{"id":"https://openalex.org/W6924846684","doi":"https://doi.org/10.15496/publikation-103844","title":"Language Grounding in Vision","display_name":"Language Grounding in Vision","publication_year":2025,"publication_date":"2025-02-25","ids":{"openalex":"https://openalex.org/W6924846684","doi":"https://doi.org/10.15496/publikation-103844"},"language":"de","primary_location":{"id":"doi:10.15496/publikation-103844","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-103844","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.15496/publikation-103844","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shahmohammadi, Hassan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shahmohammadi, Hassan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T14509","display_name":"demographic modeling and climate adaptation","score":0.17599999904632568,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14509","display_name":"demographic modeling and climate adaptation","score":0.17599999904632568,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10471","display_name":"Climate Change Policy and Economics","score":0.06759999692440033,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12615","display_name":"Climate Change and Geoengineering","score":0.029400000348687172,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/normal-vision","display_name":"Normal vision","score":0.14560000598430634},{"id":"https://openalex.org/keywords/schmidt-camera","display_name":"Schmidt camera","score":0.13899999856948853},{"id":"https://openalex.org/keywords/fire-safety","display_name":"Fire safety","score":0.11169999837875366}],"concepts":[{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.4602999985218048},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.3756999969482422},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.21860000491142273},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18700000643730164},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1770000010728836},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.17260000109672546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.1712999939918518},{"id":"https://openalex.org/C2909061311","wikidata":"https://www.wikidata.org/wiki/Q555066","display_name":"Normal vision","level":2,"score":0.14560000598430634},{"id":"https://openalex.org/C87791202","wikidata":"https://www.wikidata.org/wiki/Q891841","display_name":"Schmidt camera","level":3,"score":0.13899999856948853},{"id":"https://openalex.org/C2989191132","wikidata":"https://www.wikidata.org/wiki/Q2997557","display_name":"Fire safety","level":2,"score":0.11169999837875366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.15496/publikation-103844","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-103844","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.15496/publikation-103844","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-103844","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Other"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.43945008516311646}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Das":[0],"Forschungsgebiet":[1],"\u201cVisuelle":[2],"Verankerung":[3,70,94,142,162,263,315,342],"von":[4,47,129,184,230,447,460,465,527,538,546],"Sprache\u201c":[5],"befasst":[6],"sich":[7,90,294,361],"mit":[8,18,120,475],"der":[9,20,38,82,86,126,228,237,280,367,388,428,482,536,544],"Konstruktion":[10],"kognitiv":[11],"plausibler":[12],"textueller":[13],"Sprachrepr\u00e4sentation":[14],"unter":[15,124,194,502],"Ber\u00fccksichtigung":[16],"und":[17,89,108,165,171,186,203,232,245,274,299,308,335,347,371,395,406,432,455,509],"Hilfe":[19],"visuellen":[21,121],"Perzeption.":[22],"Trotz":[23],"zahlreicher":[24],"fr\u00fcherer":[25],"Versuche,":[26],"Sprache":[27,185,202,370,381,449,487],"visuell":[28,109,250],"zu":[29,174,279,357,409,414],"verankern,":[30],"bleiben":[31],"noch":[32],"viele":[33],"Forschungsfragen":[34],"offen.":[35],"Erstens:":[36],"Bei":[37],"Darstellung":[39,170],"ihres":[40],"semantischen":[41],"Beziehungsnetzes":[42],"profitieren":[43],"Konkreta":[44,73],"ganz":[45],"nat\u00fcrlicherweise":[46],"Visueller":[48,69,341],"Verankerung,":[49],"inwieweit":[50],"dies":[51],"jedoch":[52],"auf":[53,92,234,296,377,515],"Abstrakta":[54],"\u00fcbertragbar":[55],"ist,":[56],"muss":[57],"dringend":[58],"weiter":[59],"untersucht":[60],"werden.":[61,146,191],"Die":[62,290,323,463,524],"vorliegende":[63],"Arbeit":[64,363],"postuliert":[65],"den":[66,249,320,338,530],"gro\u00dfen":[67,473],"Mehrwert":[68],"f\u00fcr":[71,139,217,404,499],"sowohl":[72,149],"als":[74,151,239,316,483],"auch":[75,138,152,240,295],"Abstrakta.":[76],"Wir":[77],"er\u00f6rtern":[78],"einen":[79],"neuartigen":[80],"Ansatz,":[81],"eine":[83,168,218,384,436,451],"vollst\u00e4ndige":[84],"Fusion":[85],"Modalit\u00e4ten":[87],"vermeidet":[88],"stattdessen":[91],"implizite":[93],"fokussiert.":[95],"Dies":[96,192],"erreichen":[97],"wir":[98,376,417],"durch":[99,337,345,392,435,450,494],"das":[100,241],"Erlernen":[101],"einer":[102],"umkehrbaren":[103],"Abbildung":[104,137],"zwischen":[105,201,319,369],"rein":[106],"textbasierten":[107],"verankerten":[110,251],"Repr\u00e4sentationen":[111,330],"mittels":[112,340,522],"Multi-task-Learning.":[113],"Dieser":[114],"Prozess":[115],"gleicht":[116],"die":[117,135,140,199,235,261,265,270,301,313,329,362,378,383,444,458],"textuellen":[118],"Einbettungen":[119,252,257,359],"Informationen":[122],"ab,":[123,382],"Beibehaltung":[125],"charakteristischen":[127],"Verteilung":[128],"W\u00f6rtern":[130],"in":[131,248,438,532],"Textkorpora.":[132],"Schlie\u00dflich":[133],"kann":[134,198],"gelernte":[136],"Visuelle":[141,262,314],"ungesehener":[143],"W\u00f6rter":[144,154],"\u00fcbertragen":[145],"Dieses":[147],"schlie\u00dft":[148],"konkrete":[150,393,439],"abstrakte":[153,405],"ein.":[155],"Zweitens:":[156],"Der":[157,441],"erste":[158],"Ansatz":[159,178,442],"zur":[160,182,517],"Visuellen":[161],"wird":[163,312],"erweitert":[164],"vereinfacht,":[166],"um":[167],"effektivere":[169],"bessere":[172],"Interpretierbarkeit":[173],"erreichen.":[175],"Mit":[176],"diesem":[177],"k\u00f6nnen":[179],"bestehende":[180],"Denkmodelle":[181],"Interaktion":[183],"visueller":[187,204,372,497],"Wahrnehmung":[188,205],"genauer":[189],"beleuchtet":[190],"beinhaltet":[193],"anderem":[195],"(1)":[196,470],"Wie":[197],"L\u00fccke":[200],"optimal":[206],"\u00fcberbr\u00fcckt":[207],"werden?":[208],"(2)":[209,489],"Inwieweit":[210],"ist":[211],"wahrnehmungsbasiertes":[212],"Wissen,":[213],"extrahiert":[214],"aus":[215,480,540],"Bildern,":[216],"kontextualisierte":[219],"Einbettung":[220],"moderner":[221],"Sprachmodelle":[222],"hilfreich?":[223],"In":[224],"neuen":[225],"Experimenten":[226],"werden":[227,273,350],"Einfluss":[229],"Konkretheit":[231],"Abstraktheit":[233],"Funktionst\u