{"id":"https://openalex.org/W4388622909","doi":"https://doi.org/10.1109/access.2023.3332098","title":"An Approach to Generate a Caption for an Image Collection Using Scene Graph Generation","display_name":"An Approach to Generate a Caption for an Image Collection Using Scene Graph Generation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388622909","doi":"https://doi.org/10.1109/access.2023.3332098"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3332098","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3332098","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10315005.pdf","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":null,"license_id":null,"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://ieeexplore.ieee.org/ielx7/6287639/6514899/10315005.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031050400","display_name":"Itthisak Phueaksri","orcid":"https://orcid.org/0000-0002-1295-777X"},"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":"Itthisak Phueaksri","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Seika, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1295-777X","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Seika, Kyoto, Japan","institution_ids":[]}]},{"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/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc A. Kastner","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto-shi, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9193-5973","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto-shi, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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":["Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Seika, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3799-4550","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Seika, Kyoto, Japan","institution_ids":[]}]},{"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":["Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","Mathematical and Data Science Center, Nagoya University, Nagoya, Aichi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3041-4330","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Mathematical and Data Science Center, Nagoya University, 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":["Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3942-9296","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.8562,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8667041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"128245","last_page":"128260"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.7677782773971558},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5753825306892395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5467109680175781},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45914292335510254},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.35758131742477417},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.17109879851341248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677782773971558},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5753825306892395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5467109680175781},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45914292335510254},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35758131742477417},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.17109879851341248}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3332098","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3332098","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10315005.pdf","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ef20140078c342c5b406df8b7eca12e7","is_oa":true,"landing_page_url":"https://doaj.org/article/ef20140078c342c5b406df8b7eca12e7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 128245-128260 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3332098","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3332098","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10315005.pdf","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3578610760","display_name":"Toward describing fine-grained details in computer vision through visual discrimination learning","funder_award_id":"23K16945","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3982318327","display_name":null,"funder_award_id":"JP23K16945","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5266459512","display_name":null,"funder_award_id":"JP21H03519","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G622071442","display_name":null,"funder_award_id":"JP23K16945","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G8428565986","display_name":null,"funder_award_id":"JP21H03519","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G8618070128","display_name":"Analysis of the visual characteristics of language information and its application to multimedia integrated processing","funder_award_id":"23K24868","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G908983284","display_name":"A Framework for Understanding and Describing Scenes with Unknown Objects Based on Extended Spatio-Temporal Scene Graphs","funder_award_id":"23K21708","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320337013","display_name":"Information Technology Center, Nagoya University","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388622909.pdf","grobid_xml":"https://content.openalex.org/works/W4388622909.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W950821216","https://openalex.org/W1826672328","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2077069816","https://openalex.org/W2099970772","https://openalex.org/W2101105183","https://openalex.org/W2143017621","https://openalex.org/W2143668817","https://openalex.org/W2153624566","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2255466643","https://openalex.org/W2277195237","https://openalex.org/W2519718368","https://openalex.org/W2530979053","https://openalex.org/W2549139847","https://openalex.org/W2561529111","https://openalex.org/W2565639579","https://openalex.org/W2745461083","https://openalex.org/W2797184725","https://openalex.org/W2889518897","https://openalex.org/W2904790185","https://openalex.org/W2963187786","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963829244","https://openalex.org/W2970785793","https://openalex.org/W3003908908","https://openalex.org/W3035017890","https://openalex.org/W3035628162","https://openalex.org/W3036869132","https://openalex.org/W3038038411","https://openalex.org/W3097754216","https://openalex.org/W3107848485","https://openalex.org/W3162397205","https://openalex.org/W3170092793","https://openalex.org/W3173220247","https://openalex.org/W3173360659","https://openalex.org/W3183139384","https://openalex.org/W3186478344","https://openalex.org/W4214617019","https://openalex.org/W4287757444","https://openalex.org/W4288089799","https://openalex.org/W4292945941","https://openalex.org/W4312240915","https://openalex.org/W4318718936","https://openalex.org/W4361757055","https://openalex.org/W4366352717","https://openalex.org/W4385574358","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6682631176","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6761205521","https://openalex.org/W6769627184","https://openalex.org/W6771915120","https://openalex.org/W6779787121","https://openalex.org/W6783483657","https://openalex.org/W6785349798","https://openalex.org/W6798046381","https://openalex.org/W6842542540","https://openalex.org/W6849177959"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Summarization":[0],"is":[1,23,175],"a":[2,9,16,24,33,45,49,61,72,83,88,108,120,146,178,185,209],"challenging":[3],"task":[4,26,213],"that":[5],"aims":[6,42],"to":[7,43,59,118,187,240],"generate":[8,71,119],"summary":[10,35,47],"by":[11,162,214],"grasping":[12],"common":[13,133,166,196],"information":[14],"of":[15,19,27,36,48,51,76,91,160,218,229],"given":[17],"set":[18],"information.":[20],"Text":[21],"summarization":[22,41],"popular":[25],"determining":[28],"the":[29,115,164,171,192,204,216,219,230],"topic":[30],"or":[31],"generating":[32,60,87],"textual":[34,74],"documents.":[37],"In":[38,181],"contrast,":[39],"image":[40,78,93,125,128,224],"find":[44,132],"representative":[46],"collection":[50],"images.":[52],"However,":[53],"current":[54],"methods":[55],"are":[56],"still":[57],"restricted":[58],"visual":[62],"scene":[63,96,121,140,148,155,173],"graph,":[64],"tags,":[65],"and":[66,104,135,142,157,168],"noun":[67],"phrases,":[68],"but":[69],"cannot":[70],"fitting":[73],"description":[75],"an":[77,92,127,223],"collection.":[79,94,129],"Thus,":[80],"we":[81,111,131,152,183,207],"introduce":[82,184],"novel":[84],"framework":[85],"for":[86,123,211],"summarized":[89,147,172],"caption":[90,194],"Since":[95],"graph":[97,122,174],"generation":[98],"shows":[99],"advancement":[100],"in":[101,114,126,191],"describing":[102],"objects":[103,134,167],"their":[105,136],"relationships":[106,137],"on":[107,233],"single":[109],"image,":[110],"use":[112],"it":[113,161],"proposed":[116,205,231],"method":[117,232],"each":[124],"Then,":[130],"from":[138],"all":[139,154],"graphs":[141,156],"represent":[143],"them":[144],"as":[145],"graph.":[149],"For":[150],"this,":[151],"merge":[153],"select":[158],"part":[159],"estimating":[163],"most":[165],"relationships.":[169],"Finally,":[170],"input":[176],"into":[177,195],"captioning":[179],"model.":[180],"addition,":[182],"technique":[186],"generalize":[188],"specific":[189],"words":[190,198],"final":[193],"concept":[197],"incorporating":[199],"external":[200],"knowledge.":[201],"To":[202],"evaluate":[203],"method,":[206],"construct":[208],"dataset":[210,221,235],"this":[212,234],"extending":[215],"annotation":[217],"MS-COCO":[220],"using":[222],"retrieval":[225],"method.":[226],"The":[227],"evaluation":[228],"showed":[236],"promising":[237],"performance":[238],"compared":[239],"text":[241],"summarization-based":[242],"methods.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}