{"id":"https://openalex.org/W4416078212","doi":"https://doi.org/10.1109/access.2025.3631093","title":"Semantic Alignment on Action for Image Captioning","display_name":"Semantic Alignment on Action for Image Captioning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416078212","doi":"https://doi.org/10.1109/access.2025.3631093"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3631093","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3631093","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3631093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094054993","display_name":"Da Huo","orcid":"https://orcid.org/0009-0004-5490-0407"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Da Huo","raw_affiliation_strings":["Nagoya University, Nagoya, Aichi, Japan","Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102907439","display_name":"Marc A. Kastner","orcid":"https://orcid.org/0000-0002-9193-5973"},"institutions":[{"id":"https://openalex.org/I57930482","display_name":"Hiroshima City University","ror":"https://ror.org/001et4e78","country_code":"JP","type":"education","lineage":["https://openalex.org/I57930482"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc A. Kastner","raw_affiliation_strings":["Hiroshima City University, Hiroshima, Japan","Hiroshima City University, Asaminami-ku, Hiroshima, Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima City University, Hiroshima, Japan","institution_ids":["https://openalex.org/I57930482"]},{"raw_affiliation_string":"Hiroshima City University, Asaminami-ku, Hiroshima, Hiroshima, Japan","institution_ids":["https://openalex.org/I57930482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036735172","display_name":"Takatsugu Hirayama","orcid":"https://orcid.org/0000-0001-6290-9680"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takatsugu Hirayama","raw_affiliation_strings":["Nagoya University, Nagoya, Aichi, Japan","Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047823141","display_name":"Takahiro Komamizu","orcid":"https://orcid.org/0000-0002-3041-4330"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Komamizu","raw_affiliation_strings":["Nagoya University, Nagoya, Aichi, Japan","Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027960360","display_name":"Yasutomo Kawanishi","orcid":"https://orcid.org/0000-0002-3799-4550"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasutomo Kawanishi","raw_affiliation_strings":["Nagoya University, Nagoya, Aichi, Japan","Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034941095","display_name":"Ichiro Ide","orcid":"https://orcid.org/0000-0003-3942-9296"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ichiro Ide","raw_affiliation_strings":["Nagoya University, Nagoya, Aichi, Japan","Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Chikusa-ku, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5094054993"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36273871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"199615","last_page":"199629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9940999746322632,"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":0.9940999746322632,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0010999999940395355,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0005000000237487257,"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":0.965399980545044},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6191999912261963},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.599399983882904},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5879999995231628},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5418999791145325},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4991999864578247},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4821999967098236}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.965399980545044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302000164985657},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.599399983882904},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5879999995231628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5795999765396118},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4821999967098236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47510001063346863},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4122999906539917},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38449999690055847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36410000920295715},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35010001063346863},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2646999955177307}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3631093","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3631093","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:932fed4693124fbe9d89a583d6ea7f29","is_oa":true,"landing_page_url":"https://doaj.org/article/932fed4693124fbe9d89a583d6ea7f29","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 199615-199629 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3631093","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3631093","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,174],"is":[2,236,250],"a":[3,132,148,251],"popular":[4],"task":[5],"in":[6,67,79,88,163,198,216,277],"vision":[7],"and":[8,24,55,73,117,189,218,269],"language":[9],"processing,":[10],"which":[11,82,119,160,247],"aims":[12],"to":[13,30,50,140,195,253,273],"generate":[14],"textual":[15],"descriptions":[16],"for":[17,150,266],"images.":[18],"Previously,":[19],"it":[20],"simply":[21],"used":[22],"image":[23,54,89,127],"text":[25,56],"as":[26,47,224],"input":[27,42],"with":[28,57],"self-attention":[29],"capture":[31],"global":[32],"dependencies.":[33],"Recent":[34],"research":[35],"further":[36],"uses":[37],"objects":[38],"detected":[39],"from":[40],"the":[41,58,71,80,98,107,126,142,164,173,180,191,210,227,258,264,278],"image,":[43,81],"so-called":[44],"object":[45,65,74,241],"tags,":[46],"anchor":[48,141],"points":[49],"ease":[51],"alignment":[52],"between":[53],"attention":[59],"mechanism.":[60],"However,":[61],"they":[62],"only":[63],"consider":[64],"information":[66],"images,":[68],"while":[69],"neglecting":[70],"actions":[72,84,105,116,162,193],"interactions":[75],"that":[76,121,179,209,239],"also":[77],"appear":[78],"causes":[83],"not":[85],"caught":[86],"properly":[87],"captioning.":[90],"To":[91],"tackle":[92],"this":[93],"previously":[94],"underrepresented":[95],"dimension":[96],"of":[97,104,125,135,229,240],"semantic":[99,108],"alignment,":[100],"we":[101,146,167],"take":[102],"account":[103],"on":[106,114,203],"level.":[109],"Specifically,":[110],"our":[111],"work":[112],"focuses":[113],"human":[115],"interactions,":[118],"ensures":[120],"more":[122,233,244],"salient":[123,192],"parts":[124],"get":[128],"captioned.":[129],"We":[130],"introduce":[131],"new":[133],"type":[134],"tag,":[136,139],"called":[137],"action":[138,143,153,157,170,182,187,222,230],"information.":[144],"First,":[145],"provide":[147],"method":[149],"obtaining":[151],"such":[152],"tags":[154,171,183,223,231,242],"using":[155,221],"an":[156],"detection":[158],"model":[159,212],"predicts":[161],"image.":[165],"Next,":[166],"leverage":[168],"these":[169],"into":[172],"model.":[175],"Experimental":[176,201],"results":[177,202],"indicate":[178],"proposed":[181,211],"can":[184],"help":[185],"learn":[186],"semantics":[188],"catch":[190],"leading":[194],"perceived":[196],"improvements":[197],"common":[199],"performance.":[200],"MS-COCO":[204],"Karpathy":[205],"test":[206],"split":[207],"show":[208],"achieves":[213],"good":[214],"scores":[215],"BLEU-4":[217],"CIDEr":[219],"metrics,":[220],"anchors.":[225],"Furthermore,":[226],"number":[228],"(no":[232],"than":[234,238,245],"5)":[235],"smaller":[237],"(commonly":[243],"20),":[246],"means":[248],"there":[249],"potential":[252,265],"reduce":[254],"FLOPs":[255],"by":[256],"reducing":[257],"total":[259],"sequence":[260],"length.":[261],"It":[262],"indicates":[263],"efficient":[267],"reasoning":[268],"may":[270],"be":[271],"applied":[272],"daily":[274],"activity":[275],"scenes":[276],"future.":[279]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-10T00:00:00"}