{"id":"https://openalex.org/W4416035200","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1745","title":"Concept-pedia: a Wide-coverage Semantically-annotated Multimodal Dataset","display_name":"Concept-pedia: a Wide-coverage Semantically-annotated Multimodal Dataset","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035200","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1745"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1745","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1745","pdf_url":"https://aclanthology.org/2025.emnlp-main.1745.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1745.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094077393","display_name":"Karim Ghonim","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Karim Ghonim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107436210","display_name":"Andrei Stefan Bejgu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrei Stefan Bejgu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106203278","display_name":"Alberte Fern\u00e1ndez-Castro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alberte Fern\u00e1ndez-Castro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026648049","display_name":"Roberto Navigli","orcid":"https://orcid.org/0000-0003-3831-9706"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Navigli","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5094077393"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35848471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34405","last_page":"34426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9817000031471252,"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":0.9817000031471252,"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/T10028","display_name":"Topic Modeling","score":0.0035000001080334187,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002199999988079071,"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/pipeline","display_name":"Pipeline (software)","score":0.5400999784469604},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3946000039577484},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3682999908924103},{"id":"https://openalex.org/keywords/de-facto","display_name":"De facto","score":0.34549999237060547},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3244999945163727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6945000290870667},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.423799991607666},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3662000000476837},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1745","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1745","pdf_url":"https://aclanthology.org/2025.emnlp-main.1745.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1755854","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1755854","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1745","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1745","pdf_url":"https://aclanthology.org/2025.emnlp-main.1745.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035200.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"Models":[1],"(VLMs),":[2],"such":[3],"as":[4,18],"CLIP":[5],"and":[6,30,57,64,175],"SigLIP,":[7],"have":[8],"become":[9],"the":[10,59,101,164,183,192],"de":[11],"facto":[12],"standard":[13],"for":[14,22,35,54,167],"multimodal":[15,83,186],"tasks,":[16],"serving":[17],"essential":[19],"building":[20],"blocks":[21],"recent":[23],"Multimodal":[24],"Large":[25],"Language":[26],"Models,":[27],"including":[28,106],"LLaVA":[29],"PaliGemma.":[31],"However,":[32],"current":[33,139],"evaluations":[34],"VLMs":[36],"remain":[37],"heavily":[38],"anchored":[39],"to":[40,181,191],"ImageNet.":[41],"In":[42],"this":[43,74],"paper,":[44],"we":[45,76,113],"question":[46],"whether":[47],"ImageNet\u2019s":[48],"coverage":[49],"is":[50],"still":[51],"sufficiently":[52],"challenging":[53],"modern":[55],"VLMs,":[56],"investigate":[58],"impact":[60],"of":[61,103,127,133,185,194],"adding":[62],"novel":[63],"varied":[65],"concept":[66],"categories,":[67],"i.e.,":[68],"semantically":[69,176],"grouped":[70],"fine-grained":[71],"synsets.":[72],"To":[73],"end,":[75],"introduce":[77],"Concept-pedia,":[78,112],"a":[79,91,116,130,154,173],"novel,":[80],"large-scale,":[81],"semantically-annotated":[82],"resource":[84],"covering":[85],"more":[86,168],"than":[87],"165,000":[88],"concepts.":[89],"Leveraging":[90],"language-agnostic,":[92],"automatic":[93],"annotation":[94],"pipeline":[95],"grounded":[96],"in":[97],"Wikipedia,":[98],"Concept-pedia":[99],"expands":[100],"range":[102,132],"visual":[104,196],"concepts,":[105,159],"diverse":[107],"abstract":[108],"categories.":[109,134],"Building":[110],"on":[111,143],"also":[114,162],"present":[115],"manually-curated":[117],"Visual":[118],"Concept":[119],"Recognition":[120],"evaluation":[121],"benchmark,":[122],"Concept-10k,":[123],"that":[124,138,188],"spans":[125],"thousands":[126],"concepts":[128,197],"across":[129],"wide":[131],"Our":[135],"experiments":[136],"show":[137],"models,":[140],"although":[141],"excelling":[142],"ImageNet,":[144],"struggle":[145],"with":[146],"Concept-10k.":[147],"Not":[148],"only":[149],"do":[150],"these":[151],"findings":[152],"highlight":[153],"persistent":[155],"bias":[156],"toward":[157],"ImageNet-centric":[158],"but":[160],"they":[161],"underscore":[163],"urgent":[165],"need":[166],"representative":[169],"benchmarks.":[170],"By":[171],"offering":[172],"broader":[174],"richer":[177],"testbed,":[178],"Concept-10k":[179],"aims":[180],"support":[182],"development":[184],"systems":[187],"better":[189],"generalize":[190],"complexities":[193],"real-world":[195]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}