{"id":"https://openalex.org/W4307989627","doi":"https://doi.org/10.3390/s22218376","title":"Caps Captioning: A Modern Image Captioning Approach Based on Improved Capsule Network","display_name":"Caps Captioning: A Modern Image Captioning Approach Based on Improved Capsule Network","publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W4307989627","doi":"https://doi.org/10.3390/s22218376","pmid":"https://pubmed.ncbi.nlm.nih.gov/36366079"},"language":"en","primary_location":{"id":"doi:10.3390/s22218376","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22218376","pdf_url":"https://www.mdpi.com/1424-8220/22/21/8376/pdf?version=1675669327","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/21/8376/pdf?version=1675669327","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072535862","display_name":"Shima Javanmardi","orcid":"https://orcid.org/0000-0002-3027-5895"},"institutions":[{"id":"https://openalex.org/I112536369","display_name":"Yazd University","ror":"https://ror.org/02x99ac45","country_code":"IR","type":"education","lineage":["https://openalex.org/I112536369"]},{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["IR","NL"],"is_corresponding":false,"raw_author_name":"Shima Javanmardi","raw_affiliation_strings":["Computer Engineering Department, Yazd University, Yazd P.O. Box 8915818411, Iran","Section Imaging and Bioinformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Yazd University, Yazd P.O. Box 8915818411, Iran","institution_ids":["https://openalex.org/I112536369"]},{"raw_affiliation_string":"Section Imaging and Bioinformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033951266","display_name":"Alimohammad Latif","orcid":"https://orcid.org/0000-0002-0697-4952"},"institutions":[{"id":"https://openalex.org/I112536369","display_name":"Yazd University","ror":"https://ror.org/02x99ac45","country_code":"IR","type":"education","lineage":["https://openalex.org/I112536369"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Ali Latif","raw_affiliation_strings":["Computer Engineering Department, Yazd University, Yazd P.O. Box 8915818411, Iran"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Yazd University, Yazd P.O. Box 8915818411, Iran","institution_ids":["https://openalex.org/I112536369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103030199","display_name":"Mohammad Taghi Sadeghi","orcid":"https://orcid.org/0000-0001-9106-3346"},"institutions":[{"id":"https://openalex.org/I112536369","display_name":"Yazd University","ror":"https://ror.org/02x99ac45","country_code":"IR","type":"education","lineage":["https://openalex.org/I112536369"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad Sadeghi","raw_affiliation_strings":["Electrical Engineering Department, Yazd University, Yazd P.O. Box 89195741, Iran"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Yazd University, Yazd P.O. Box 89195741, Iran","institution_ids":["https://openalex.org/I112536369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086087986","display_name":"Mehrdad Jahanbanifard","orcid":"https://orcid.org/0000-0002-2224-8387"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mehrdad Jahanbanifard","raw_affiliation_strings":["Section Imaging and Bioinformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Section Imaging and Bioinformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062502864","display_name":"Marcello Bonsangue","orcid":"https://orcid.org/0000-0003-3746-3618"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marcello Bonsangue","raw_affiliation_strings":["Section Imaging and Bioinformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Section Imaging and Bioinformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022631255","display_name":"Fons J. Verbeek","orcid":"https://orcid.org/0000-0003-2445-8158"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Fons Verbeek","raw_affiliation_strings":["Section Imaging and Bioinformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Section Imaging and Bioinformatics, Leiden Institute of Advanced Computer Science (LIACS), Leiden University, Niels Bohrweg 1, 2333 CA Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5022631255","https://openalex.org/A5033951266"],"corresponding_institution_ids":["https://openalex.org/I112536369","https://openalex.org/I121797337"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.9177,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75557471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"22","issue":"21","first_page":"8376","last_page":"8376"},"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":0.9954000115394592,"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":0.9797999858856201,"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":0.9463323950767517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8025461435317993},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6704555153846741},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6648433804512024},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6201254725456238},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6170617938041687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.596426248550415},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5579840540885925},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4994161128997803},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4847564399242401},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4693760871887207},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41835319995880127},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3496331572532654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32566359639167786},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3220733404159546}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9463323950767517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025461435317993},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6704555153846741},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6648433804512024},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6201254725456238},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6170617938041687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.596426248550415},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5579840540885925},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4994161128997803},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4847564399242401},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4693760871887207},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41835319995880127},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3496331572532654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32566359639167786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3220733404159546},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":7,"locations":[{"id":"doi:10.3390/s22218376","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22218376","pdf_url":"https://www.mdpi.com/1424-8220/22/21/8376/pdf?version=1675669327","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:36366079","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36366079","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:012a63752c664c05a17e04634ec68002","is_oa":true,"landing_page_url":"https://doaj.org/article/012a63752c664c05a17e04634ec68002","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":"Sensors, Vol 22, Iss 21, p 8376 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/21/8376/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22218376","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9654532","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9654532","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3486354","is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/3486354","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors","raw_type":"Article / Letter to editor"},{"id":"pmh:ul:oai:scholarlypublications.universiteitleiden.nl:item_3486354","is_oa":true,"landing_page_url":"http://hdl.handle.net/1887/3486354","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, 22(21):8376","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.3390/s22218376","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22218376","pdf_url":"https://www.mdpi.com/1424-8220/22/21/8376/pdf?version=1675669327","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4307989627.pdf","grobid_xml":"https://content.openalex.org/works/W4307989627.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1687846465","https://openalex.org/W1828348983","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1969616664","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2109586012","https://openalex.org/W2123301721","https://openalex.org/W2131179926","https://openalex.org/W2144715671","https://openalex.org/W2185175083","https://openalex.org/W2296385829","https://openalex.org/W2302086703","https://openalex.org/W2481240925","https://openalex.org/W2560920409","https://openalex.org/W2564898401","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2767780846","https://openalex.org/W2789876780","https://openalex.org/W2803259101","https://openalex.org/W2885013662","https://openalex.org/W2896348597","https://openalex.org/W2954841306","https://openalex.org/W2963084599","https://openalex.org/W2963093799","https://openalex.org/W2963686907","https://openalex.org/W2963758027","https://openalex.org/W2976711440","https://openalex.org/W2977928982","https://openalex.org/W2979739834","https://openalex.org/W2981165461","https://openalex.org/W2982693492","https://openalex.org/W2996202528","https://openalex.org/W3012183480","https://openalex.org/W3014001464","https://openalex.org/W3038377241","https://openalex.org/W3152080878","https://openalex.org/W3158091094","https://openalex.org/W3179017304","https://openalex.org/W4212979146","https://openalex.org/W4225288434","https://openalex.org/W4295220592","https://openalex.org/W6638549007","https://openalex.org/W6676497082","https://openalex.org/W6685230081","https://openalex.org/W6743446608","https://openalex.org/W6745827836","https://openalex.org/W6748053814","https://openalex.org/W6768465552"],"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/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2810679507"],"abstract_inverted_index":{"In":[0,182],"image":[1,10,231],"captioning":[2,232],"models,":[3],"the":[4,14,19,22,29,53,55,72,98,111,133,144,165,188,208,211,221,236,240],"main":[5,151],"challenge":[6],"in":[7,95,101],"describing":[8,235],"an":[9,39,148],"is":[11,68,85,156],"identifying":[12],"all":[13],"objects":[15,23],"by":[16,110,179,206],"precisely":[17],"considering":[18,207],"relationships":[20],"between":[21],"and":[24,49,62,92,197],"producing":[25],"various":[26],"captions.":[27],"Over":[28],"past":[30],"few":[31],"years,":[32],"many":[33],"methods":[34],"have":[35],"been":[36],"proposed,":[37],"from":[38,59],"attribute-to-attribute":[40],"comparison":[41],"approach":[42],"to":[43,47,89,106],"handling":[44],"issues":[45],"related":[46],"semantics":[48],"their":[50,216],"relationships.":[51,217],"Despite":[52],"improvements,":[54],"existing":[56],"techniques":[57],"suffer":[58],"inadequate":[60],"positional":[61],"geometrical":[63,198],"attributes":[64,199],"concepts.":[65],"The":[66,150],"reason":[67],"that":[69,131,161,226],"most":[70],"of":[71,135,141,143,147,153,167,177,190,204,210,239],"abovementioned":[73],"approaches":[74],"depend":[75],"on":[76,126,187,220],"Convolutional":[77],"Neural":[78],"Networks":[79],"(CNNs)":[80],"for":[81,87,121,200],"object":[82],"detection.":[83],"CNN":[84],"notorious":[86],"failing":[88],"detect":[90],"equivariance":[91],"rotational":[93],"invariance":[94],"objects.":[96],"Moreover,":[97],"pooling":[99],"layers":[100],"CNNs":[102,168],"cause":[103],"valuable":[104],"information":[105],"be":[107],"lost.":[108],"Inspired":[109],"recent":[112],"successful":[113],"approaches,":[114],"this":[115,154],"paper":[116,155],"introduces":[117],"a":[118,127,138,158,174,201],"novel":[119],"framework":[120,228],"extracting":[122],"meaningful":[123,191],"descriptions":[124,172,192],"based":[125],"parallelized":[128],"capsule":[129],"network":[130],"describes":[132],"content":[134,238],"images":[136,205],"through":[137],"high":[139],"level":[140],"understanding":[142],"semantic":[145,237],"contents":[146],"image.":[149],"contribution":[152],"proposing":[157],"new":[159],"method":[160],"not":[162],"only":[163],"overrides":[164],"limitations":[166],"but":[169],"also":[170],"generates":[171],"with":[173,193],"wide":[175],"variety":[176],"words":[178],"using":[180],"Wikipedia.":[181],"our":[183,227],"framework,":[184],"capsules":[185],"focus":[186],"generation":[189],"more":[194],"detailed":[195],"spatial":[196],"given":[202],"set":[203],"position":[209],"entities":[212],"as":[213,215],"well":[214],"Qualitative":[218],"experiments":[219],"benchmark":[222],"dataset":[223],"MS-COCO":[224],"show":[225],"outperforms":[229],"state-of-the-art":[230],"models":[233],"when":[234],"images.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}