{"id":"https://openalex.org/W2964616647","doi":"https://doi.org/10.1109/icphys.2019.8780171","title":"Visual Image Caption Generation for Service Robotics and Industrial Applications","display_name":"Visual Image Caption Generation for Service Robotics and Industrial Applications","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2964616647","doi":"https://doi.org/10.1109/icphys.2019.8780171","mag":"2964616647"},"language":"en","primary_location":{"id":"doi:10.1109/icphys.2019.8780171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icphys.2019.8780171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Industrial Cyber Physical Systems (ICPS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113503581","display_name":"Ren C. Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ren C. Luo","raw_affiliation_strings":["International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA), National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA), National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101856879","display_name":"Yu\u2010Ting Hsu","orcid":"https://orcid.org/0000-0001-7467-0101"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ting Hsu","raw_affiliation_strings":["International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA), National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA), National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064321219","display_name":"Yu-Cheng Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Cheng Wen","raw_affiliation_strings":["International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA), National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA), National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079123127","display_name":"Huan-Jun Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huan-Jun Ye","raw_affiliation_strings":["International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA), National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Center of Excellence in Intelligent Robotics and Automation Research (NTU-iCeiRA), National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"827","last_page":"832"},"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":0.9937000274658203,"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":0.9896000027656555,"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":0.9347618818283081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8361778259277344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7545919418334961},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6902233362197876},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5965483784675598},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.5492002964019775},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5436917543411255},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46939295530319214},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4627741575241089},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.447252094745636},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4471896290779114},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4311203360557556},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3783215880393982},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0921562910079956}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9347618818283081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8361778259277344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7545919418334961},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6902233362197876},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5965483784675598},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.5492002964019775},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5436917543411255},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46939295530319214},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4627741575241089},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.447252094745636},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4471896290779114},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4311203360557556},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3783215880393982},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0921562910079956},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icphys.2019.8780171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icphys.2019.8780171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Industrial Cyber Physical Systems (ICPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W8316075","https://openalex.org/W68733909","https://openalex.org/W956551720","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1949478088","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W1973321600","https://openalex.org/W2101105183","https://openalex.org/W2102605133","https://openalex.org/W2112912048","https://openalex.org/W2118542129","https://openalex.org/W2123024445","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2143449221","https://openalex.org/W2163922914","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2560920409","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2901749036","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W2982553922","https://openalex.org/W6625044600","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6639657675","https://openalex.org/W6675026286","https://openalex.org/W6676647902","https://openalex.org/W6678470764","https://openalex.org/W6679434410","https://openalex.org/W6681184217","https://openalex.org/W6725318829","https://openalex.org/W6742999658","https://openalex.org/W6756309682","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Image":[0],"caption":[1,62,96,106,112],"generation":[2,107],"is":[3,15,33],"a":[4,8,11,77,101],"task":[5,32],"that":[6,21,110,132],"generates":[7],"sentence":[9],"from":[10,25],"raw":[12],"image,":[13],"which":[14],"mimicking":[16],"the":[17,26,34,61,69,72,83,90,94,111,115,123,137],"intelligence":[18],"of":[19,30,36,42,68,85,93,104],"human":[20],"can":[22,118],"acquire":[23],"knowledge":[24,38],"view.":[27],"The":[28],"difficulty":[29],"this":[31],"combination":[35],"multimodal":[37],"learning,":[39],"i.e.":[40],"recognition":[41,67,87],"objects,":[43],"actions,":[44],"scenes,":[45],"human,":[46],"etc.":[47],"In":[48],"order":[49],"to":[50,121],"perform":[51],"semantic":[52],"understanding":[53],"for":[54,66,81],"service":[55],"robotics":[56],"or":[57],"other":[58,91],"industrial":[59],"applications,":[60],"must":[63],"be":[64,119],"enhanced":[65],"objects":[70],"in":[71,129,140],"confined":[73],"environment.":[74],"We":[75,127],"propose":[76],"template-based":[78],"augmentation":[79],"method":[80],"improving":[82],"capability":[84,92],"object":[86],"while":[88],"retaining":[89],"image":[95,105],"model.":[97,126],"This":[98],"work":[99],"opens":[100],"new":[102],"era":[103],"training":[108],"procedure":[109],"dataset":[113,117],"and":[114],"classification":[116],"combined":[120],"train":[122],"deep":[124],"captioning":[125],"show":[128],"our":[130,133],"experiments":[131],"improved":[134],"model":[135,139],"outperforms":[136],"original":[138],"SPICE":[141],"metrics":[142],"by":[143],"4":[144],"times.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}