{"id":"https://openalex.org/W4297644311","doi":"https://doi.org/10.1145/3503161.3548189","title":"Multi-Modal Experience Inspired AI Creation","display_name":"Multi-Modal Experience Inspired AI Creation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4297644311","doi":"https://doi.org/10.1145/3503161.3548189"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548189","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548189","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.02427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101467862","display_name":"Qian Cao","orcid":"https://orcid.org/0000-0001-7141-6159"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qian Cao","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385702","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0002-1805-5435"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505571","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0002-2163-7401"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002846606","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0002-2306-7596"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Jiang","raw_affiliation_strings":["Poisson Lab, Huawei, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Poisson Lab, Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115589535","display_name":"Guang Yang","orcid":"https://orcid.org/0000-0002-0012-3831"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Yang","raw_affiliation_strings":["Poisson Lab, Huawei, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Poisson Lab, Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000839824","display_name":"Zhao Cao","orcid":"https://orcid.org/0000-0002-4214-7858"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Cao","raw_affiliation_strings":["Poisson Lab, Huawei, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Poisson Lab, Huawei, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101467862"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.1193,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.41247871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"242","issue":null,"first_page":"1445","last_page":"1454"},"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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9894999861717224,"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":0.8411591053009033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6150930523872375},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5949066281318665},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5389050245285034},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5233377814292908},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5093563795089722},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.47626397013664246},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45950692892074585},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45032113790512085},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42711341381073},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14500415325164795},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.13777810335159302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8411591053009033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6150930523872375},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5949066281318665},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5389050245285034},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5233377814292908},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5093563795089722},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47626397013664246},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45950692892074585},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45032113790512085},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42711341381073},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14500415325164795},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.13777810335159302},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548189","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548189","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.02427","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.02427","pdf_url":"https://arxiv.org/pdf/2209.02427","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.02427","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.02427","pdf_url":"https://arxiv.org/pdf/2209.02427","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W116271097","https://openalex.org/W170842245","https://openalex.org/W1593271688","https://openalex.org/W2250842199","https://openalex.org/W2461084364","https://openalex.org/W2804809828","https://openalex.org/W2883891001","https://openalex.org/W2890721473","https://openalex.org/W2896124351","https://openalex.org/W2905544595","https://openalex.org/W2952771545","https://openalex.org/W2953486038","https://openalex.org/W2963109634","https://openalex.org/W2963829244","https://openalex.org/W2969348315","https://openalex.org/W2982260486","https://openalex.org/W2998356391","https://openalex.org/W3048921104","https://openalex.org/W3087871082","https://openalex.org/W3090449556","https://openalex.org/W3091499453","https://openalex.org/W3100995281","https://openalex.org/W3103668594","https://openalex.org/W3106477714","https://openalex.org/W3109320561","https://openalex.org/W4212937970","https://openalex.org/W4240010157","https://openalex.org/W4285751616","https://openalex.org/W4289387529","https://openalex.org/W4297889967","https://openalex.org/W6604650031"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2185469136","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4301143707","https://openalex.org/W2952745240","https://openalex.org/W2941608206"],"abstract_inverted_index":{"AI":[0,77],"creation,":[1],"such":[2,65],"as":[3],"poem":[4],"or":[5,40],"lyrics":[6],"generation,":[7],"has":[8,112],"attracted":[9],"increasing":[10],"attention":[11,149],"from":[12],"both":[13,215],"industry":[14],"and":[15,37,59,73,116,123,172,217,222],"academic":[16],"communities,":[17],"with":[18,98,146,198],"many":[19],"promising":[20],"models":[21],"proposed":[22],"in":[23,44,68,130,210],"the":[24,32,99,109,118,128,165,174],"past":[25],"few":[26],"years.":[27],"Existing":[28],"methods":[29],"usually":[30,47],"estimate":[31],"outputs":[33],"based":[34,80,92,213],"on":[35,81,93,214],"single":[36],"independent":[38],"visual":[39],"textual":[41],"information.":[42,96],"However,":[43],"reality,":[45],"humans":[46],"make":[48],"creations":[49],"according":[50],"to":[51,89,113],"their":[52],"experiences,":[53],"which":[54],"may":[55],"involve":[56],"different":[57,121],"modalities":[58,122],"be":[60],"sequentially":[61],"correlated.":[62],"To":[63,134,168],"model":[64,111,197,212],"human":[66,82],"capabilities,":[67],"this":[69,102,170,188],"paper,":[70],"we":[71,86,138,155,179,190,205],"define":[72],"solve":[74],"a":[75,131,141,147,158,182,199],"novel":[76],"creation":[78],"problem":[79,171],"experiences.":[83],"More":[84],"specifically,":[85],"study":[87],"how":[88],"generate":[90],"texts":[91],"sequential":[94,132,166],"multi-modal":[95,148,184],"Compared":[97],"previous":[100],"works,":[101],"task":[103],"is":[104],"much":[105],"more":[106,152],"difficult":[107],"because":[108],"designed":[110],"well":[114],"understand":[115],"adapt":[117],"semantics":[119],"among":[120],"effectively":[124],"convert":[125],"them":[126],"into":[127],"output":[129],"manner.":[133],"alleviate":[135],"these":[136],"difficulties,":[137],"firstly":[139],"design":[140],"multi-channel":[142],"sequence-to-sequence":[143],"architecture":[144],"equipped":[145],"network.":[150],"For":[151],"effective":[153],"optimization,":[154],"then":[156],"propose":[157],"curriculum":[159],"negative":[160],"sampling":[161],"strategy":[162],"tailored":[163],"for":[164],"inputs.":[167],"benchmark":[169],"demonstrate":[173,207],"effectiveness":[175],"of":[176,201],"our":[177,196,211],"model,":[178],"manually":[180],"labeled":[181],"new":[183],"experience":[185],"dataset.":[186],"With":[187],"dataset,":[189],"conduct":[191],"extensive":[192],"experiments":[193],"by":[194],"comparing":[195],"series":[200],"representative":[202],"baselines,":[203],"where":[204],"can":[206],"significant":[208],"improvements":[209],"automatic":[216],"human-centered":[218],"metrics.":[219],"The":[220],"code":[221],"data":[223],"are":[224],"available":[225],"at:":[226],"https://github.com/Aman-4-Real/MMTG.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}