{"id":"https://openalex.org/W3187369021","doi":"https://doi.org/10.1145/3474085.3475354","title":"Distributed Attention for Grounded Image Captioning","display_name":"Distributed Attention for Grounded Image Captioning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3187369021","doi":"https://doi.org/10.1145/3474085.3475354","mag":"3187369021"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475354","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/2108.01056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nenglun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nenglun Chen","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingjia Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjia Pan","raw_affiliation_strings":["Youtu Lab, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Runnan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Runnan Chen","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiwen Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Lin","raw_affiliation_strings":["Youtu Lab, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuqiang Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqiang Ren","raw_affiliation_strings":["Youtu Lab, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haolei Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolei Yuan","raw_affiliation_strings":["Youtu Lab, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaowei Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Guo","raw_affiliation_strings":["Youtu Lab, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feiyue Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyue Huang","raw_affiliation_strings":["Youtu Lab, Tencent, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenping Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenping Wang","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4554,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.84113159,"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":"1966","last_page":"1975"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9961000084877014,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9958999752998352,"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":0.8428000211715698},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5680999755859375},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5547000169754028},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5238999724388123},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4643000066280365},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45179998874664307}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8428000211715698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6053000092506409},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48410001397132874},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3799000084400177},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2896000146865845}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475354","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.01056","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.01056","pdf_url":"https://arxiv.org/pdf/2108.01056","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:2108.01056","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.01056","pdf_url":"https://arxiv.org/pdf/2108.01056","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1934621328","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W1995820507","https://openalex.org/W2016016818","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2194775991","https://openalex.org/W2247513039","https://openalex.org/W2277195237","https://openalex.org/W2295107390","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2883554151","https://openalex.org/W2962762462","https://openalex.org/W2962964995","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963445828","https://openalex.org/W2963603913","https://openalex.org/W2963783181","https://openalex.org/W2964276121","https://openalex.org/W2964345792","https://openalex.org/W2968101724","https://openalex.org/W2969557970","https://openalex.org/W2969764577","https://openalex.org/W2981663434","https://openalex.org/W2986670728","https://openalex.org/W2992308087","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035323998","https://openalex.org/W3037533539","https://openalex.org/W3048686909","https://openalex.org/W3092659741"],"related_works":[],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,15,24,27,35,39,47,79,92,103,111,126,145,160,163,166,177,186,194],"problem":[3,132],"of":[4,26,49,65,165,179,188],"weakly":[5,58],"supervised":[6,59,81],"grounded":[7,33],"image":[8,28],"captioning.":[9],"That":[10],"is,":[11],"given":[12],"an":[13],"image,":[14],"goal":[16],"is":[17,43,90],"to":[18,34,46,68,124,143,147],"automatically":[19],"generate":[20],"a":[21,119,139,172],"sentence":[22],"describing":[23],"context":[25],"with":[29,155,193],"each":[30],"noun":[31],"word":[32,53],"corresponding":[36],"region":[37,52,168,174],"in":[38,133],"image.":[40],"This":[41],"task":[42],"challenging":[44],"due":[45],"lack":[48],"explicit":[50],"fine-grained":[51],"alignments":[54],"as":[55,129],"supervision.":[56],"Previous":[57],"methods":[60],"mainly":[61],"explore":[62],"various":[63],"kinds":[64],"regularization":[66],"schemes":[67],"improve":[69],"attention":[70,93,141],"accuracy.":[71],"However,":[72],"their":[73],"performances":[74],"are":[75],"still":[76],"far":[77],"from":[78,150],"fully":[80],"ones.":[82],"One":[83],"main":[84],"issue":[85],"that":[86,91,175],"has":[87],"been":[88],"ignored":[89],"for":[94],"generating":[95,159],"visually":[96],"groundable":[97],"words":[98],"may":[99],"only":[100],"focus":[101],"on":[102],"most":[104],"discriminate":[105],"parts":[106],"and":[107],"can":[108],"not":[109],"cover":[110],"whole":[112],"object.":[113],"To":[114],"this":[115],"end,":[116],"we":[117,137],"propose":[118],"simple":[120],"yet":[121],"effective":[122],"method":[123,191],"alleviate":[125],"issue,":[127],"termed":[128],"partial":[130],"grounding":[131],"our":[134,189],"paper.":[135],"Specifically,":[136],"design":[138],"distributed":[140],"mechanism":[142],"enforce":[144],"network":[146],"aggregate":[148],"information":[149],"multiple":[151],"spatially":[152],"different":[153],"regions":[154],"consistent":[156],"semantics":[157],"while":[158],"words.":[161],"Therefore,":[162],"union":[164],"focused":[167],"proposals":[169],"should":[170],"form":[171],"visual":[173],"encloses":[176],"object":[178],"interest":[180],"completely.":[181],"Extensive":[182],"experiments":[183],"have":[184],"demonstrated":[185],"superiority":[187],"proposed":[190],"compared":[192],"state-of-the-arts.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2021-08-16T00:00:00"}