{"id":"https://openalex.org/W4367189547","doi":"https://doi.org/10.1145/3591106.3592223","title":"Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining","display_name":"Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4367189547","doi":"https://doi.org/10.1145/3591106.3592223"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.13130","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083113186","display_name":"Giacomo Nebbia","orcid":"https://orcid.org/0000-0002-4766-6278"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]},{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Giacomo Nebbia","raw_affiliation_strings":["Intelligent Systems Program, University of Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-4766-6278","affiliations":[{"raw_affiliation_string":"Intelligent Systems Program, University of Pittsburgh, USA","institution_ids":["https://openalex.org/I4210105785","https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072882318","display_name":"Adriana Kovashka","orcid":"https://orcid.org/0000-0003-1901-9660"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adriana Kovashka","raw_affiliation_strings":["Computer Science Department, University of Pittsburgh, USA and Intelligent Systems Program, University of Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-1901-9660","affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Pittsburgh, USA and Intelligent Systems Program, University of Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083113186"],"corresponding_institution_ids":["https://openalex.org/I170201317","https://openalex.org/I4210105785"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03157057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965999722480774,"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/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.8699429035186768},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7271342277526855},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.672958493232727},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.6282800436019897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6187030076980591},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6072958707809448},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5904485583305359},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5877901315689087},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5567886233329773},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5312972664833069},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5142195224761963},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.5119091272354126},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4301835894584656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3417682647705078},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22128283977508545},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.1862030029296875},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07627260684967041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8699429035186768},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7271342277526855},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.672958493232727},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.6282800436019897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187030076980591},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6072958707809448},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5904485583305359},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5877901315689087},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5567886233329773},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5312972664833069},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5142195224761963},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.5119091272354126},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4301835894584656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3417682647705078},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22128283977508545},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.1862030029296875},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07627260684967041},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3591106.3592223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.13130","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13130","pdf_url":"https://arxiv.org/pdf/2304.13130","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.13130","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.13130","pdf_url":"https://arxiv.org/pdf/2304.13130","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5997888051","display_name":null,"funder_award_id":"2046853","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310174","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367189547.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1552847225","https://openalex.org/W1861492603","https://openalex.org/W2096765155","https://openalex.org/W2150824314","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2886641317","https://openalex.org/W2913939497","https://openalex.org/W2963936013","https://openalex.org/W2979826702","https://openalex.org/W2982573303","https://openalex.org/W3090449556","https://openalex.org/W3135367836","https://openalex.org/W3141624005","https://openalex.org/W3156892778","https://openalex.org/W3173859428","https://openalex.org/W3174415835","https://openalex.org/W3176276772","https://openalex.org/W3176641147","https://openalex.org/W4283742233","https://openalex.org/W4292794004","https://openalex.org/W4312563428","https://openalex.org/W4312599396","https://openalex.org/W4312747482"],"related_works":["https://openalex.org/W3140537242","https://openalex.org/W2186562580","https://openalex.org/W2155874911","https://openalex.org/W2015784841","https://openalex.org/W4288047282","https://openalex.org/W2032007337","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W1980182063","https://openalex.org/W3000685722"],"abstract_inverted_index":{"Named":[0],"entities":[1,23,54,113],"are":[2,50],"ubiquitous":[3],"in":[4,11,76],"text":[5],"that":[6],"naturally":[7],"accompanies":[8],"images,":[9],"especially":[10],"domains":[12],"such":[13],"as":[14,27,106],"news":[15],"or":[16],"Wikipedia":[17,40,165],"articles.":[18],"In":[19,100],"previous":[20],"work,":[21,102],"named":[22,44,53,72,112],"have":[24],"been":[25],"identified":[26],"a":[28,96,107,133,138,145,151],"likely":[29],"reason":[30],"for":[31,66,114,120],"low":[32],"performance":[33,176],"of":[34,141,179,188],"image-text":[35],"retrieval":[36],"models":[37,118],"pretrained":[38],"on":[39,43,122,137,162,177,190,194],"and":[41,74,119,143,166,183],"evaluated":[42],"entities-free":[45],"benchmark":[46],"datasets.":[47],"Because":[48],"they":[49],"rarely":[51],"mentioned,":[52],"could":[55],"be":[56,80,89],"challenging":[57],"to":[58,109,129,154,156],"model.":[59],"They":[60],"also":[61],"represent":[62],"missed":[63,81],"learning":[64],"opportunities":[65],"self-supervised":[67],"models:":[68],"the":[69,77,83,91,186],"link":[70],"between":[71],"entity":[73],"object":[75,92],"image":[78],"may":[79],"by":[82],"model,":[84],"but":[85],"it":[86],"would":[87],"not":[88,196],"if":[90],"were":[93],"mentioned":[94],"using":[95],"more":[97],"common":[98],"term.":[99],"this":[101],"we":[103,149,184],"investigate":[104],"hypernymization":[105,189],"way":[108],"deal":[110],"with":[111],"pretraining":[115,175],"grounding-based":[116],"multi-modal":[117],"fine-tuning":[121],"open-vocabulary":[123,191],"detection.":[124],"We":[125,159,172],"propose":[126],"two":[127],"ways":[128],"perform":[130,157],"hypernymization:":[131],"(1)":[132],"\u201cmanual\u201d":[134],"pipeline":[135],"relying":[136],"comprehensive":[139],"ontology":[140],"concepts,":[142],"(2)":[144],"\u201clearned\u201d":[146],"approach":[147],"where":[148],"train":[150],"language":[152],"model":[153],"learn":[155],"hypernymization.":[158],"run":[160],"experiments":[161],"data":[163],"from":[164,167],"The":[168],"New":[169],"York":[170],"Times.":[171],"report":[173],"improved":[174],"objects":[178],"interest":[180],"following":[181],"hypernymization,":[182],"show":[185],"promise":[187],"detection,":[192],"specifically":[193],"classes":[195],"seen":[197],"during":[198],"training.":[199]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-04-28T00:00:00"}