Vision-Language Modeling Meets Remote Sensing: Models, datasets, and perspectives Article Swipe
Xingxing Weng
,
Chao Pang
,
Gui-Song Xia
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1109/mgrs.2025.3572702
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1109/mgrs.2025.3572702
Vision-language modeling (VLM) aims to bridge the information gap between images and natural language. Under the new paradigm of first pre-training on massive image-text pairs and then fine-tuning on task-specific data, VLM in the remote sensing domain has made significant progress. The resulting models benefit from the absorption of extensive general knowledge and demonstrate strong performance across a variety of remote sensing data analysis tasks. Moreover, they are capable of interacting with users in a conversational manner. In this paper, we aim to provide the remote sensing community with a timely and comprehensive review of the developments in VLM using the two-stage paradigm. Specifically, we first cover a taxonomy of VLM in remote sensing: contrastive learning, visual instruction tuning, and text-conditioned image generation. For each category, we detail the commonly used network architecture and pre-training objectives. Second, we conduct a thorough review of existing works, examining foundation models and task-specific adaptation methods in contrastive-based VLM, architectural upgrades, training strategies and model capabilities in instruction-based VLM, as well as generative foundation models with their representative downstream applications. Third, we summarize datasets used for VLM pre-training, fine-tuning, and evaluation, with an analysis of their construction methodologies (including image sources and caption generation) and key properties, such as scale and task adaptability. Finally, we conclude this survey with insights and discussions on future research directions: cross-modal representation alignment, vague requirement comprehension, explanation-driven model reliability, continually scalable model capabilities, and large-scale datasets featuring richer modalities and greater challenges.
Related Topics
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/mgrs.2025.3572702
- OA Status
- green
- Cited By
- 5
- References
- 211
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4411143162
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4411143162Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/mgrs.2025.3572702Digital Object Identifier
- Title
-
Vision-Language Modeling Meets Remote Sensing: Models, datasets, and perspectivesWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-06-09Full publication date if available
- Authors
-
Xingxing Weng, Chao Pang, Gui-Song XiaList of authors in order
- Landing page
-
https://doi.org/10.1109/mgrs.2025.3572702Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2505.14361Direct OA link when available
- Concepts
-
Remote sensing, Computer science, Artificial intelligence, GeologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
5Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 5Per-year citation counts (last 5 years)
- References (count)
-
211Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4411143162 |
|---|---|
| doi | https://doi.org/10.1109/mgrs.2025.3572702 |
| ids.doi | https://doi.org/10.1109/mgrs.2025.3572702 |
| ids.openalex | https://openalex.org/W4411143162 |
| fwci | 96.51199847 |
| type | article |
| title | Vision-Language Modeling Meets Remote Sensing: Models, datasets, and perspectives |
| biblio.issue | 3 |
| biblio.volume | 13 |
| biblio.last_page | 323 |
| biblio.first_page | 276 |
| topics[0].id | https://openalex.org/T10757 |
| topics[0].field.id | https://openalex.org/fields/33 |
| topics[0].field.display_name | Social Sciences |
| topics[0].score | 0.7519000172615051 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3305 |
| topics[0].subfield.display_name | Geography, Planning and Development |
| topics[0].display_name | Geographic Information Systems Studies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C62649853 |
| concepts[0].level | 1 |
| concepts[0].score | 0.6243234872817993 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q199687 |
