{"id":"https://openalex.org/W3091679853","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206632","title":"Extricating from GroundTruth: An Unpaired Learning Based Evaluation Metric for Image Captioning","display_name":"Extricating from GroundTruth: An Unpaired Learning Based Evaluation Metric for Image Captioning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3091679853","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206632","mag":"3091679853"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5100722639","display_name":"Zhong\u2010Qiu Zhao","orcid":"https://orcid.org/0000-0002-0477-4412"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Zhao","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology","School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005960609","display_name":"Yue-Lin Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue-Lin Sun","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology","School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017107193","display_name":"Nan-Xun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan-Xun Wang","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology","School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076347170","display_name":"Weidong Tian","orcid":"https://orcid.org/0000-0003-0175-1132"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Dong Tian","raw_affiliation_strings":["Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology","School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0979,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41387698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1512 3385","issue":null,"first_page":"1","last_page":"8"},"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":0.9894000291824341,"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":0.9836999773979187,"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":0.9011015295982361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7967543005943298},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6557690501213074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6478158235549927},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6161618232727051},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5040596723556519},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49726489186286926},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4868428111076355},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48514804244041443},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.45674222707748413},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44558703899383545},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1015298068523407},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07595318555831909}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9011015295982361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967543005943298},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6557690501213074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478158235549927},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6161618232727051},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5040596723556519},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49726489186286926},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4868428111076355},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48514804244041443},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.45674222707748413},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44558703899383545},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1015298068523407},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07595318555831909},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1489525520","https://openalex.org/W1514535095","https://openalex.org/W1530622307","https://openalex.org/W1566289585","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1969616664","https://openalex.org/W2028176545","https://openalex.org/W2099471712","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2143449221","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2581637843","https://openalex.org/W2583679610","https://openalex.org/W2604178507","https://openalex.org/W2605045867","https://openalex.org/W2625940279","https://openalex.org/W2745461083","https://openalex.org/W2765961751","https://openalex.org/W2766182427","https://openalex.org/W2798490859","https://openalex.org/W2799009156","https://openalex.org/W2808503835","https://openalex.org/W2822349497","https://openalex.org/W2887153785","https://openalex.org/W2890231609","https://openalex.org/W2903179935","https://openalex.org/W2949376505","https://openalex.org/W2949748713","https://openalex.org/W2951520714","https://openalex.org/W2951590222","https://openalex.org/W2951684117","https://openalex.org/W2952640344","https://openalex.org/W2962824887","https://openalex.org/W2962968835","https://openalex.org/W2963049308","https://openalex.org/W2963206679","https://openalex.org/W2963223306","https://openalex.org/W2963248296","https://openalex.org/W2963267809","https://openalex.org/W2963527228","https://openalex.org/W2963743213","https://openalex.org/W2963992143","https://openalex.org/W2964042428","https://openalex.org/W3103022576","https://openalex.org/W4298393544","https://openalex.org/W4302353911","https://openalex.org/W4320013936","https://openalex.org/W6630875275","https://openalex.org/W6639432524","https://openalex.org/W6681184217","https://openalex.org/W6685322675","https://openalex.org/W6687483927","https://openalex.org/W6725318829","https://openalex.org/W6732817193","https://openalex.org/W6742999658","https://openalex.org/W6745388339","https://openalex.org/W6745740328","https://openalex.org/W6752865951","https://openalex.org/W6753816263","https://openalex.org/W6754706244","https://openalex.org/W6756893277"],"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/W4388002133","https://openalex.org/W3087250444","https://openalex.org/W4323929292"],"abstract_inverted_index":{"Recently,":[0],"instead":[1],"of":[2,13,83,176],"pursuing":[3],"high":[4],"performance":[5],"on":[6],"classical":[7],"evaluation":[8,58],"metrics,":[9,79],"the":[10,42,47,86,91,102,110,122,126,135,161,173,180],"research":[11],"focus":[12],"image":[14,96,123],"captioning":[15],"has":[16],"shifted":[17],"to":[18,46,70,141,149],"generating":[19],"sentences":[20],"which":[21,37,66],"are":[22,32,45],"more":[23],"vivid":[24],"and":[25,74,98,101,125,144,179,185],"stylized":[26,151],"than":[27],"human-written":[28,48,73],"ones.":[29,49],"However,":[30],"there":[31],"still":[33],"no":[34],"applicable":[35],"metrics":[36],"can":[38,67,146,170],"judge":[39,172],"how":[40,108],"close":[41],"generated":[43,75,177],"captions":[44,178,184],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"a":[55,130],"novel":[56],"learning-based":[57],"metric,":[59],"namely":[60],"Unpaired":[61],"Image":[62],"Captioning":[63],"Evaluation":[64],"(UICE),":[65],"be":[68,142,147,150],"trained":[69,148],"distinguish":[71],"between":[72,94,183],"captions.":[76],"Unlike":[77],"existing":[78],"our":[80,168],"UICE":[81],"consists":[82],"two":[84],"parts:":[85],"semantic":[87,92,115,181],"alignment":[88,116],"module":[89,105,117,138],"measuring":[90],"distance":[93],"extracted":[95],"features":[97,124],"caption":[99,112],"meanings,":[100],"syntactic":[103,136],"discriminating":[104,137],"syntactically":[106],"judging":[107],"human-like":[109],"candidate":[111],"is.":[113],"The":[114],"is":[118,139],"implemented":[119],"by":[120,152],"mapping":[121],"word":[127],"embedding":[128],"into":[129],"unified":[131],"tensor":[132],"space.":[133],"And":[134],"designed":[140],"learning-based,":[143],"thereby":[145],"users'":[153],"own,":[154],"fed":[155],"with":[156],"additional":[157],"personalized":[158],"corpus":[159],"during":[160],"training":[162],"process.":[163],"Extensive":[164],"experiments":[165],"indicate":[166],"that":[167],"metric":[169],"correctly":[171],"grammatical":[174],"correctness":[175],"consistency":[182],"corresponding":[186],"images.":[187]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}