{"id":"https://openalex.org/W2990216675","doi":"https://doi.org/10.1109/tmm.2019.2954750","title":"Visual Relationship Embedding Network for Image Paragraph Generation","display_name":"Visual Relationship Embedding Network for Image Paragraph Generation","publication_year":2019,"publication_date":"2019-11-20","ids":{"openalex":"https://openalex.org/W2990216675","doi":"https://doi.org/10.1109/tmm.2019.2954750","mag":"2990216675"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2954750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2954750","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5108278406","display_name":"Wenbin Che","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenbin Che","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","Research Center of Intelligent Interface and Human Computer Interaction, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Research Center of Intelligent Interface and Human Computer Interaction, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079412089","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Fan","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","Research Center of Intelligent Interface and Human Computer Interaction, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Research Center of Intelligent Interface and Human Computer Interaction, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013727612","display_name":"Ruiqin Xiong","orcid":"https://orcid.org/0000-0001-9796-0478"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqin Xiong","raw_affiliation_strings":["Institute of Digital Media, School of Electronic Engineering and Computer Science, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Digital Media, School of Electronic Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100600353","display_name":"Debin Zhao","orcid":"https://orcid.org/0000-0003-3434-9967"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Debin Zhao","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","Research Center of Intelligent Interface and Human Computer Interaction, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Research Center of Intelligent Interface and Human Computer Interaction, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108278406"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":1.7208,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.88151106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"22","issue":"9","first_page":"2307","last_page":"2320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.994700014591217,"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":0.9943000078201294,"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/paragraph","display_name":"Paragraph","score":0.895626425743103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.846022367477417},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6934948563575745},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6487686634063721},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6099621057510376},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5961418151855469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5771772265434265},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5504579544067383},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.52838534116745},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5057179927825928},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4231989085674286},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4200119376182556},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15700086951255798},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0837424099445343}],"concepts":[{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.895626425743103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.846022367477417},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6934948563575745},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6487686634063721},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6099621057510376},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5961418151855469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771772265434265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5504579544067383},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.52838534116745},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5057179927825928},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4231989085674286},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4200119376182556},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15700086951255798},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0837424099445343},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2954750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2954750","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1342049569","display_name":null,"funder_award_id":"61972115","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4220777412","display_name":null,"funder_award_id":"61631017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5048440815","display_name":null,"funder_award_id":"61872116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W179875071","https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1810943226","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1923211482","https://openalex.org/W1930223417","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2017313218","https://openalex.org/W2099471712","https://openalex.org/W2109586012","https://openalex.org/W2132339004","https://openalex.org/W2133459682","https://openalex.org/W2159243025","https://openalex.org/W2169393274","https://openalex.org/W2185175083","https://openalex.org/W2193413348","https://openalex.org/W2194187530","https://openalex.org/W2277195237","https://openalex.org/W2294053032","https://openalex.org/W2294978630","https://openalex.org/W2407414618","https://openalex.org/W2479423890","https://openalex.org/W2481240925","https://openalex.org/W2528841789","https://openalex.org/W2549599535","https://openalex.org/W2550553598","https://openalex.org/W2552002300","https://openalex.org/W2575842049","https://openalex.org/W2591644541","https://openalex.org/W2607855566","https://openalex.org/W2625219738","https://openalex.org/W2754191212","https://openalex.org/W2754689878","https://openalex.org/W2890718122","https://openalex.org/W2897544947","https://openalex.org/W2906314281","https://openalex.org/W2951183276","https://openalex.org/W2962835968","https://openalex.org/W2963758027","https://openalex.org/W3099884890","https://openalex.org/W4285719527","https://openalex.org/W4320013936","https://openalex.org/W6607333740","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6638273328","https://openalex.org/W6639204139","https://openalex.org/W6676497082","https://openalex.org/W6683512859","https://openalex.org/W6687566353","https://openalex.org/W6694395031","https://openalex.org/W6714077321","https://openalex.org/W6721769334","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","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/W2597655663"],"abstract_inverted_index":{"Image":[0],"paragraph":[1,32,37,82,169],"generation":[2,33,83],"aims":[3],"to":[4,26,74,105],"produce":[5,36],"a":[6,10,47,80,95,140],"complete":[7],"description":[8],"of":[9,131],"given":[11],"image.":[12,30],"This":[13],"task":[14],"is":[15,103],"more":[16,76,165],"challenging":[17],"than":[18,171],"image":[19],"captioning,":[20],"which":[21],"only":[22],"generates":[23],"one":[24],"sentence":[25],"describe":[27],"the":[28,125,157],"entire":[29],"Traditional":[31],"methods":[34],"usually":[35],"descriptions":[38,170],"based":[39],"on":[40],"individual":[41],"regions":[42,107],"that":[43,85,108,153],"are":[44,57,118,135],"detected":[45],"by":[46,139,154],"Region":[48],"Proposal":[49],"Network":[50,101],"(RPN).":[51],"However,":[52],"relationships":[53,117],"among":[54],"visual":[55,77,88,126],"objects":[56],"either":[58],"ignored":[59],"or":[60,112],"utilized":[61],"in":[62,66],"an":[63,121],"implicit":[64],"manner":[65],"previous":[67,172],"work.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"attempt":[73],"explore":[75],"information":[78],"through":[79,120],"novel":[81,96],"network":[84,145],"explicitly":[86,155],"incorporates":[87],"relationship":[89,129,159],"semantics":[90,130],"when":[91],"producing":[92],"descriptions.":[93],"First,":[94],"Relation":[97],"Pair":[98],"Generative":[99],"Adversarial":[100],"(RP-GAN)":[102],"designed":[104],"locate":[106],"may":[109],"cover":[110],"subjective":[111],"objective":[113],"elements.":[114],"Then,":[115],"their":[116],"inferred":[119],"attention-based":[122],"network.":[123],"Finally,":[124],"features":[127],"and":[128,167],"valid":[132],"relation":[133],"pairs":[134],"taken":[136],"as":[137],"inputs":[138],"Long":[141],"Short-Term":[142],"Memory":[143],"(LSTM)":[144],"for":[146],"generating":[147],"sentences.":[148],"The":[149],"experimental":[150],"results":[151],"show":[152],"utilizing":[156],"predicted":[158],"information,":[160],"our":[161],"proposed":[162],"method":[163],"obtains":[164],"accurate":[166],"informative":[168],"methods.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}