{"id":"https://openalex.org/W3194910448","doi":"https://doi.org/10.23919/mva51890.2021.9511360","title":"Saliency based Subject Selection for Diverse Image Captioning","display_name":"Saliency based Subject Selection for Diverse Image Captioning","publication_year":2021,"publication_date":"2021-07-25","ids":{"openalex":"https://openalex.org/W3194910448","doi":"https://doi.org/10.23919/mva51890.2021.9511360","mag":"3194910448"},"language":"en","primary_location":{"id":"doi:10.23919/mva51890.2021.9511360","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva51890.2021.9511360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Machine Vision and Applications (MVA)","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/A5023639562","display_name":"Quoc-An Luong","orcid":"https://orcid.org/0000-0002-4863-2694"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I4210110163","display_name":"Nippon Soken (Japan)","ror":"https://ror.org/01yk36x23","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110163"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Quoc-An Luong","raw_affiliation_strings":["SOKENDAI, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SOKENDAI, Japan","institution_ids":["https://openalex.org/I200475212","https://openalex.org/I4210110163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043253670","display_name":"Duc Minh Vo","orcid":"https://orcid.org/0000-0003-4839-032X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Duc Minh Vo","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101463320","display_name":"Akihiro Sugimoto","orcid":"https://orcid.org/0000-0001-9148-9822"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Sugimoto","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09447461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9991999864578247,"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":0.9951000213623047,"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":0.9325509071350098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7949103713035583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6286647915840149},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.6151045560836792},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6134509444236755},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6038885116577148},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5300659537315369},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5172408223152161},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4896562695503235},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44475057721138},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42408472299575806},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41456297039985657},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34595152735710144},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1468014121055603},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09907576441764832}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9325509071350098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949103713035583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6286647915840149},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.6151045560836792},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6134509444236755},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6038885116577148},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5300659537315369},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5172408223152161},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4896562695503235},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44475057721138},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42408472299575806},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41456297039985657},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34595152735710144},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1468014121055603},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09907576441764832},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mva51890.2021.9511360","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva51890.2021.9511360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 17th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W1988615825","https://openalex.org/W2077069816","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2252123671","https://openalex.org/W2506483933","https://openalex.org/W2745461083","https://openalex.org/W2798759657","https://openalex.org/W2886970679","https://openalex.org/W2901988662","https://openalex.org/W2923793772","https://openalex.org/W2939217524","https://openalex.org/W2950178297","https://openalex.org/W2954841306","https://openalex.org/W2962918138","https://openalex.org/W2963101956","https://openalex.org/W2963150697","https://openalex.org/W2963374482","https://openalex.org/W2963743213","https://openalex.org/W2982553922","https://openalex.org/W3008585839","https://openalex.org/W3011702232","https://openalex.org/W3034655362","https://openalex.org/W3034984754","https://openalex.org/W3035160838","https://openalex.org/W3035643210","https://openalex.org/W3083930292","https://openalex.org/W3107015116","https://openalex.org/W3107848485","https://openalex.org/W3109579959","https://openalex.org/W3110157234","https://openalex.org/W4213019668","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6691329670","https://openalex.org/W6760432180","https://openalex.org/W6771429369","https://openalex.org/W6781053692","https://openalex.org/W6898505805"],"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/W4287661223","https://openalex.org/W3116367518","https://openalex.org/W4392007279","https://openalex.org/W4387129494"],"abstract_inverted_index":{"Image":[0],"captioning":[1,60],"has":[2,79],"drawn":[3],"more":[4,6,152],"and":[5,110,197],"attention":[7],"because":[8,40],"of":[9,30,88,113,124],"its":[10,45,151],"practical":[11],"usefulness":[12],"in":[13,65,74,102,194],"many":[14],"multimedia":[15],"applications.":[16],"Multiple":[17],"criteria":[18],"such":[19],"as":[20,71],"accuracy,":[21],"detail":[22],"or":[23],"diversity":[24,35,196],"exist":[25],"to":[26,57,97,132,135,158],"evaluate":[27],"the":[28,37,98,103,108,125,133,146,160,163,166],"quality":[29],"generated":[31,50],"captions.":[32,76],"Among":[33],"them,":[34],"is":[36,130,165],"most":[38],"difficult":[39],"for":[41,140],"a":[42,72,89,117,122],"given":[43,90],"image,":[44,91],"multiple":[46],"captions":[47,175],"should":[48],"be":[49],"while":[51],"retaining":[52],"their":[53],"accuracy.":[54,198],"We":[55,144],"approach":[56],"diverse":[58],"image":[59,67],"by":[61,69],"explicitly":[62],"selecting":[63],"objects":[64],"an":[66],"one":[68,70],"subject":[73,134,164],"generating":[75,85],"Our":[77,185],"method":[78,187],"three":[80],"main":[81],"steps:":[82],"(1)":[83],"After":[84],"scene":[86,104,126,138,148],"graph":[87,105,127,139,149],"we":[92,120,172],"first":[93],"give":[94],"selection":[95],"priority":[96],"nodes":[99],"(namely,":[100],"subjects)":[101],"based":[106],"on":[107],"size":[109],"visual":[111],"saliency":[112],"objects.":[114],"(2)":[115],"With":[116],"selected":[118,167],"subject,":[119],"prune":[121],"portion":[123],"structure":[128],"that":[129],"irrelevant":[131],"have":[136],"subject-oriented":[137,147],"accurate":[141],"captioning.":[142],"(3)":[143],"convert":[145],"into":[150],"sentence-friendly":[153],"abstract":[154],"meaning":[155],"representation":[156],"(AMR)":[157],"generate":[159,174],"caption":[161],"whose":[162,176],"root.":[168],"In":[169],"this":[170],"way,":[171],"can":[173],"subjects":[177],"are":[178],"different":[179],"from":[180],"each":[181],"other,":[182],"achieving":[183],"diversity.":[184],"proposed":[186],"achieves":[188],"comparable":[189],"results":[190],"with":[191],"other":[192],"methods":[193],"both":[195]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}