{"id":"https://openalex.org/W4416033958","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1097","title":"Differentiated Vision: Unveiling Entity-Specific Visual Modality Requirements for Multimodal Knowledge Graph","display_name":"Differentiated Vision: Unveiling Entity-Specific Visual Modality Requirements for Multimodal Knowledge Graph","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033958","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1097"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1097","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1097.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1097.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087261869","display_name":"Minghang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086972170","display_name":"Yinghan Shen","orcid":"https://orcid.org/0009-0004-1727-665X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghan Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zihe Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihe Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057538607","display_name":"Yuanzhuo Wang","orcid":"https://orcid.org/0000-0002-6799-1756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanzhuo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091865553","display_name":"Xuhui Jiang","orcid":"https://orcid.org/0000-0002-1741-0781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuhui Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047897879","display_name":"Huawei Shen","orcid":"https://orcid.org/0000-0002-1081-8119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huawei Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28845186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20170","last_page":"20183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8499000072479248,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8499000072479248,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.06560000032186508,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.012400000356137753,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4453999996185303},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4187999963760376},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37389999628067017},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.325300008058548},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.30219998955726624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6241999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4790000021457672},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3626999855041504},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1097","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1097.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1097","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1097.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6940299913","display_name":null,"funder_award_id":"62172393","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033958.pdf","grobid_xml":"https://content.openalex.org/works/W4416033958.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,94],"Knowledge":[1,95],"Graphs":[2,96],"(MMKGs)":[3],"enhance":[4],"knowledge":[5,25],"representations":[6],"by":[7],"integrating":[8],"structural":[9],"and":[10,27,68,80,113,119],"multimodal":[11],"information":[12,23,58],"of":[13,56,102,128,140,152],"entities.Recently,":[14],"MMKGs":[15],"have":[16],"proven":[17],"effective":[18],"in":[19],"tasks":[20],"such":[21],"as":[22],"retrieval,":[24],"discovery,":[26],"question":[28],"answering.Current":[29],"methods":[30],"typically":[31],"utilize":[32],"pre-trained":[33],"visual":[34,57,66,103,129],"encoders":[35],"to":[36,136],"extract":[37],"features":[38],"from":[39,65],"images":[40,72,77],"associated":[41,71],"with":[42,75],"each":[43,106],"entity,":[44],"emphasizing":[45],"complex":[46],"cross-modal":[47],"interactions.However,":[48],"these":[49,86,121],"approaches":[50],"often":[51],"overlook":[52],"the":[53,90,100,126,137,150],"varying":[54],"relevance":[55],"across":[59],"entities.Specifically,":[60],"not":[61,69],"all":[62,70],"entities":[63],"benefit":[64],"data,":[67],"are":[73],"pertinent,":[74],"irrelevant":[76],"introducing":[78],"noise":[79],"potentially":[81],"degrading":[82],"model":[83],"performance.To":[84],"address":[85],"issues,":[87],"we":[88],"propose":[89],"Differentiated":[91],"Vision":[92],"for":[93,105],"(DVMKG)":[97],"model.DVMKG":[98],"evaluates":[99],"necessity":[101],"modality":[104],"entity":[107,142],"based":[108],"on":[109,145],"its":[110],"intrinsic":[111],"attributes":[112],"assesses":[114],"image":[115],"quality":[116],"through":[117],"representativeness":[118],"diversity.Leveraging":[120],"metrics,":[122],"DVMKG":[123],"dynamically":[124],"adjusts":[125],"influence":[127],"data":[130],"during":[131],"feature":[132],"integration,":[133],"tailoring":[134],"it":[135],"specific":[138],"needs":[139],"different":[141],"types.Extensive":[143],"experiments":[144],"multiple":[146],"benchmark":[147],"datasets":[148],"confirm":[149],"effectiveness":[151],"DVMKG,":[153],"demonstrating":[154],"significant":[155],"improvements":[156],"over":[157],"existing":[158],"methods.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}