00fcchtigkeit":[236],"Modelle":[238,292],"Zusammenspiel":[242],"struktureller":[243],"\u00c4hnlichkeiten":[244],"semantischer":[246],"Beziehungen":[247],"untersucht.":[253],"Auch":[254],"hinsichtlich":[255],"kontextualisierter":[256],"ganzer":[258],"S\u00e4tze":[259],"bringt":[260],"Vorteile,":[264],"besonders":[266],"deutlich":[267],"hervortreten,":[268],"wenn":[269],"Trainings-Korpora":[271],"beschr\u00e4nkt":[272],"im":[275],"Umfang":[276],"vergleichbar":[277],"sind":[278],"Menge,":[281],"denen":[282],"Menschen":[283],"w\u00e4hrend":[284],"des":[285],"Spracherwerbs":[286],"ausgesetzt":[287],"sind.":[288],"Drittens:":[289],"vorgeschlagenen":[291],"lassen":[293],"andere":[297],"Sprachen":[298,321,332],"sogar":[300],"gleichzeitige":[302],"Betrachtung":[303],"mehrerer":[304],"Sprachen,":[305],"z.B.":[306],"Deutsch":[307,336],"Arabisch,":[309],"ausweiten.":[310],"Hier":[311],"ein":[317],"Informationsflaschenhals":[318],"eingef\u00fchrt.":[322],"Ergebnisse":[324],"deuten":[325],"darauf":[326],"hin,":[327],"dass":[328],"\u00e4hnlicher":[331],"wie":[333,535],"Englisch":[334],"Informationsaustausch":[339],"profitieren,":[343],"was":[344],"Wort\u00e4hnlichkeitsma\u00dfe":[346],"Kategorisierungsgenauigkeit":[348],"belegt":[349],"kann.":[351],"Im":[352],"Anschluss":[353],"an":[354,366],"umfangreiche":[355],"Studien":[356],"multimodalen":[358],"widmet":[360],"anderen":[364],"Anwendungen":[365,534],"Schnittstelle":[368],"Repr\u00e4sentation.":[373],"Insbesondere":[374],"zielen":[375],"Visualisierung":[379,429,459],"metaphorischer":[380],"entscheidende":[385],"Rolle":[386],"bei":[387,427],"Vermittlung":[389],"abstrakter":[390,433],"Konzepte":[391],"Erfahrungen":[394],"Emotionen":[396],"spielt.":[397],"Moderne":[398],"Text-Bild-Modelle":[399,425],"haben":[400],"Schwierigkeiten,":[401],"aussagekr\u00e4ftige":[402],"Bilder":[403],"bildhafte":[407],"Ausdr\u00fccke":[408,434],"synthetisieren.":[410],"Um":[411],"diese":[412],"Herausforderung":[413],"meistern,":[415],"stellen":[416],"ViPE":[418,423,466,528],"vor:":[419],"Visualize":[420],"Pretty-much":[421],"Everything.":[422],"unterst\u00fctzt":[424],"effektiv":[426],"beliebiger":[430],"figurativer":[431,448,461,486],"\u00dcbertragung":[437],"Textbausteine.":[440],"\u00fcbersetzt":[443],"impliziten":[445],"Bedeutungen":[446],"neue":[452],"visualisierbare":[453],"Textbeschreibung":[454],"erleichtert":[456],"so":[457],"Sprache.":[462],"Entwicklung":[464],"umfasst":[467],"drei":[468],"Hauptphasen:":[469],"Kompilieren":[471],"eines":[472,491,504,512,519],"Datensatzes":[474],"ca.":[476],"10":[477],"Millionen":[478],"Textzeilen":[479],"Liedtexten,":[481],"reichhaltige":[484],"Quelle":[485],"dient;":[488],"Erstellen":[490],"Datensatzes,":[492],"LyricCanvas,":[493],"Generieren":[495],"verrauschter":[496],"Elaborationen":[498],"alle":[500],"Liedtexte":[501],"Verwendung":[503],"Large":[505],"Language":[506],"Model":[507],"(LLM);":[508],"(3)":[510],"Nachtrainieren":[511],"mittelgro\u00dfen":[513],"Sprachmodells":[514],"LyricCanvas":[516],"Gewinnung":[518],"robusten":[520],"Modells":[521],"Wissensdestillation.":[523],"leistungsstarke":[525],"Zero-Shot-F\u00e4higkeit":[526],"erm\u00f6glicht":[529],"Einsatz":[531],"nachgelagerten":[533],"Generierung":[537],"Visualisierungen":[539],"abstrakten":[541],"Schl\u00fcsselw\u00f6rtern":[542],"oder":[543],"Erstellung":[545],"Musikvideos.":[547]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
