LLM-Enhanced Composed Image Retrieval: An Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model Article Swipe
Hongfei Ge
,
Yuanchun Jiang
,
Jianshan Sun
,
Kun Yuan
,
Yezheng Liu
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1145/3699715
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1145/3699715
Composed image retrieval (CoIR) involves a multi-modal query of the reference image and modification text describing the desired changes, allowing users to express image retrieval intents flexibly and effectively. The key of CoIR lies in how to properly reason the search intent from the multi-modal query. Existing work either aligns the composite embedding of the multi-modal query and the target image embedding in the visual domain through late-fusion or converts all images into text descriptions and leverage large language models (LLM) for text semantic reasoning. However, this single-modality reasoning approach fails to comprehensively and interpretably capture the users’ ambiguous and uncertain intents in the multi-modal queries, incurring the inconsistency between retrieved results and ground truth. Besides, the expensive manually annotated datasets limit the further performance improvement of CoIR. To this end, this article proposes an LLM-enhanced Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model (IUDC), which combines the strengths of multi-modal late-fusion and LLMs for CoIR. We first construct an LLM-based triplet augmentation strategy to generate more synthetic training triplets. Based on this, the core of IUDC consists of two matching channels: the semantic matching channel is responsible for intent reasoning on the aspect-level attributes extracted by an LLM, and the visual matching channel accounts for the fine-grained visual matching between multi-modal fusion embedding and target images. Considering the intent uncertainty presented in the multi-modal queries, we introduce Probability Distribution Encoder (PDE) to project the intents as probabilistic distributions in the two matching channels. Consequently, a mutually enhanced module is designed to share knowledge between the visual and semantic representations for better representation learning. Finally, the matching scores of two channels are added to retrieve the target image. Extensive experiments conducted on two real datasets demonstrate the effectiveness and superiority of our model. Notably, with the help of the proposed LLM-based triplet augmentation strategy, our model achieves a new record of state-of-the-art performance among all datasets.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3699715
- https://dl.acm.org/doi/pdf/10.1145/3699715
- OA Status
- bronze
- Cited By
- 5
- References
- 39
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403246017
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403246017Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3699715Digital Object Identifier
- Title
-
LLM-Enhanced Composed Image Retrieval: An Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching ModelWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-10-09Full publication date if available
- Authors
-
Hongfei Ge, Yuanchun Jiang, Jianshan Sun, Kun Yuan, Yezheng LiuList of authors in order
- Landing page
-
https://doi.org/10.1145/3699715Publisher landing page
- PDF URL
-
https://dl.acm.org/doi/pdf/10.1145/3699715Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
bronzeOpen access status per OpenAlex
- OA URL
-
https://dl.acm.org/doi/pdf/10.1145/3699715Direct OA link when available
- Concepts
-
Computer science, Embedding, Matching (statistics), Artificial intelligence, Encoder, Information retrieval, Modal, Natural language processing, Computer vision, Mathematics, Operating system, Polymer chemistry, Statistics, ChemistryTop 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)
-
39Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403246017 |
|---|---|
| doi | https://doi.org/10.1145/3699715 |
| ids.doi | https://doi.org/10.1145/3699715 |
| ids.openalex | https://openalex.org/W4403246017 |
| fwci | 2.6507878 |
| type | article |
| title | LLM-Enhanced Composed Image Retrieval: An Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model |
| biblio.issue | 2 |
| biblio.volume | 43 |
| biblio.last_page | 30 |
| biblio.first_page | 1 |
| 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 | 0.9998999834060669 |
| 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/T10627 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9997000098228455 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Image and Video Retrieval Techniques |