| concepts[0].display_name | Remote sensing |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6112210750579834 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.36977967619895935 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C127313418 |
| concepts[3].level | 0 |
| concepts[3].score | 0.16740137338638306 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1069 |
| concepts[3].display_name | Geology |
| keywords[0].id | https://openalex.org/keywords/remote-sensing |
| keywords[0].score | 0.6243234872817993 |
| keywords[0].display_name | Remote sensing |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6112210750579834 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.36977967619895935 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/geology |
| keywords[3].score | 0.16740137338638306 |
| keywords[3].display_name | Geology |
| language | en |
| locations[0].id | doi:10.1109/mgrs.2025.3572702 |
| locations[0].is_oa | False |
| locations[0].source.id | https://openalex.org/S2491948244 |
| locations[0].source.issn | 2168-6831, 2373-7468, 2473-2397 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 2168-6831 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | IEEE Geoscience and Remote Sensing Magazine |
| locations[0].source.host_organization | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_name | Institute of Electrical and Electronics Engineers |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_lineage_names | 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 Geoscience and Remote Sensing Magazine |
| locations[0].landing_page_url | https://doi.org/10.1109/mgrs.2025.3572702 |
| locations[1].id | pmh:oai:arXiv.org:2505.14361 |
| 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 | https://arxiv.org/pdf/2505.14361 |
| 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 | |
| locations[1].landing_page_url | http://arxiv.org/abs/2505.14361 |
| indexed_in | arxiv, crossref |
| authorships[0].author.id | https://openalex.org/A5071887817 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-3326-8439 |
| authorships[0].author.display_name | Xingxing Weng |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I37461747 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Computer Science, Wuhan University, Wuhan, China |
| authorships[0].institutions[0].id | https://openalex.org/I37461747 |
| authorships[0].institutions[0].ror | https://ror.org/033vjfk17 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I37461747 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Wuhan University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xingxing Weng |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Computer Science, Wuhan University, Wuhan, China |
| authorships[1].author.id | https://openalex.org/A5073051182 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4315-024X |
| authorships[1].author.display_name | Chao Pang |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I37461747 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Artificial Intelligence, Wuhan University, Wuhan, China |
| authorships[1].institutions[0].id | https://openalex.org/I37461747 |
| authorships[1].institutions[0].ror | https://ror.org/033vjfk17 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I37461747 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Wuhan University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chao Pang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Artificial Intelligence, Wuhan University, Wuhan, China |
| authorships[2].author.id | https://openalex.org/A5073032922 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7660-6090 |
| authorships[2].author.display_name | Gui-Song Xia |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I37461747 |
| authorships[2].affiliations[0].raw_affiliation_string | School of Computer Science, Wuhan University, Wuhan, China |
| authorships[2].institutions[0].id | https://openalex.org/I37461747 |
| authorships[2].institutions[0].ror | https://ror.org/033vjfk17 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I37461747 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Wuhan University |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Gui-Song Xia |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | School of Computer Science, Wuhan University, Wuhan, China |
