{"id":"https://openalex.org/W2766237723","doi":"https://doi.org/10.1145/3123266.3123391","title":"Adaptively Attending to Visual Attributes and Linguistic Knowledge for Captioning","display_name":"Adaptively Attending to Visual Attributes and Linguistic Knowledge for Captioning","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2766237723","doi":"https://doi.org/10.1145/3123266.3123391","mag":"2766237723"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066557235","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-3836-4163"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["University of Queensland, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1345","last_page":"1353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.993399977684021,"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":0.9927999973297119,"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/closed-captioning","display_name":"Closed captioning","score":0.904393196105957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8345898389816284},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5898937582969666},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5419645309448242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310678482055664},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5101547837257385},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5077112913131714},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49452683329582214},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49300524592399597},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4301985502243042},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1726418435573578}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.904393196105957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345898389816284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5898937582969666},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5419645309448242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310678482055664},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5101547837257385},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5077112913131714},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49452683329582214},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49300524592399597},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4301985502243042},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1726418435573578},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3123266.3123391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:705066","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/126307","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/126307","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1514535095","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1686810756","https://openalex.org/W1858383477","https://openalex.org/W1861492603","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W1931639407","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W1996430422","https://openalex.org/W2041259983","https://openalex.org/W2064675550","https://openalex.org/W2080672747","https://openalex.org/W2101105183","https://openalex.org/W2128272608","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2152984213","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2173180041","https://openalex.org/W2250539671","https://openalex.org/W2339652278","https://openalex.org/W2412696269","https://openalex.org/W2430164002","https://openalex.org/W2435696002","https://openalex.org/W2523937091","https://openalex.org/W2524558894","https://openalex.org/W2525981529","https://openalex.org/W2526544345","https://openalex.org/W2527145521","https://openalex.org/W2527321146","https://openalex.org/W2575842049","https://openalex.org/W2665436006","https://openalex.org/W2741263162","https://openalex.org/W2953022248","https://openalex.org/W2963576560","https://openalex.org/W2964137974","https://openalex.org/W2964241990","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Visual":[0],"content":[1,75],"description":[2],"has":[3],"been":[4],"attracting":[5],"broad":[6],"research":[7],"attention":[8,63,134,154],"in":[9],"multimedia":[10],"community":[11],"because":[12],"it":[13],"deeply":[14],"uncovers":[15],"intrinsic":[16],"semantic":[17,147],"facet":[18],"of":[19,112,123,146,175],"visual":[20,26,48,66,74,88],"data.":[21],"Most":[22],"existing":[23],"approaches":[24],"formulate":[25],"captioning":[27],"as":[28,151],"machine":[29],"translation":[30],"task":[31],"(i.e.,":[32],"from":[33],"vision":[34],"to":[35,46,72,90,100,119,131,142,180],"language)":[36],"via":[37],"a":[38,60,83,116,139,144],"top-down":[39],"paradigm":[40],"with":[41],"global":[42],"attention,":[43],"which":[44,68,126],"ignores":[45],"distinguish":[47],"and":[49,94,167],"non-visual":[50],"parts":[51],"during":[52,101],"word":[53,103],"generation.":[54],"In":[55],"this":[56],"work,":[57],"we":[58,81,137],"propose":[59],"novel":[61],"adaptive":[62],"strategy":[64],"for":[65,149],"captioning,":[67],"can":[69],"selectively":[70],"attend":[71,99],"salient":[73],"based":[76],"on":[77,161],"linguistic":[78],"knowledge.":[79],"Specifically,":[80],"design":[82],"key":[84],"control":[85],"unit,":[86],"termed":[87],"gate,":[89],"adaptively":[91],"decide":[92],"\"when\"":[93],"\"what\"":[95],"the":[96,102,109,121,128,152,158,173],"language":[97,113],"generator":[98,114],"generation":[104],"process.":[105],"We":[106,156],"map":[107],"all":[108],"preceding":[110],"outputs":[111],"into":[115],"latent":[117],"space":[118],"derive":[120],"representation":[122],"sentence":[124],"structures,":[125],"assists":[127],"\"visual":[129],"gate\"":[130],"choose":[132],"appropriate":[133],"timing.":[135],"Meanwhile,":[136],"employ":[138],"bottom-up":[140],"workflow":[141],"learn":[143],"pool":[145],"attributes":[148],"serving":[150],"propositional":[153],"resources.":[155],"evaluate":[157],"proposed":[159,177],"approach":[160,178],"two":[162],"commonly-used":[163],"benchmarks,":[164],"i.e.,":[165],"MSCOCO":[166],"MSVD.":[168],"The":[169],"experimental":[170],"results":[171],"demonstrate":[172],"superiority":[174],"our":[176],"compared":[179],"several":[181],"state-of-the-art":[182],"methods.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}