| topics[2].id | https://openalex.org/T11307 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9962000250816345 |
| 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 | Domain Adaptation and Few-Shot Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.765874445438385 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C41608201 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6336274743080139 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q980509 |
| concepts[1].display_name | Embedding |
| concepts[2].id | https://openalex.org/C165064840 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5483759045600891 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1321061 |
| concepts[2].display_name | Matching (statistics) |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5410860776901245 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C118505674 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5057778358459473 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[4].display_name | Encoder |
| concepts[5].id | https://openalex.org/C23123220 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5042701959609985 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[5].display_name | Information retrieval |
| concepts[6].id | https://openalex.org/C71139939 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4947735667228699 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q910194 |
| concepts[6].display_name | Modal |
| concepts[7].id | https://openalex.org/C204321447 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3980373740196228 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[7].display_name | Natural language processing |
| concepts[8].id | https://openalex.org/C31972630 |
| concepts[8].level | 1 |
| concepts[8].score | 0.33746129274368286 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[8].display_name | Computer vision |
| concepts[9].id | https://openalex.org/C33923547 |
| concepts[9].level | 0 |
| concepts[9].score | 0.09509268403053284 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[9].display_name | Mathematics |
| concepts[10].id | https://openalex.org/C111919701 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[10].display_name | Operating system |
| concepts[11].id | https://openalex.org/C188027245 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q750446 |
| concepts[11].display_name | Polymer chemistry |
| concepts[12].id | https://openalex.org/C105795698 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[12].display_name | Statistics |
| concepts[13].id | https://openalex.org/C185592680 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[13].display_name | Chemistry |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.765874445438385 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/embedding |
| keywords[1].score | 0.6336274743080139 |
| keywords[1].display_name | Embedding |
| keywords[2].id | https://openalex.org/keywords/matching |
| keywords[2].score | 0.5483759045600891 |
| keywords[2].display_name | Matching (statistics) |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5410860776901245 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/encoder |
| keywords[4].score | 0.5057778358459473 |
| keywords[4].display_name | Encoder |
| keywords[5].id | https://openalex.org/keywords/information-retrieval |
| keywords[5].score | 0.5042701959609985 |
| keywords[5].display_name | Information retrieval |
| keywords[6].id | https://openalex.org/keywords/modal |
| keywords[6].score | 0.4947735667228699 |
| keywords[6].display_name | Modal |
| keywords[7].id | https://openalex.org/keywords/natural-language-processing |
| keywords[7].score | 0.3980373740196228 |
| keywords[7].display_name | Natural language processing |
| keywords[8].id | https://openalex.org/keywords/computer-vision |
| keywords[8].score | 0.33746129274368286 |
| keywords[8].display_name | Computer vision |
| keywords[9].id | https://openalex.org/keywords/mathematics |
| keywords[9].score | 0.09509268403053284 |
| keywords[9].display_name | Mathematics |
| language | en |
| locations[0].id | doi:10.1145/3699715 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4394735545 |
| locations[0].source.issn | 1046-8188, 1558-2868 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 1046-8188 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | ACM Transactions on Information Systems |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].license | |