| 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/2505.14361 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Vision-Language Modeling Meets Remote Sensing: Models, datasets, and perspectives |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10757 |
| primary_topic.field.id | https://openalex.org/fields/33 |
| primary_topic.field.display_name | Social Sciences |
| primary_topic.score | 0.7519000172615051 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3305 |
| primary_topic.subfield.display_name | Geography, Planning and Development |
| primary_topic.display_name | Geographic Information Systems Studies |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 5 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 5 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2505.14361 |
| 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/2505.14361 |
| 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/2505.14361 |
| primary_location.id | doi:10.1109/mgrs.2025.3572702 |
| primary_location.is_oa | False |
| primary_location.source.id | https://openalex.org/S2491948244 |
| primary_location.source.issn | 2168-6831, 2373-7468, 2473-2397 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 2168-6831 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | IEEE Geoscience and Remote Sensing Magazine |
| primary_location.source.host_organization | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_lineage_names | 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 Geoscience and Remote Sensing Magazine |
| primary_location.landing_page_url | https://doi.org/10.1109/mgrs.2025.3572702 |
| publication_date | 2025-06-09 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4394966885, https://openalex.org/W2510520237, https://openalex.org/W3012111773, https://openalex.org/W3004137323, https://openalex.org/W2919929126, https://openalex.org/W2973586224, https://openalex.org/W3011916860, https://openalex.org/W3154766321, https://openalex.org/W4220716465, https://openalex.org/W2194775991, https://openalex.org/W2064675550, https://openalex.org/W4385245566, https://openalex.org/W4402473945, https://openalex.org/W4393159564, https://openalex.org/W4409383105, https://openalex.org/W4402776460, https://openalex.org/W2138621090, https://openalex.org/W4394938913, https://openalex.org/W4402124974, https://openalex.org/W4404536218, https://openalex.org/W4312933868, https://openalex.org/W4282968790, https://openalex.org/W4390873118, https://openalex.org/W4386075882, https://openalex.org/W4387402974, https://openalex.org/W4400977318, https://openalex.org/W4388752343, https://openalex.org/W4324258884, https://openalex.org/W4412531963, https://openalex.org/W4408013552, https://openalex.org/W4409367667, https://openalex.org/W4407152340, https://openalex.org/W4405895891, https://openalex.org/W4402674165, https://openalex.org/W4409263230, https://openalex.org/W4414563896, https://openalex.org/W4404741162, https://openalex.org/W4401510256, https://openalex.org/W4408840974, https://openalex.org/W4401070677, https://openalex.org/W4401516150, https://openalex.org/W3094502228, https://openalex.org/W2592962403, https://openalex.org/W2963785576, https://openalex.org/W2587639398, https://openalex.org/W4409368417, https://openalex.org/W3152083889, https://openalex.org/W2986943971, https://openalex.org/W2515866431, https://openalex.org/W2964194231, https://openalex.org/W3091842132, https://openalex.org/W2890732922, https://openalex.org/W2626107033, https://openalex.org/W1958291604, https://openalex.org/W2466055095, https://openalex.org/W3012326541, https://openalex.org/W2779054585, https://openalex.org/W2294802479, https://openalex.org/W1980038761, https://openalex.org/W3165084071, https://openalex.org/W4323824384, https://openalex.org/W4302275239, https://openalex.org/W4391305855, https://openalex.org/W4404371572, https://openalex.org/W4391136447, https://openalex.org/W4387350510, https://openalex.org/W4403827182, https://openalex.org/W4402260693, https://openalex.org/W4404914849, https://openalex.org/W2737434030, https://openalex.org/W4404481310, https://openalex.org/W4399534251, https://openalex.org/W4312420092, https://openalex.org/W4413157547, https://openalex.org/W4402258974, https://openalex.org/W4390848649, https://openalex.org/W4391892563, https://openalex.org/W4285818301, https://openalex.org/W4387803671, https://openalex.org/W4400229943, https://openalex.org/W4403921858, https://openalex.org/W2896457183, https://openalex.org/W4386790226, https://openalex.org/W3188086824, https://openalex.org/W2561529111, https://openalex.org/W4390874575, https://openalex.org/W3180045188, https://openalex.org/W4312549298, https://openalex.org/W3198377975, https://openalex.org/W4386076522, https://openalex.org/W4399399400, https://openalex.org/W2251512949, https://openalex.org/W2489434015, https://openalex.org/W4403919659, https://openalex.org/W4402727764, https://openalex.org/W4395041667, https://openalex.org/W4404784276, https://openalex.org/W4389518760, https://openalex.org/W2101105183, https://openalex.org/W1956340063, https://openalex.org/W4292968451, https://openalex.org/W2020912318, https://openalex.org/W4304084012, https://openalex.org/W4322707256, https://openalex.org/W3006792692, https://openalex.org/W3134231019, https://openalex.org/W3015756600, https://openalex.org/W4401857575, https://openalex.org/W4285151875, https://openalex.org/W4317877833, https://openalex.org/W4390874514, https://openalex.org/W4390873054, https://openalex.org/W4402917057, https://openalex.org/W2952773607, https://openalex.org/W4410115177, https://openalex.org/W2526483905, https://openalex.org/W4403117661, https://openalex.org/W845365781, https://openalex.org/W3186564193, https://openalex.org/W2473464331, https://openalex.org/W3094897602, https://openalex.org/W4388936927, https://openalex.org/W4391093042, https://openalex.org/W4366377770, https://openalex.org/W4389610328, https://openalex.org/W4402451527, https://openalex.org/W4379057906, https://openalex.org/W4366827602, https://openalex.org/W4393864405, https://openalex.org/W4392450086, https://openalex.org/W4386275830, https://openalex.org/W4403980953, https://openalex.org/W3155072588, https://openalex.org/W4409261944, https://openalex.org/W4392174019, https://openalex.org/W4405598832, https://openalex.org/W4378194624, https://openalex.org/W4312443924, https://openalex.org/W4408767510, https://openalex.org/W4409365606, https://openalex.org/W4410549634, https://openalex.org/W3201797941, https://openalex.org/W2992240579, https://openalex.org/W3097157418, https://openalex.org/W2577537809, https://openalex.org/W2962921175, https://openalex.org/W2935079508, https://openalex.org/W3027225766, https://openalex.org/W2519586580, https://openalex.org/W3205100603, https://openalex.org/W2594177559, https://openalex.org/W2963474852, https://openalex.org/W2199890863, https://openalex.org/W4387026640, https://openalex.org/W4390872394, https://openalex.org/W2886641317, https://openalex.org/W3208364069, https://openalex.org/W3038948729, https://openalex.org/W3200733355, https://openalex.org/W4226456028, https://openalex.org/W3168972675, https://openalex.org/W3196922338, https://openalex.org/W3175205795, https://openalex.org/W4366392594, https://openalex.org/W4391331851, https://openalex.org/W2908320224, https://openalex.org/W3028752951, https://openalex.org/W2296151615, https://openalex.org/W2779335303, https://openalex.org/W3133008479, https://openalex.org/W4386472879, https://openalex.org/W2979382172, https://openalex.org/W4366598917, https://openalex.org/W4404809967, https://openalex.org/W4362472800, https://openalex.org/W4221044012, https://openalex.org/W4313908836, https://openalex.org/W1824774525, https://openalex.org/W2804199516, https://openalex.org/W2991488782, https://openalex.org/W3176198174, https://openalex.org/W3184566187, https://openalex.org/W4403674734, https://openalex.org/W4402916392, https://openalex.org/W2963499661, https://openalex.org/W3176105227, https://openalex.org/W2945020140, https://openalex.org/W3093965839, https://openalex.org/W3156208778, https://openalex.org/W3007766931, https://openalex.org/W4318681845, https://openalex.org/