{"id":"https://openalex.org/W3217412301","doi":"https://doi.org/10.1007/s12369-021-00842-1","title":"Video Captioning Based on Both Egocentric and Exocentric Views of Robot Vision for Human-Robot Interaction","display_name":"Video Captioning Based on Both Egocentric and Exocentric Views of Robot Vision for Human-Robot Interaction","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W3217412301","doi":"https://doi.org/10.1007/s12369-021-00842-1","mag":"3217412301"},"language":"en","primary_location":{"id":"doi:10.1007/s12369-021-00842-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12369-021-00842-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12369-021-00842-1.pdf","source":{"id":"https://openalex.org/S168738021","display_name":"International Journal of Social Robotics","issn_l":"1875-4791","issn":["1875-4791","1875-4805"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Social Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12369-021-00842-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053110962","display_name":"Soo-Han Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Soo-Han Kang","raw_affiliation_strings":["Seoul National University of Science and Technology, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology, Seoul, South Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062826616","display_name":"Ji-Hyeong Han","orcid":"https://orcid.org/0000-0001-8391-6898"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji-Hyeong Han","raw_affiliation_strings":["Seoul National University of Science and Technology, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology, Seoul, South Korea","institution_ids":["https://openalex.org/I118373667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053110962"],"corresponding_institution_ids":["https://openalex.org/I118373667"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":1.1622,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.81137186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"15","issue":"4","first_page":"631","last_page":"641"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9997000098228455,"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":0.9980999827384949,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7466738224029541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7121502757072449},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.673931896686554},{"id":"https://openalex.org/keywords/endocentric-and-exocentric","display_name":"Endocentric and exocentric","score":0.6247676014900208},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5803211331367493},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5686464905738831},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.491745263338089},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4378894567489624},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.42091104388237},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4206291139125824},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4129073917865753},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.27955567836761475},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.26080864667892456},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07587233185768127}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7466738224029541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121502757072449},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.673931896686554},{"id":"https://openalex.org/C131042201","wikidata":"https://www.wikidata.org/wiki/Q493198","display_name":"Endocentric and exocentric","level":4,"score":0.6247676014900208},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5803211331367493},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5686464905738831},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.491745263338089},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4378894567489624},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.42091104388237},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4206291139125824},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4129073917865753},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.27955567836761475},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.26080864667892456},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07587233185768127},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s12369-021-00842-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12369-021-00842-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12369-021-00842-1.pdf","source":{"id":"https://openalex.org/S168738021","display_name":"International Journal of Social Robotics","issn_l":"1875-4791","issn":["1875-4791","1875-4805"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Social Robotics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s12369-021-00842-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12369-021-00842-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12369-021-00842-1.pdf","source":{"id":"https://openalex.org/S168738021","display_name":"International Journal of Social Robotics","issn_l":"1875-4791","issn":["1875-4791","1875-4805"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Social Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G112893163","display_name":null,"funder_award_id":"2018R1C1B6007230","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3034753964","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5099067714","display_name":null,"funder_award_id":"No. 2018R1C1B6007230","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G626505518","display_name":null,"funder_award_id":"No. 201","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8713825000","display_name":null,"funder_award_id":"2018R1C1B6007230","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3217412301.pdf","grobid_xml":"https://content.openalex.org/works/W3217412301.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W105287674","https://openalex.org/W1483019628","https://openalex.org/W1519475388","https://openalex.org/W1637016997","https://openalex.org/W1947050545","https://openalex.org/W1999547171","https://openalex.org/W2031688197","https://openalex.org/W2038485832","https://openalex.org/W2101105183","https://openalex.org/W2106229755","https://openalex.org/W2120645068","https://openalex.org/W2139501017","https://openalex.org/W2167626157","https://openalex.org/W2212494831","https://openalex.org/W2396108084","https://openalex.org/W2430164002","https://openalex.org/W2519434724","https://openalex.org/W2739107216","https://openalex.org/W2740388348","https://openalex.org/W2783838156","https://openalex.org/W2803620531","https://openalex.org/W2803638078","https://openalex.org/W2887712318","https://openalex.org/W2904698318","https://openalex.org/W2921112876","https://openalex.org/W2921488949","https://openalex.org/W2941651142","https://openalex.org/W2962681491","https://openalex.org/W2963155035","https://openalex.org/W2963381281","https://openalex.org/W2963860638","https://openalex.org/W2964137974","https://openalex.org/W2964242760","https://openalex.org/W2971645868","https://openalex.org/W2990152177","https://openalex.org/W3009192917","https://openalex.org/W3109667662"],"related_works":["https://openalex.org/W3009270862","https://openalex.org/W2955859849","https://openalex.org/W2160434794","https://openalex.org/W3181705171","https://openalex.org/W2963761716","https://openalex.org/W3005142023","https://openalex.org/W2166267632","https://openalex.org/W2049851324","https://openalex.org/W4250841346","https://openalex.org/W2344425795"],"abstract_inverted_index":{"Abstract":[0],"Robot":[1],"vision":[2,66,83,183],"provides":[3],"the":[4,15,28,36,41,89,112,148,170,174],"most":[5],"important":[6],"information":[7,98],"to":[8,24,43,63,74,85,110,131,167],"robots":[9],"so":[10],"that":[11],"they":[12],"can":[13,179],"read":[14],"context":[16],"and":[17,71,115,125,135,151,173],"interact":[18],"with":[19],"human":[20],"partners":[21],"successfully.":[22],"Moreover,":[23],"allow":[25],"humans":[26],"recognize":[27],"robot\u2019s":[29,90],"visual":[30],"understanding":[31,49],"during":[32],"human-robot":[33],"interaction":[34,116],"(HRI),":[35],"best":[37],"way":[38],"is":[39,144,158],"for":[40,79],"robot":[42,65,82,182],"provide":[44],"an":[45,68],"explanation":[46],"of":[47,121],"its":[48,152],"in":[50,128,164],"natural":[51,129],"language.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,104],"propose":[57,105],"a":[58,106,181],"new":[59,107],"approach":[60],"by":[61],"which":[62,119],"interpret":[64],"from":[67],"egocentric":[69,76,86,96,122,134],"standpoint":[70],"generate":[72],"descriptions":[73,127],"explain":[75],"videos":[77],"particularly":[78],"HRI.":[80],"Because":[81],"equals":[84],"video":[87,123],"on":[88,147,154],"side,":[91],"it":[92],"contains":[93],"as":[94,99,111],"much":[95],"view":[97,101],"exocentric":[100,136],"information.":[102,137],"Thus,":[103],"dataset,":[108,118],"referred":[109],"global,":[113],"action,":[114],"(GAI)":[117],"consists":[120],"clips":[124],"GAI":[126,149,171],"language":[130],"represent":[132],"both":[133],"The":[138],"encoder-decoder":[139],"based":[140,146],"deep":[141,176],"learning":[142,177],"model":[143,178],"trained":[145,175],"dataset":[150,172],"performance":[153],"description":[155],"generation":[156],"assessments":[157],"evaluated.":[159],"We":[160],"also":[161],"conduct":[162],"experiments":[163],"actual":[165],"environments":[166],"verify":[168],"whether":[169],"improve":[180],"system":[184]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}