| locations[0].pdf_url | https://dl.acm.org/doi/pdf/10.1145/3699715 |
| 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 | ACM Transactions on Information Systems |
| locations[0].landing_page_url | https://doi.org/10.1145/3699715 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5026531655 |
| authorships[0].author.orcid | https://orcid.org/0009-0000-3044-6124 |
| authorships[0].author.display_name | Hongfei Ge |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I16365422 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Management, Hefei University of Technology, China |
| authorships[0].institutions[0].id | https://openalex.org/I16365422 |
| authorships[0].institutions[0].ror | https://ror.org/02czkny70 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I16365422 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Hefei University of Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Hongfei Ge |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Management, Hefei University of Technology, China |
| authorships[1].author.id | https://openalex.org/A5004103125 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-0886-3647 |
| authorships[1].author.display_name | Yuanchun Jiang |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I16365422 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Management, Hefei University of Technology |
| authorships[1].affiliations[1].institution_ids | https://openalex.org/I16365422 |
| authorships[1].affiliations[1].raw_affiliation_string | School of Management, Hefei University of Technology; Key Laboratory of Process Optimization and Intelligent Decision Making, Ministry of Education, China |
| authorships[1].institutions[0].id | https://openalex.org/I16365422 |
| authorships[1].institutions[0].ror | https://ror.org/02czkny70 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I16365422 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Hefei University of Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yuanchun Jiang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Management, Hefei University of Technology, School of Management, Hefei University of Technology; Key Laboratory of Process Optimization and Intelligent Decision Making, Ministry of Education, China |
| authorships[2].author.id | https://openalex.org/A5101987792 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2981-5812 |
| authorships[2].author.display_name | Jianshan Sun |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I16365422 |
| authorships[2].affiliations[0].raw_affiliation_string | School of Management, Hefei University of Technology, China |
| authorships[2].institutions[0].id | https://openalex.org/I16365422 |
| authorships[2].institutions[0].ror | https://ror.org/02czkny70 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I16365422 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Hefei University of Technology |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Jianshan Sun |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | School of Management, Hefei University of Technology, China |
| authorships[3].author.id | https://openalex.org/A5049657236 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-6542-4483 |
| authorships[3].author.display_name | Kun Yuan |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I16365422 |
| authorships[3].affiliations[0].raw_affiliation_string | School of Management, Hefei University of Technology; Key Laboratory of Philosophy and Social Sciences for Cyberspace Behaviour and Management, China |
| authorships[3].affiliations[1].institution_ids | https://openalex.org/I16365422 |
| authorships[3].affiliations[1].raw_affiliation_string | School of Management, Hefei University of Technology |
| authorships[3].institutions[0].id | https://openalex.org/I16365422 |
| authorships[3].institutions[0].ror | https://ror.org/02czkny70 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I16365422 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Hefei University of Technology |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Kun Yuan |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | School of Management, Hefei University of Technology, School of Management, Hefei University of Technology; Key Laboratory of Philosophy and Social Sciences for Cyberspace Behaviour and Management, China |
| authorships[4].author.id | https://openalex.org/A5030946475 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-9193-5236 |