W4403423082, https://openalex.org/W4391306135, https://openalex.org/W4323240445, https://openalex.org/W4392477514, https://openalex.org/W3185151088, https://openalex.org/W3118843071, https://openalex.org/W2340897893, https://openalex.org/W2103163130, https://openalex.org/W3108907096, https://openalex.org/W3179267034, https://openalex.org/W4403947192, https://openalex.org/W3092933908, https://openalex.org/W2592451672, https://openalex.org/W2945554431, https://openalex.org/W2211843587, https://openalex.org/W3201616222, https://openalex.org/W2964169840, https://openalex.org/W1912954554, https://openalex.org/W2580774552, https://openalex.org/W2605388673 |
| referenced_works_count | 211 |
| abstract_inverted_index.a | 57, 74, 89, 107, 139 |
| abstract_inverted_index.In | 77 |
| abstract_inverted_index.an | 188 |
| abstract_inverted_index.as | 165, 167, 204 |
| abstract_inverted_index.in | 32, 73, 97, 111, 152, 162 |
| abstract_inverted_index.of | 18, 48, 59, 69, 94, 109, 142, 190 |
| abstract_inverted_index.on | 21, 28, 218 |
| abstract_inverted_index.to | 4, 82 |
| abstract_inverted_index.we | 80, 104, 126, 137, 177, 210 |
| abstract_inverted_index.For | 123 |
| abstract_inverted_index.The | 41 |
| abstract_inverted_index.VLM | 31, 98, 110, 182 |
| abstract_inverted_index.aim | 81 |
| abstract_inverted_index.and | 11, 25, 52, 91, 119, 133, 148, 159, 185, 197, 200, 206, 216, 235, 241 |
| abstract_inverted_index.are | 67 |
| abstract_inverted_index.for | 181 |
| abstract_inverted_index.gap | 8 |
| abstract_inverted_index.has | 37 |
| abstract_inverted_index.key | 201 |
| abstract_inverted_index.new | 16 |
| abstract_inverted_index.the | 6, 15, 33, 46, 84, 95, 100, 128 |
| abstract_inverted_index.VLM, | 154, 164 |
| abstract_inverted_index.aims | 3 |
| abstract_inverted_index.data | 62 |
| abstract_inverted_index.each | 124 |
| abstract_inverted_index.from | 45 |
| abstract_inverted_index.made | 38 |
| abstract_inverted_index.such | 203 |
| abstract_inverted_index.task | 207 |
| abstract_inverted_index.then | 26 |
| abstract_inverted_index.they | 66 |
| abstract_inverted_index.this | 78, 212 |
| abstract_inverted_index.used | 130, 180 |
| abstract_inverted_index.well | 166 |
| abstract_inverted_index.with | 71, 88, 171, 187, 214 |
| abstract_inverted_index.(VLM) | 2 |
| abstract_inverted_index.Under | 14 |
| abstract_inverted_index.cover | 106 |
| abstract_inverted_index.data, | 30 |
| abstract_inverted_index.first | 19, 105 |
| abstract_inverted_index.image | 121, 195 |
| abstract_inverted_index.model | 160, 229, 233 |
| abstract_inverted_index.pairs | 24 |
| abstract_inverted_index.scale | 205 |
| abstract_inverted_index.their | 172, 191 |
| abstract_inverted_index.users | 72 |
| abstract_inverted_index.using | 99 |
| abstract_inverted_index.vague | 225 |
| abstract_inverted_index.Third, | 176 |
| abstract_inverted_index.across | 56 |
| abstract_inverted_index.bridge | 5 |
| abstract_inverted_index.detail | 127 |
| abstract_inverted_index.domain | 36 |
| abstract_inverted_index.future | 219 |
| abstract_inverted_index.images | 10 |
| abstract_inverted_index.models | 43, 147, 170 |
| abstract_inverted_index.paper, | 79 |
| abstract_inverted_index.remote | 34, 60, 85, 112 |
| abstract_inverted_index.review | 93, 141 |
| abstract_inverted_index.richer | 239 |
| abstract_inverted_index.strong | 54 |
| abstract_inverted_index.survey | 213 |
| abstract_inverted_index.tasks. | 64 |
| abstract_inverted_index.timely | 90 |
| abstract_inverted_index.visual | 116 |
| abstract_inverted_index.works, | 144 |
| abstract_inverted_index.Second, | 136 |
| abstract_inverted_index.benefit | 44 |
| abstract_inverted_index.between | 9 |
| abstract_inverted_index.capable | 68 |
| abstract_inverted_index.caption | 198 |
| abstract_inverted_index.conduct | 138 |
| abstract_inverted_index.general | 50 |
| abstract_inverted_index.greater | 242 |
| abstract_inverted_index.manner. | 76 |
| abstract_inverted_index.massive | 22 |
| abstract_inverted_index.methods | 151 |
| abstract_inverted_index.natural | 12 |
| abstract_inverted_index.network | 131 |
| abstract_inverted_index.provide | 83 |
| abstract_inverted_index.sensing | 35, 61, 86 |
