{"id":"https://openalex.org/W3010564927","doi":"https://doi.org/10.1145/3374587.3374649","title":"PororoGAN","display_name":"PororoGAN","publication_year":2019,"publication_date":"2019-12-06","ids":{"openalex":"https://openalex.org/W3010564927","doi":"https://doi.org/10.1145/3374587.3374649","mag":"3010564927"},"language":"en","primary_location":{"id":"doi:10.1145/3374587.3374649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3374587.3374649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence","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/A5046229717","display_name":"Gangyan Zeng","orcid":"https://orcid.org/0000-0003-2696-8549"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gangyan Zeng","raw_affiliation_strings":["School of Information and, Communication Engineering, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and, Communication Engineering, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376709","display_name":"Zhaohui Li","orcid":"https://orcid.org/0000-0002-6076-8367"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohui Li","raw_affiliation_strings":["School of Information and, Communication Engineering, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information and, Communication Engineering, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100368686","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0002-1335-2780"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["School of Data Science and Media, Intelligence, Communication, University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science and Media, Intelligence, Communication, University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046229717"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":1.124,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.82872229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"159"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9976000189781189,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.991100013256073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8313107490539551},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6640170812606812},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6276182532310486},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6188953518867493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5924322009086609},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.5703785419464111},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5599203705787659},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5562835335731506},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.552692711353302},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5343930125236511},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5143545866012573},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5115531086921692},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4937969148159027},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4815785884857178},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32756245136260986},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09484589099884033},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0660870373249054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313107490539551},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6640170812606812},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6276182532310486},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6188953518867493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5924322009086609},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.5703785419464111},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5599203705787659},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5562835335731506},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.552692711353302},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5343930125236511},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5143545866012573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5115531086921692},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4937969148159027},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4815785884857178},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32756245136260986},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09484589099884033},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0660870373249054},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3374587.3374649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3374587.3374649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2099471712","https://openalex.org/W2117539524","https://openalex.org/W2131774270","https://openalex.org/W2183341477","https://openalex.org/W2788191623","https://openalex.org/W2891802882","https://openalex.org/W2904190302","https://openalex.org/W2950577311","https://openalex.org/W2962931774","https://openalex.org/W2963143316","https://openalex.org/W2963184176","https://openalex.org/W2963413689","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2979672901"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W2391800119","https://openalex.org/W2595239241","https://openalex.org/W2799181378","https://openalex.org/W2052919063","https://openalex.org/W3003711649","https://openalex.org/W2904173691","https://openalex.org/W4365517254","https://openalex.org/W270947280","https://openalex.org/W2366944513"],"abstract_inverted_index":{"Generating":[0],"a":[1,6,10,45,79],"sequence":[2],"of":[3,55,125],"images":[4],"from":[5,38],"multi-sentence":[7],"paragraph":[8],"is":[9,34,43],"recently":[11],"proposed":[12],"task":[13],"called":[14],"Story-Visualization.":[15],"In":[16,94],"this":[17,75],"task,":[18],"how":[19],"to":[20,107,121],"keep":[21],"the":[22,31,35,49,123,136],"global":[23,109],"consistency":[24],"across":[25],"dynamic":[26],"scenes":[27],"and":[28,52,91,102,110,129],"characters":[29],"in":[30],"story":[32,81],"flow":[33],"distinct":[36],"difference":[37],"other":[39],"single-image":[40],"works,":[41],"which":[42,86],"also":[44],"significant":[46],"challenge.":[47],"However,":[48],"visual":[50],"quality":[51],"semantic":[53,66],"relevance":[54],"existing":[56],"results":[57],"are":[58],"not":[59],"satisfying":[60],"when":[61],"handling":[62],"datasets":[63],"with":[64],"high":[65],"complexity,":[67],"such":[68],"as":[69],"Pororo-SV":[70],"cartoon":[71],"dataset.":[72],"To":[73],"address":[74],"issue,":[76],"we":[77,96,115],"propose":[78],"new":[80],"visualization":[82],"model":[83],"named":[84],"PororoGAN,":[85],"jointly":[87],"considers":[88],"story-to-image-sequence,":[89],"sentence-to-image":[90],"word-to-image-patch":[92],"alignment.":[93],"particular,":[95],"introduce":[97],"ASE":[98],"(aligned":[99],"sentence":[100],"encoder)":[101,106],"AWE":[103],"(attentional":[104],"word":[105],"improve":[108,122],"local":[111],"relevance,":[112],"respectively.":[113],"Additionally,":[114],"add":[116],"an":[117],"image":[118],"patches":[119],"discriminator":[120],"reality":[124],"results.":[126],"Both":[127],"quantitative":[128],"qualitative":[130],"studies":[131],"show":[132],"that":[133],"PororoGAN":[134],"outperforms":[135],"state-of-the-art":[137],"models.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2020-03-13T00:00:00"}