{"id":"https://openalex.org/W3127801554","doi":"https://doi.org/10.3390/s21041270","title":"Image Captioning Using Motion-CNN with Object Detection","display_name":"Image Captioning Using Motion-CNN with Object Detection","publication_year":2021,"publication_date":"2021-02-10","ids":{"openalex":"https://openalex.org/W3127801554","doi":"https://doi.org/10.3390/s21041270","mag":"3127801554","pmid":"https://pubmed.ncbi.nlm.nih.gov/33578956"},"language":"en","primary_location":{"id":"doi:10.3390/s21041270","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21041270","pdf_url":"https://www.mdpi.com/1424-8220/21/4/1270/pdf?version=1612967510","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/1424-8220/21/4/1270/pdf?version=1612967510","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083707250","display_name":"Kiyohiko Iwamura","orcid":"https://orcid.org/0000-0001-9088-2534"},"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":true,"raw_author_name":"Kiyohiko Iwamura","raw_affiliation_strings":["Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9088-2534","affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051800939","display_name":"Jun Younes Louhi Kasahara","orcid":"https://orcid.org/0000-0002-5924-8858"},"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":"Jun Younes Louhi Kasahara","raw_affiliation_strings":["Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5924-8858","affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103157205","display_name":"Alessandro Moro","orcid":"https://orcid.org/0000-0001-8711-0330"},"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":"Alessandro Moro","raw_affiliation_strings":["Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","RITECS Inc., 3-5-11-403, Shibasakityo, Tatekawa-shi, Tokyo 190-0023, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"RITECS Inc., 3-5-11-403, Shibasakityo, Tatekawa-shi, Tokyo 190-0023, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021260328","display_name":"Atsushi Yamashita","orcid":"https://orcid.org/0000-0003-1280-069X"},"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":"Atsushi Yamashita","raw_affiliation_strings":["Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1280-069X","affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064103302","display_name":"Hajime Asama","orcid":"https://orcid.org/0000-0002-9482-497X"},"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":"Hajime Asama","raw_affiliation_strings":["Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9482-497X","affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, 7-3-1, Hongo, Bunkyo-ku, Tokyo 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083707250"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":1.6959,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.85968553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"21","issue":"4","first_page":"1270","last_page":"1270"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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":0.9977999925613403,"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":0.9871337413787842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115665316581726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7719308137893677},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.7311804294586182},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6355820894241333},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5830433964729309},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5808276534080505},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45265454053878784},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43849658966064453}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9871337413787842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115665316581726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7719308137893677},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7311804294586182},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6355820894241333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5830433964729309},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5808276534080505},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45265454053878784},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43849658966064453},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009038","descriptor_name":"Motion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009038","descriptor_name":"Motion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009038","descriptor_name":"Motion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014786","descriptor_name":"Vision Disorders","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014786","descriptor_name":"Vision Disorders","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014786","descriptor_name":"Vision Disorders","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s21041270","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21041270","pdf_url":"https://www.mdpi.com/1424-8220/21/4/1270/pdf?version=1612967510","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:33578956","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33578956","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:86b6fef88ab24279a59c759a9675993a","is_oa":true,"landing_page_url":"https://doaj.org/article/86b6fef88ab24279a59c759a9675993a","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":"Sensors, Vol 21, Iss 4, p 1270 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/21/4/1270/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s21041270","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; Volume 21; Issue 4; Pages: 1270","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7916682","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7916682","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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"}],"best_oa_location":{"id":"doi:10.3390/s21041270","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21041270","pdf_url":"https://www.mdpi.com/1424-8220/21/4/1270/pdf?version=1612967510","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3127801554.pdf","grobid_xml":"https://content.openalex.org/works/W3127801554.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2082512208","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2133459682","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2339652278","https://openalex.org/W2425121537","https://openalex.org/W2575842049","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2951763382","https://openalex.org/W2952122856","https://openalex.org/W2963758027","https://openalex.org/W2964297311","https://openalex.org/W3007471652","https://openalex.org/W3145501194"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W3217388757","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W3161816943"],"abstract_inverted_index":{"Automatic":[0],"image":[1,29,44,53,78,138],"captioning":[2,30,101,108],"has":[3],"many":[4],"important":[5],"applications,":[6],"such":[7,62],"as":[8,63],"the":[9,19,24,41,50,71,87,100,107,123,126,143],"depiction":[10],"of":[11,21,73,122,146],"visual":[12],"contents":[13],"for":[14,59,80,119,125,137],"visually":[15],"impaired":[16],"people":[17],"or":[18],"indexing":[20],"images":[22],"on":[23],"internet.":[25],"Recently,":[26],"deep":[27],"learning-based":[28],"models":[31],"have":[32],"been":[33],"researched":[34],"extensively.":[35],"For":[36],"caption":[37,139,147,170],"generation,":[38],"they":[39],"learn":[40],"relation":[42],"between":[43],"features":[45,54,75,79,89,96,105,118],"and":[46,159],"words":[47,61],"included":[48,70],"in":[49,128],"captions.":[51],"However,":[52,85],"might":[55],"not":[56,93],"be":[57],"relevant":[58],"certain":[60],"verbs.":[64,84],"Therefore,":[65],"our":[66,166],"earlier":[67],"reported":[68],"method":[69,136,168],"use":[72,114],"motion":[74,88,95,104,117],"along":[76],"with":[77,116],"generating":[81],"captions":[82],"including":[83],"all":[86,94],"were":[90],"used.":[91],"Since":[92],"contributed":[97],"positively":[98],"to":[99],"process,":[102],"unnecessary":[103],"decreased":[106,144],"accuracy.":[109,129],"As":[110],"described":[111],"herein,":[112],"we":[113],"experiments":[115],"thorough":[120],"analysis":[121],"reasons":[124],"decline":[127],"We":[130],"propose":[131],"a":[132],"novel,":[133],"end-to-end":[134],"trainable":[135],"generation":[140,171],"that":[141,165],"alleviates":[142],"accuracy":[145],"generation.":[148],"Our":[149],"proposed":[150,167],"model":[151],"was":[152],"evaluated":[153],"using":[154],"three":[155],"datasets:":[156],"MSR-VTT2016-Image,":[157],"MSCOCO,":[158],"several":[160],"copyright-free":[161],"images.":[162],"Results":[163],"demonstrate":[164],"improves":[169],"performance.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