| authorships[4].author.display_name | Yezheng Liu |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I16365422 |
| authorships[4].affiliations[0].raw_affiliation_string | School of Management, Hefei University of Technology |
| authorships[4].affiliations[1].institution_ids | https://openalex.org/I16365422 |
| authorships[4].affiliations[1].raw_affiliation_string | School of Management, Hefei University of Technology; National Engineering Laboratory for Big Data Distribution and Exchange Technologies, China |
| authorships[4].institutions[0].id | https://openalex.org/I16365422 |
| authorships[4].institutions[0].ror | https://ror.org/02czkny70 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I16365422 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Hefei University of Technology |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Yezheng Liu |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | School of Management, Hefei University of Technology, School of Management, Hefei University of Technology; National Engineering Laboratory for Big Data Distribution and Exchange Technologies, China |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://dl.acm.org/doi/pdf/10.1145/3699715 |
| open_access.oa_status | bronze |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | LLM-Enhanced Composed Image Retrieval: An Intent Uncertainty-Aware Linguistic-Visual Dual Channel Matching Model |
| 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 | 0.9998999834060669 |
| 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/W2081900870, https://openalex.org/W4390516098, https://openalex.org/W2037549926, https://openalex.org/W2181948922, https://openalex.org/W2384362569, https://openalex.org/W2345479200, https://openalex.org/W2183306018, https://openalex.org/W2142795561, https://openalex.org/W2849310602, https://openalex.org/W4205302943 |
| cited_by_count | 5 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 5 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1145/3699715 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4394735545 |
| best_oa_location.source.issn | 1046-8188, 1558-2868 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 1046-8188 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | ACM Transactions on Information Systems |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3699715 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | ACM Transactions on Information Systems |
| best_oa_location.landing_page_url | https://doi.org/10.1145/3699715 |
| primary_location.id | doi:10.1145/3699715 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4394735545 |
| primary_location.source.issn | 1046-8188, 1558-2868 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 1046-8188 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | ACM Transactions on Information Systems |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.license | |
| primary_location.pdf_url | https://dl.acm.org/doi/pdf/10.1145/3699715 |
| 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 | ACM Transactions on Information Systems |
| primary_location.landing_page_url | https://doi.org/10.1145/3699715 |
| publication_date | 2024-10-09 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W4384652592, https://openalex.org/W4214612132, https://openalex.org/W4292828970, https://openalex.org/W4386075688, https://openalex.org/W3026458074, https://openalex.org/W3033276647, https://openalex.org/W2531409750, https://openalex.org/W4386729453, https://openalex.org/W3034368386, https://openalex.org/W6751039726, https://openalex.org/W3176909828, https://openalex.org/W3175684172, https://openalex.org/W4312749754, https://openalex.org/W2997006708, https://openalex.org/W2760103357, https://openalex.org/W6762811270, https://openalex.org/W4382318659, https://openalex.org/W3135367836, https://openalex.org/W4386076063, https://openalex.org/W4386071700, https://openalex.org/W1978394996, https://openalex.org/W2022692239, https://openalex.org/W4386273457, https://openalex.org/W2511279186, https://openalex.org/W3212037738, https://openalex.org/W3154902219, https://openalex.org/W4386501573, https://openalex.org/W3172514680, https://openalex.org/W4225774139, https://openalex.org/W2987861506, https://openalex.org/W2620998106, https://openalex.org/W3138154797, https://openalex.org/W4386075815, https://openalex.org/W4390873539, https://openalex.org/W2905544595, https://openalex.org/W4386071614, https://openalex.org/W2963058055, https://openalex.org/W4382467088, https://openalex.org/W2984809863 |