| abstract_inverted_index.sources | 196 |
| abstract_inverted_index.tuning, | 118 |
| abstract_inverted_index.variety | 58 |
| abstract_inverted_index.Finally, | 209 |
| abstract_inverted_index.analysis | 63, 189 |
| abstract_inverted_index.commonly | 129 |
| abstract_inverted_index.conclude | 211 |
| abstract_inverted_index.datasets | 179, 237 |
| abstract_inverted_index.existing | 143 |
| abstract_inverted_index.insights | 215 |
| abstract_inverted_index.modeling | 1 |
| abstract_inverted_index.paradigm | 17 |
| abstract_inverted_index.research | 220 |
| abstract_inverted_index.scalable | 232 |
| abstract_inverted_index.sensing: | 113 |
| abstract_inverted_index.taxonomy | 108 |
| abstract_inverted_index.thorough | 140 |
| abstract_inverted_index.training | 157 |
| abstract_inverted_index.Moreover, | 65 |
| abstract_inverted_index.category, | 125 |
| abstract_inverted_index.community | 87 |
| abstract_inverted_index.examining | 145 |
| abstract_inverted_index.extensive | 49 |
| abstract_inverted_index.featuring | 238 |
| abstract_inverted_index.knowledge | 51 |
| abstract_inverted_index.language. | 13 |
| abstract_inverted_index.learning, | 115 |
| abstract_inverted_index.paradigm. | 102 |
| abstract_inverted_index.progress. | 40 |
| abstract_inverted_index.resulting | 42 |
| abstract_inverted_index.summarize | 178 |
| abstract_inverted_index.two-stage | 101 |
| abstract_inverted_index.upgrades, | 156 |
| abstract_inverted_index.(including | 194 |
| abstract_inverted_index.absorption | 47 |
| abstract_inverted_index.adaptation | 150 |
| abstract_inverted_index.alignment, | 224 |
| abstract_inverted_index.downstream | 174 |
| abstract_inverted_index.foundation | 146, 169 |
| abstract_inverted_index.generative | 168 |
| abstract_inverted_index.image-text | 23 |
| abstract_inverted_index.modalities | 240 |
| abstract_inverted_index.strategies | 158 |
| abstract_inverted_index.challenges. | 243 |
| abstract_inverted_index.continually | 231 |
| abstract_inverted_index.contrastive | 114 |
| abstract_inverted_index.cross-modal | 222 |
| abstract_inverted_index.demonstrate | 53 |
| abstract_inverted_index.directions: | 221 |
| abstract_inverted_index.discussions | 217 |
| abstract_inverted_index.evaluation, | 186 |
| abstract_inverted_index.fine-tuning | 27 |
| abstract_inverted_index.generation) | 199 |
| abstract_inverted_index.generation. | 122 |
| abstract_inverted_index.information | 7 |
| abstract_inverted_index.instruction | 117 |
| abstract_inverted_index.interacting | 70 |
| abstract_inverted_index.large-scale | 236 |
| abstract_inverted_index.objectives. | 135 |
| abstract_inverted_index.performance | 55 |
| abstract_inverted_index.properties, | 202 |
| abstract_inverted_index.requirement | 226 |
| abstract_inverted_index.significant | 39 |
| abstract_inverted_index.architecture | 132 |
| abstract_inverted_index.capabilities | 161 |
| abstract_inverted_index.construction | 192 |
| abstract_inverted_index.developments | 96 |
| abstract_inverted_index.fine-tuning, | 184 |
| abstract_inverted_index.pre-training | 20, 134 |
| abstract_inverted_index.reliability, | 230 |
| abstract_inverted_index.Specifically, | 103 |
| abstract_inverted_index.adaptability. | 208 |
| abstract_inverted_index.applications. | 175 |
| abstract_inverted_index.architectural | 155 |
| abstract_inverted_index.capabilities, | 234 |
| abstract_inverted_index.comprehensive | 92 |
| abstract_inverted_index.methodologies | 193 |
| abstract_inverted_index.pre-training, | 183 |
| abstract_inverted_index.task-specific | 29, 149 |
| abstract_inverted_index.comprehension, | 227 |
| abstract_inverted_index.conversational | 75 |
| abstract_inverted_index.representation | 223 |
| abstract_inverted_index.representative | 173 |
| abstract_inverted_index.Vision-language | 0 |
| abstract_inverted_index.text-conditioned | 120 |
| abstract_inverted_index.contrastive-based | 153 |
| abstract_inverted_index.instruction-based | 163 |
| abstract_inverted_index.explanation-driven | 228 |
| cited_by_percentile_year.max | 98 |
| cited_by_percentile_year.min | 97 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.99807277 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |