{"id":"https://openalex.org/W2968389886","doi":"https://doi.org/10.1109/icra.2019.8794327","title":"An Interactive Scene Generation Using Natural Language","display_name":"An Interactive Scene Generation Using Natural Language","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2968389886","doi":"https://doi.org/10.1109/icra.2019.8794327","mag":"2968389886"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101653972","display_name":"Yu Cheng","orcid":"https://orcid.org/0000-0002-8686-4277"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Cheng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089007798","display_name":"Yan Shi","orcid":"https://orcid.org/0000-0002-7844-6227"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Shi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727179","display_name":"Zhiyong Sun","orcid":"https://orcid.org/0000-0001-9510-4897"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyong Sun","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064320219","display_name":"Dezhi Feng","orcid":"https://orcid.org/0000-0002-9727-6075"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dezhi Feng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100718940","display_name":"Lixin Dong","orcid":"https://orcid.org/0000-0002-8816-4944"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lixin Dong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101653972"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":0.2024,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.53430237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6957","last_page":"6963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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":0.9865000247955322,"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":0.8309188485145569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7007680535316467},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5235240459442139},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5174896717071533},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4950332045555115},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.46616464853286743},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4593181610107422},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4525529444217682},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4301917552947998},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4174419641494751},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32753807306289673},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3220140039920807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309188485145569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7007680535316467},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5235240459442139},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5174896717071533},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4950332045555115},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.46616464853286743},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4593181610107422},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4525529444217682},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4301917552947998},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4174419641494751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32753807306289673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3220140039920807},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8794327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1544201619","https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2059057465","https://openalex.org/W2085302753","https://openalex.org/W2097606805","https://openalex.org/W2123301721","https://openalex.org/W2124592697","https://openalex.org/W2125436662","https://openalex.org/W2154652894","https://openalex.org/W2162150860","https://openalex.org/W2250673545","https://openalex.org/W2337068785","https://openalex.org/W2405756170","https://openalex.org/W2526315025","https://openalex.org/W2533598788","https://openalex.org/W2553280805","https://openalex.org/W2740765036","https://openalex.org/W2770089303","https://openalex.org/W2949999304","https://openalex.org/W2963143316","https://openalex.org/W2963270749","https://openalex.org/W2963567641","https://openalex.org/W2963966654","https://openalex.org/W4236859963","https://openalex.org/W6632683562","https://openalex.org/W6638319203","https://openalex.org/W6639102338","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6683074461","https://openalex.org/W6687500345","https://openalex.org/W6713645886","https://openalex.org/W6746511181"],"related_works":["https://openalex.org/W2955859849","https://openalex.org/W2152921782","https://openalex.org/W382594479","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2151245229","https://openalex.org/W2140902089","https://openalex.org/W2030298461","https://openalex.org/W1510553545","https://openalex.org/W3020827637"],"abstract_inverted_index":{"Scene":[0],"generation":[1,16,46,87],"is":[2],"an":[3],"important":[4],"step":[5],"of":[6,23,54,101,123],"robotic":[7],"drawing.":[8],"Recent":[9],"works":[10],"have":[11,129],"shown":[12],"success":[13],"in":[14],"scene":[15,45,86],"conditioned":[17],"on":[18,39,75,105,116],"text":[19],"using":[20,58,78],"a":[21,49],"variety":[22],"approaches,":[24],"with":[25,98,135],"which":[26],"the":[27,44,61,69,82,85,99,102],"generated":[28,40,124],"scenes":[29,125],"cannot":[30],"be":[31],"revised":[32],"after":[33],"its":[34],"generation.":[35],"To":[36],"allow":[37],"modification":[38],"scenes,":[41],"we":[42],"model":[43],"process":[47],"as":[48],"discrete":[50],"event":[51],"system.":[52],"Instead":[53],"training":[55],"text-to-pixel":[56],"mappings":[57],"large":[59],"datasets,":[60],"proposed":[62],"approach":[63,104],"uses":[64],"object":[65],"instances":[66],"retrieved":[67],"from":[68],"Internet":[70],"to":[71,128],"synthesize":[72],"scenes.":[73],"Evaluated":[74],"128":[76],"experiments":[77],"MSCOCO":[79],"evaluation":[80,114],"dataset,":[81],"result":[83],"shows":[84,120],"performance":[88],"has":[89],"been":[90],"increased":[91],"by":[92],"197%,":[93],"22.3%,":[94],"and":[95,132],"55.7%":[96],"compared":[97],"state":[100],"art":[103],"three":[106],"standard":[107],"metrics":[108],"(CIDEr,":[109],"ROUGH-L,":[110],"METEOR),":[111],"respectively.":[112],"Human":[113],"conducted":[115],"Amazon":[117],"Mechanical":[118],"Turk":[119],"over":[121],"80%":[122],"are":[126],"considered":[127],"higher":[130],"recognizability":[131],"better":[133],"alignment":[134],"natural":[136],"language":[137],"descriptions":[138],"than":[139],"baseline":[140],"works.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}