| referenced_works_count | 39 |
| abstract_inverted_index.a | 5, 244, 306 |
| abstract_inverted_index.To | 128 |
| abstract_inverted_index.We | 155 |
| abstract_inverted_index.an | 134, 158, 196 |
| abstract_inverted_index.as | 235 |
| abstract_inverted_index.by | 195 |
| abstract_inverted_index.in | 34, 62, 102, 221, 238 |
| abstract_inverted_index.is | 185, 248 |
| abstract_inverted_index.of | 8, 31, 53, 126, 148, 174, 177, 267, 289, 296, 309 |
| abstract_inverted_index.on | 170, 190, 280 |
| abstract_inverted_index.or | 68 |
| abstract_inverted_index.to | 21, 36, 91, 163, 231, 250, 272 |
| abstract_inverted_index.we | 225 |
| abstract_inverted_index.The | 29 |
| abstract_inverted_index.all | 70, 313 |
| abstract_inverted_index.and | 12, 27, 57, 75, 93, 99, 112, 151, 198, 213, 256, 287 |
| abstract_inverted_index.are | 270 |
| abstract_inverted_index.for | 81, 153, 187, 204, 259 |
| abstract_inverted_index.how | 35 |
| abstract_inverted_index.key | 30 |
| abstract_inverted_index.new | 307 |
| abstract_inverted_index.our | 290, 303 |
| abstract_inverted_index.the | 9, 16, 39, 43, 50, 54, 58, 63, 96, 103, 107, 116, 122, 146, 172, 181, 191, 199, 205, 217, 222, 233, 239, 254, 264, 274, 285, 294, 297 |
| abstract_inverted_index.two | 178, 240, 268, 281 |
| abstract_inverted_index.CoIR | 32 |
| abstract_inverted_index.Dual | 139 |
| abstract_inverted_index.IUDC | 175 |
| abstract_inverted_index.LLM, | 197 |
| abstract_inverted_index.LLMs | 152 |
| abstract_inverted_index.core | 173 |
| abstract_inverted_index.end, | 130 |
| abstract_inverted_index.from | 42 |
| abstract_inverted_index.help | 295 |
| abstract_inverted_index.into | 72 |
| abstract_inverted_index.lies | 33 |
| abstract_inverted_index.more | 165 |
| abstract_inverted_index.real | 282 |
| abstract_inverted_index.text | 14, 73, 82 |
| abstract_inverted_index.this | 86, 129, 131 |
| abstract_inverted_index.with | 293 |
| abstract_inverted_index.work | 47 |
| abstract_inverted_index.(LLM) | 80 |
| abstract_inverted_index.(PDE) | 230 |
| abstract_inverted_index.Based | 169 |
| abstract_inverted_index.CoIR. | 127, 154 |
| abstract_inverted_index.Model | 142 |
| abstract_inverted_index.added | 271 |
| abstract_inverted_index.among | 312 |
| abstract_inverted_index.fails | 90 |
| abstract_inverted_index.first | 156 |
| abstract_inverted_index.image | 1, 11, 23, 60 |
| abstract_inverted_index.large | 77 |
| abstract_inverted_index.limit | 121 |
| abstract_inverted_index.model | 304 |
| abstract_inverted_index.query | 7, 56 |
| abstract_inverted_index.share | 251 |
| abstract_inverted_index.this, | 171 |
| abstract_inverted_index.users | 20 |
| abstract_inverted_index.which | 144 |
| abstract_inverted_index.(CoIR) | 3 |
| abstract_inverted_index.Intent | 136 |
| abstract_inverted_index.aligns | 49 |
| abstract_inverted_index.better | 260 |
| abstract_inverted_index.domain | 65 |
| abstract_inverted_index.either | 48 |
| abstract_inverted_index.fusion | 211 |
| abstract_inverted_index.ground | 113 |
| abstract_inverted_index.image. | 276 |
| abstract_inverted_index.images | 71 |
| abstract_inverted_index.intent | 41, 188, 218 |
| abstract_inverted_index.model. | 291 |
| abstract_inverted_index.models | 79 |
| abstract_inverted_index.module | 247 |
| abstract_inverted_index.query. | 45 |
| abstract_inverted_index.reason | 38 |
| abstract_inverted_index.record | 308 |
| abstract_inverted_index.scores | 266 |
| abstract_inverted_index.search | 40 |
| abstract_inverted_index.target | 59, 214, 275 |
| abstract_inverted_index.truth. | 114 |
| abstract_inverted_index.visual | 64, 200, 207, 255 |
| abstract_inverted_index.(IUDC), | 143 |
| abstract_inverted_index.Channel | 140 |
| abstract_inverted_index.Encoder | 229 |
| abstract_inverted_index.article | 132 |
| abstract_inverted_index.between | 109, 209, 253 |
| abstract_inverted_index.capture | 95 |
| abstract_inverted_index.channel | 184, 202 |
| abstract_inverted_index.desired | 17 |
| abstract_inverted_index.express | 22 |
| abstract_inverted_index.further | 123 |
| abstract_inverted_index.images. | 215 |
| abstract_inverted_index.intents | 25, 101, 234 |
| abstract_inverted_index.project | 232 |
| abstract_inverted_index.results | 111 |
| abstract_inverted_index.through | 66 |
| abstract_inverted_index.triplet | 160, 300 |
| abstract_inverted_index.Besides, | 115 |
| abstract_inverted_index.Composed | 0 |
| abstract_inverted_index.Existing | 46 |
| abstract_inverted_index.Finally, | 263 |
| abstract_inverted_index.However, | 85 |
