[12].id | https://openalex.org/keywords/engineering |
| keywords[12].score | 0.13637018203735352 |
| keywords[12].display_name | Engineering |
| keywords[13].id | https://openalex.org/keywords/chemistry |
| keywords[13].score | 0.09748134016990662 |
| keywords[13].display_name | Chemistry |
| keywords[14].id | https://openalex.org/keywords/programming-language |
| keywords[14].score | 0.08922946453094482 |
| keywords[14].display_name | Programming language |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2109.11797 |
| 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/2109.11797 |
| 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/2109.11797 |
| locations[1].id | doi:10.48550/arxiv.2109.11797 |
| 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.2109.11797 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5103072099 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3616-2496 |
| authorships[0].author.display_name | Yuan Yao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yuan Yao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100437598 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1304-2181 |
| authorships[1].author.display_name | Ao Zhang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Ao Zhang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101584823 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2988-0083 |
| authorships[2].author.display_name | Zhengyan Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhengyan Zhang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100320723 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-7709-2543 |
| authorships[3].author.display_name | Zhiyuan Liu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhiyuan Liu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5089404640 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6097-7807 |
| authorships[4].author.display_name | Tat‐Seng Chua |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Tat-Seng Chua |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5046448314 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-6011-6115 |
| authorships[5].author.display_name | Maosong Sun |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Maosong Sun |
| authorships[5].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/2109.11797 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models |
| 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 | 1.0 |
| 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/W2497720472, https://openalex.org/W4292659306, https://openalex.org/W3044321615, https://openalex.org/W4294892107, https://openalex.org/W2806221744, https://openalex.org/W2326937258, https://openalex.org/W394267150, https://openalex.org/W2773965352, https://openalex.org/W2357748469, https://openalex.org/W2392917037 |
| cited_by_count | 86 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 19 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 51 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 12 |
| counts_by_year[4].year | 2021 |
| counts_by_year[4].cited_by_count | 2 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2109.11797 |
| 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/2109.11797 |
| 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/2109.11797 |
| primary_location.id | pmh:oai:arXiv.org:2109.11797 |
| 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/2109.11797 |
| 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/2109.11797 |
| publication_date | 2021-09-24 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W3135367836, https://openalex.org/W3044438666, https://openalex.org/W2963445828, https://openalex.org/W2963115613, https://openalex.org/W2745461083, https://openalex.org/W3132736064, https://openalex.org/W2970608575, https://openalex.org/W1933349210, https://openalex.org/W2251512949, https://openalex.org/W3119438769, https://openalex.org/W2986803748, https://openalex.org/W2963109634, https://openalex.org/W2981852735, https://openalex.org/W3173220247, https://openalex.org/W3166846774, https://openalex.org/W3177174258, https://openalex.org/W2962764817, https://openalex.org/W3005700362, https://openalex.org/W3198377975, https://openalex.org/W2964345792, https://openalex.org/W3172642864, https://openalex.org/W3030163527, https://openalex.org/W3153427360, https://openalex.org/W2970476646, https://openalex.org/W2963800628, https://openalex.org/W1861492603, https://openalex.org/W3099261920, https://openalex.org/W2236233024, https://openalex.org/W3173909648, https://openalex.org/W2768661419, https://openalex.org/W3090449556, https://openalex.org/W3172141633, https://openalex.org/W3177224328, https://openalex.org/W2489434015, https://openalex.org/W3185341429, https://openalex.org/W1905882502, https://openalex.org/W2613718673, https://openalex.org/W3098232790, https://openalex.org/W2277195237, https://openalex.org/W3173777717, https://openalex.org/W3193402170, https://openalex.org/W3129576130, https://openalex.org/W3091588028, https://openalex.org/W2963150697, https://openalex.org/W2970231061 |
| referenced_works_count | 45 |
| abstract_inverted_index.a | 16, 28, 42, 75, 86, 129 |
| abstract_inverted_index.In | 101 |
| abstract_inverted_index.To | 61 |
