{"id":"https://openalex.org/W3145501194","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382725","title":"Potential of Incorporating Motion Estimation for Image Captioning","display_name":"Potential of Incorporating Motion Estimation for Image Captioning","publication_year":2021,"publication_date":"2021-01-11","ids":{"openalex":"https://openalex.org/W3145501194","doi":"https://doi.org/10.1109/ieeeconf49454.2021.9382725","mag":"3145501194"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf49454.2021.9382725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"},"type":"article","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/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, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, Tokyo, 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, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, Tokyo, 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alessandro Moro","raw_affiliation_strings":["RITECS Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"RITECS Inc., Tokyo, 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, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, Tokyo, 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, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083707250"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.2882,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53393791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"28"},"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":0.9980000257492065,"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":0.9965000152587891,"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":0.9903724193572998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8318845629692078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.8006879091262817},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.7023352384567261},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6528556942939758},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5979295969009399},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5923214554786682},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4901503026485443},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.484829306602478},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46988537907600403},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46383628249168396},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3246457278728485}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9903724193572998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318845629692078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8006879091262817},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.7023352384567261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6528556942939758},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5979295969009399},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5923214554786682},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4901503026485443},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.484829306602478},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46988537907600403},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46383628249168396},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3246457278728485}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf49454.2021.9382725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf49454.2021.9382725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2082512208","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2118895150","https://openalex.org/W2133459682","https://openalex.org/W2194775991","https://openalex.org/W2339652278","https://openalex.org/W2425121537","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2964297311","https://openalex.org/W3007471652","https://openalex.org/W6630875275","https://openalex.org/W6760638481","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/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Automatic":[0],"image":[1,35,78,87],"captioning":[2,79],"has":[3],"various":[4],"important":[5,128],"applications":[6],"such":[7],"as":[8],"indexing":[9],"images":[10,61],"on":[11,46,97,117],"the":[12,15,21,38,122],"Web":[13],"or":[14],"depiction":[16],"of":[17,124],"visual":[18,47,58],"contents":[19],"for":[20,34],"visually":[22],"impaired.":[23],"Recently,":[24],"deep":[25,40,76],"learning":[26,41,77],"based":[27],"probabilistic":[28],"frameworks":[29],"have":[30,50],"been":[31],"greatly":[32],"researched":[33],"captioning.":[36],"However":[37],"existing":[39],"methods":[42],"are":[43],"only":[44],"established":[45],"features,":[48],"which":[49],"problems":[51],"generating":[52],"captions":[53],"related":[54],"to":[55,88,129],"motions,":[56],"because":[57],"features":[59,84,114,126],"from":[60,85],"do":[62],"not":[63],"include":[64],"motion":[65,83,113,125],"features.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"propose":[71],"a":[72,86],"novel,":[73],"end-to-end":[74],"trainable,":[75],"model":[80,94],"that":[81,108,121],"estimates":[82],"help":[89],"generate":[90,130],"captions.":[91,131],"Our":[92],"proposed":[93,110],"was":[95],"evaluated":[96],"two":[98],"datasets,":[99],"MSR-VTT2016-Image,":[100],"and":[101,120],"several":[102],"copyright":[103],"free":[104],"images.":[105],"We":[106],"demonstrate":[107],"our":[109],"method":[111],"using":[112],"improves":[115],"performance":[116],"caption":[118],"generation":[119],"quality":[123],"is":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}