| abstract_inverted_index.Matching | 141 |
| abstract_inverted_index.Notably, | 292 |
| abstract_inverted_index.accounts | 203 |
| abstract_inverted_index.achieves | 305 |
| abstract_inverted_index.allowing | 19 |
| abstract_inverted_index.approach | 89 |
| abstract_inverted_index.changes, | 18 |
| abstract_inverted_index.channels | 269 |
| abstract_inverted_index.combines | 145 |
| abstract_inverted_index.consists | 176 |
| abstract_inverted_index.converts | 69 |
| abstract_inverted_index.datasets | 120, 283 |
| abstract_inverted_index.designed | 249 |
| abstract_inverted_index.enhanced | 246 |
| abstract_inverted_index.flexibly | 26 |
| abstract_inverted_index.generate | 164 |
| abstract_inverted_index.involves | 4 |
| abstract_inverted_index.language | 78 |
| abstract_inverted_index.leverage | 76 |
| abstract_inverted_index.manually | 118 |
| abstract_inverted_index.matching | 179, 183, 201, 208, 241, 265 |
| abstract_inverted_index.mutually | 245 |
| abstract_inverted_index.properly | 37 |
| abstract_inverted_index.proposed | 298 |
| abstract_inverted_index.proposes | 133 |
| abstract_inverted_index.queries, | 105, 224 |
| abstract_inverted_index.retrieve | 273 |
| abstract_inverted_index.semantic | 83, 182, 257 |
| abstract_inverted_index.strategy | 162 |
| abstract_inverted_index.training | 167 |
| abstract_inverted_index.users’ | 97 |
| abstract_inverted_index.Extensive | 277 |
| abstract_inverted_index.LLM-based | 159, 299 |
| abstract_inverted_index.ambiguous | 98 |
| abstract_inverted_index.annotated | 119 |
| abstract_inverted_index.channels. | 242 |
| abstract_inverted_index.channels: | 180 |
| abstract_inverted_index.composite | 51 |
| abstract_inverted_index.conducted | 279 |
| abstract_inverted_index.construct | 157 |
| abstract_inverted_index.datasets. | 314 |
| abstract_inverted_index.embedding | 52, 61, 212 |
| abstract_inverted_index.expensive | 117 |
| abstract_inverted_index.extracted | 194 |
| abstract_inverted_index.incurring | 106 |
| abstract_inverted_index.introduce | 226 |
| abstract_inverted_index.knowledge | 252 |
| abstract_inverted_index.learning. | 262 |
| abstract_inverted_index.presented | 220 |
| abstract_inverted_index.reasoning | 88, 189 |
| abstract_inverted_index.reference | 10 |
| abstract_inverted_index.retrieval | 2, 24 |
| abstract_inverted_index.retrieved | 110 |
| abstract_inverted_index.strategy, | 302 |
| abstract_inverted_index.strengths | 147 |
| abstract_inverted_index.synthetic | 166 |
| abstract_inverted_index.triplets. | 168 |
| abstract_inverted_index.uncertain | 100 |
| abstract_inverted_index.attributes | 193 |
| abstract_inverted_index.describing | 15 |
| abstract_inverted_index.reasoning. | 84 |
| abstract_inverted_index.Considering | 216 |
| abstract_inverted_index.Probability | 227 |
| abstract_inverted_index.demonstrate | 284 |
| abstract_inverted_index.experiments | 278 |
| abstract_inverted_index.improvement | 125 |
| abstract_inverted_index.late-fusion | 67, 150 |
| abstract_inverted_index.multi-modal | 6, 44, 55, 104, 149, 210, 223 |
| abstract_inverted_index.performance | 124, 311 |
| abstract_inverted_index.responsible | 186 |
| abstract_inverted_index.superiority | 288 |
| abstract_inverted_index.uncertainty | 219 |
| abstract_inverted_index.Distribution | 228 |
| abstract_inverted_index.LLM-enhanced | 135 |
| abstract_inverted_index.aspect-level | 192 |
| abstract_inverted_index.augmentation | 161, 301 |
| abstract_inverted_index.descriptions | 74 |
| abstract_inverted_index.effectively. | 28 |
| abstract_inverted_index.fine-grained | 206 |
| abstract_inverted_index.modification | 13 |
| abstract_inverted_index.Consequently, | 243 |
| abstract_inverted_index.distributions | 237 |
| abstract_inverted_index.effectiveness | 286 |
| abstract_inverted_index.inconsistency | 108 |
| abstract_inverted_index.interpretably | 94 |
| abstract_inverted_index.probabilistic | 236 |
| abstract_inverted_index.representation | 261 |
| abstract_inverted_index.comprehensively | 92 |
| abstract_inverted_index.representations | 258 |
| abstract_inverted_index.single-modality | 87 |
| abstract_inverted_index.state-of-the-art | 310 |
| abstract_inverted_index.Linguistic-Visual | 138 |
| abstract_inverted_index.Uncertainty-Aware | 137 |
| cited_by_percentile_year.max | 98 |
| cited_by_percentile_year.min | 97 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.5799999833106995 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.8649194 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |