{"id":"https://openalex.org/W6907632289","doi":"https://doi.org/10.2312/egs.20221026","title":"Scene Synthesis with Automated Generation of Textual Descriptions","display_name":"Scene Synthesis with Automated Generation of Textual Descriptions","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W6907632289","doi":"https://doi.org/10.2312/egs.20221026"},"language":"en","primary_location":{"id":"doi:10.2312/egs.20221026","is_oa":true,"landing_page_url":"https://doi.org/10.2312/egs.20221026","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":[],"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":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.2312/egs.20221026","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"M\u00fcller-Huschke, Julian","orcid":null},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"M\u00fcller-Huschke, Julian","raw_affiliation_strings":["University of Innsbruck, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ritter, Marcel","orcid":"https://orcid.org/0000-0003-4495-4546"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ritter, Marcel","raw_affiliation_strings":["University of Innsbruck, Austria"],"raw_orcid":"https://orcid.org/0000-0003-4495-4546","affiliations":[{"raw_affiliation_string":"University of Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"last","author":{"id":null,"display_name":"Harders, Matthias","orcid":null},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Harders, Matthias","raw_affiliation_strings":["University of Innsbruck"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Innsbruck","institution_ids":["https://openalex.org/I190249584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21623198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8064000010490417,"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":0.8064000010490417,"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/T12290","display_name":"Human Motion and Animation","score":0.04129999876022339,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.02419999986886978,"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/closed-captioning","display_name":"Closed captioning","score":0.7746000289916992},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.6358000040054321},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5871000289916992},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5353000164031982},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4489000141620636},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4487000107765198},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.40380001068115234},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.4032999873161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7890999913215637},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7746000289916992},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.6358000040054321},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5871000289916992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5496000051498413},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5184999704360962},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.40380001068115234},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.36230000853538513},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.2944999933242798},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C205208641","wikidata":"https://www.wikidata.org/wiki/Q273404","display_name":"Pie chart","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2312/egs.20221026","is_oa":true,"landing_page_url":"https://doi.org/10.2312/egs.20221026","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":[],"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":""}],"best_oa_location":{"id":"doi:10.2312/egs.20221026","is_oa":true,"landing_page_url":"https://doi.org/10.2312/egs.20221026","pdf_url":null,"source":{"id":"https://openalex.org/S7407052899","display_name":"Eurographics","issn_l":null,"issn":[],"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":""},"sustainable_development_goals":[{"score":0.45014718174934387,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Most":[0],"current":[1],"research":[2],"on":[3,13],"automatically":[4],"captioning":[5],"and":[6,49,63,74,85,116],"describing":[7],"scenes":[8,44],"with":[9],"spatial":[10],"content":[11],"focuses":[12],"images.":[14],"We":[15],"outline":[16],"that":[17],"generating":[18],"descriptive":[19],"text":[20],"for":[21],"a":[22,30,64,77,89],"synthesized":[23],"3D":[24],"scene":[25],"can":[26],"be":[27],"achieved":[28],"via":[29],"suitable":[31],"intermediate":[32],"representation":[33],"employed":[34],"in":[35,88],"the":[36,94,101,111,118,127,138,146],"synthesis":[37],"algorithm.":[38],"As":[39],"an":[40],"example,":[41],"we":[42,92],"synthesize":[43],"of":[45,96,129],"medieval":[46],"village":[47],"settings,":[48],"generate":[50],"their":[51],"descriptions.":[52],"Our":[53],"system":[54],"employs":[55],"graph":[56],"grammars,":[57],"Markov":[58],"Chain":[59],"Monte":[60],"Carlo":[61],"optimization,":[62],"natural":[65],"language":[66],"generation":[67],"pipeline.":[68],"Randomly":[69],"placed":[70],"objects":[71],"are":[72],"evaluated":[73],"optimized":[75],"by":[76,99,107,137],"cost":[78],"function":[79],"capturing":[80],"neighborhood":[81],"relations,":[82],"path":[83],"layouts,":[84],"collisions.":[86],"Further,":[87],"pilot":[90],"study":[91,139],"assess":[93],"performance":[95],"our":[97,123],"framework":[98],"comparing":[100],"generated":[102,124],"descriptions":[103,133],"to":[104],"others":[105],"provided":[106],"human":[108,132],"subjects.":[109],"While":[110],"latter":[112],"were":[113],"often":[114],"short":[115],"low-effort,":[117],"highest-rated":[119],"ones":[120],"clearly":[121],"outperform":[122],"ones.":[125,148],"Nevertheless,":[126],"average":[128],"all":[130],"collected":[131],"was":[134],"indeed":[135],"rated":[136],"participants":[140],"as":[141],"being":[142],"less":[143],"accurate":[144],"than":[145],"automated":[147]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}