| abstract_inverted_index.We | 151 |
| abstract_inverted_index.at | 162 |
| abstract_inverted_index.by | 128 |
| abstract_inverted_index.in | 8, 12, 41, 93, 148 |
| abstract_inverted_index.of | 19, 35, 47, 56, 114 |
| abstract_inverted_index.on | 143 |
| abstract_inverted_index.to | 50 |
| abstract_inverted_index.we | 23, 65 |
| abstract_inverted_index.CPT | 104 |
| abstract_inverted_index.and | 38, 95, 108, 137, 155 |
| abstract_inverted_index.for | 44, 58, 78, 157 |
| abstract_inverted_index.gap | 30 |
| abstract_inverted_index.one | 146 |
| abstract_inverted_index.the | 32, 52, 63, 99, 121, 153 |
| abstract_inverted_index.code | 156 |
| abstract_inverted_index.data | 49, 154 |
| abstract_inverted_index.even | 109 |
| abstract_inverted_index.gap. | 100 |
| abstract_inverted_index.have | 4 |
| abstract_inverted_index.into | 85 |
| abstract_inverted_index.make | 152 |
| abstract_inverted_index.need | 43 |
| abstract_inverted_index.note | 24 |
| abstract_inverted_index.shot | 147 |
| abstract_inverted_index.show | 119 |
| abstract_inverted_index.that | 25, 120 |
| abstract_inverted_index.this | 102, 158 |
| abstract_inverted_index.way, | 103 |
| abstract_inverted_index.with | 89, 145 |
| abstract_inverted_index.(CPT, | 70 |
| abstract_inverted_index.17.3% | 133 |
| abstract_inverted_index.73.8% | 138 |
| abstract_inverted_index.broad | 17 |
| abstract_inverted_index.data, | 14 |
| abstract_inverted_index.forms | 34 |
| abstract_inverted_index.image | 13, 94 |
| abstract_inverted_index.large | 45, 130 |
| abstract_inverted_index.model | 36 |
| abstract_inverted_index.novel | 76 |
| abstract_inverted_index.paper | 159 |
| abstract_inverted_index.shown | 5 |
| abstract_inverted_index.text, | 96 |
| abstract_inverted_index.their | 125 |
| abstract_inverted_index.there | 26 |
| abstract_inverted_index.which | 81 |
| abstract_inverted_index.(e.g., | 132 |
| abstract_inverted_index.Models | 2 |
| abstract_inverted_index.Prompt | 68, 73 |
| abstract_inverted_index.Tuning | 69 |
| abstract_inverted_index.exists | 27 |
| abstract_inverted_index.margin | 131 |
| abstract_inverted_index.strong | 106 |
| abstract_inverted_index.tasks. | 21, 60 |
| abstract_inverted_index.tuning | 79 |
| abstract_inverted_index.visual | 53, 83, 111 |
| abstract_inverted_index.RefCOCO | 149 |
| abstract_inverted_index.VL-PTMs | 57, 123 |
| abstract_inverted_index.address | 62 |
| abstract_inverted_index.amounts | 46 |
| abstract_inverted_index.average | 144 |
| abstract_inverted_index.between | 31 |
| abstract_inverted_index.enables | 105 |
| abstract_inverted_index.labeled | 48 |
| abstract_inverted_index.markers | 92 |
| abstract_inverted_index.natural | 10 |
| abstract_inverted_index.present | 66 |
| abstract_inverted_index.problem | 88 |
| abstract_inverted_index.results | 118 |
| abstract_inverted_index.variety | 18 |
| abstract_inverted_index.Colorful | 72 |
| abstract_inverted_index.However, | 22 |
| abstract_inverted_index.Tuning), | 74 |
| abstract_inverted_index.VL-PTMs, | 80 |
| abstract_inverted_index.VL-PTMs. | 115 |
| abstract_inverted_index.absolute | 134 |
| abstract_inverted_index.accuracy | 135 |
| abstract_inverted_index.few-shot | 107 |
| abstract_inverted_index.language | 11 |
| abstract_inverted_index.paradigm | 77 |
| abstract_inverted_index.publicly | 160 |
| abstract_inverted_index.relative | 139 |
| abstract_inverted_index.standard | 140 |
| abstract_inverted_index.(VL-PTMs) | 3 |
| abstract_inverted_index.available | 161 |
| abstract_inverted_index.deviation | 141 |
| abstract_inverted_index.grounding | 9, 54, 84, 112 |
| abstract_inverted_index.maximally | 97 |
| abstract_inverted_index.objective | 33 |
| abstract_inverted_index.promising | 6 |
| abstract_inverted_index.reduction | 142 |
| abstract_inverted_index.resulting | 40 |
| abstract_inverted_index.stimulate | 51 |
| abstract_inverted_index.zero-shot | 110 |
| abstract_inverted_index.capability | 55 |
| abstract_inverted_index.challenge, | 64 |
| abstract_inverted_index.downstream | 59 |
| abstract_inverted_index.fine-tuned | 126 |
| abstract_inverted_index.mitigating | 98 |
| abstract_inverted_index.outperform | 124 |
| abstract_inverted_index.Cross-modal | 67 |
| abstract_inverted_index.Pre-Trained | 0 |
| abstract_inverted_index.color-based | 90 |
| abstract_inverted_index.cross-modal | 20 |
| abstract_inverted_index.significant | 29 |
| abstract_inverted_index.capabilities | 7, 113 |
| abstract_inverted_index.counterparts | 127 |
| abstract_inverted_index.evaluation). | 150 |
| abstract_inverted_index.experimental | 117 |
| abstract_inverted_index.facilitating | 15 |
| abstract_inverted_index.fine-tuning, | 39 |
| abstract_inverted_index.improvement, | 136 |
| abstract_inverted_index.pre-training | 37 |
| abstract_inverted_index.prompt-tuned | 122 |
| abstract_inverted_index.reformulates | 82 |
| abstract_inverted_index.Comprehensive | 116 |
| abstract_inverted_index.alternatively, | 71 |
| abstract_inverted_index.co-referential | 91 |
| abstract_inverted_index.Vision-Language | 1 |
| abstract_inverted_index.fill-in-the-blank | 87 |
| abstract_inverted_index.https://github.com/thunlp/CPT. | 163 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.6100000143051147 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |