{"id":"https://openalex.org/W4379539330","doi":"https://doi.org/10.1145/3597926.3598094","title":"ROME: Testing Image Captioning Systems via Recursive Object Melting","display_name":"ROME: Testing Image Captioning Systems via Recursive Object Melting","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4379539330","doi":"https://doi.org/10.1145/3597926.3598094"},"language":"en","primary_location":{"id":"doi:10.1145/3597926.3598094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597926.3598094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.02228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057321039","display_name":"Boxi Yu","orcid":"https://orcid.org/0000-0001-5213-7189"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Boxi Yu","raw_affiliation_strings":["Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057949305","display_name":"Zhiqing Zhong","orcid":"https://orcid.org/0000-0003-2304-9619"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiqing Zhong","raw_affiliation_strings":["Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102731450","display_name":"Jiaqi Li","orcid":"https://orcid.org/0000-0002-8015-8291"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaqi Li","raw_affiliation_strings":["Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049126231","display_name":"Yixing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yixing Yang","raw_affiliation_strings":["Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078511386","display_name":"Shilin He","orcid":"https://orcid.org/0000-0002-8595-5388"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin He","raw_affiliation_strings":["Microsoft Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101941950","display_name":"Pinjia He","orcid":"https://orcid.org/0000-0003-3377-8129"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pinjia He","raw_affiliation_strings":["Chinese University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"766","last_page":"778"},"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/T10036","display_name":"Advanced Neural Network Applications","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9154561758041382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7045474052429199},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6336989402770996},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5861668586730957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5495525598526001},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.546777606010437},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5200247764587402},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4411286413669586},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4279588460922241},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41741201281547546},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4157436490058899},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3392127752304077},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30268147587776184}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9154561758041382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045474052429199},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6336989402770996},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5861668586730957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5495525598526001},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.546777606010437},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5200247764587402},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4411286413669586},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4279588460922241},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41741201281547546},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4157436490058899},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3392127752304077},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30268147587776184},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":2,"locations":[{"id":"doi:10.1145/3597926.3598094","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597926.3598094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.02228","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.02228","pdf_url":"https://arxiv.org/pdf/2306.02228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.02228","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.02228","pdf_url":"https://arxiv.org/pdf/2306.02228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G5538095355","display_name":null,"funder_award_id":"No. 62102340","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8710987931","display_name":null,"funder_award_id":"62102340","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4379539330.pdf","grobid_xml":"https://content.openalex.org/works/W4379539330.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2007339694","https://openalex.org/W2016075127","https://openalex.org/W2109579504","https://openalex.org/W2168322495","https://openalex.org/W2327037637","https://openalex.org/W2741609678","https://openalex.org/W2782311202","https://openalex.org/W2804337238","https://openalex.org/W2930957955","https://openalex.org/W2957905354","https://openalex.org/W2963270032","https://openalex.org/W2963327228","https://openalex.org/W2963857521","https://openalex.org/W2963913218","https://openalex.org/W2964048171","https://openalex.org/W2979485058","https://openalex.org/W2981495453","https://openalex.org/W3007157104","https://openalex.org/W3035688398","https://openalex.org/W3090449556","https://openalex.org/W3090988182","https://openalex.org/W3091588028","https://openalex.org/W3109744225","https://openalex.org/W3124118940","https://openalex.org/W3163644064","https://openalex.org/W3173220247","https://openalex.org/W3178469298","https://openalex.org/W3199003182","https://openalex.org/W4200448782","https://openalex.org/W4229068576","https://openalex.org/W4282982144","https://openalex.org/W4285490473","https://openalex.org/W4297903204","https://openalex.org/W4308641598"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2029561777","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W172797710","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314"],"abstract_inverted_index":{"Image":[0],"captioning":[1,64,194],"(IC)":[2],"systems":[3,21,47],"aim":[4],"to":[5,62,71,80,180,189,226,262],"generate":[6,95,125,181],"a":[7,111,165,241],"text":[8],"description":[9,37],"of":[10,65,85,154,164,184,243],"the":[11,44,82,134,148,152,158,162,205,216,227,256,264],"salient":[12],"objects":[13,179],"in":[14,39,91,151,161],"an":[15,155,172],"image.":[16],"In":[17,251],"recent":[18],"years,":[19],"IC":[20,46,86,118,218],"have":[22],"been":[23],"increasingly":[24],"integrated":[25],"into":[26],"our":[27],"daily":[28],"lives,":[29],"such":[30],"as":[31,98],"assistance":[32],"for":[33,116],"visually-impaired":[34],"people":[35],"and":[36,53,69,142,196,221],"generation":[38],"Microsoft":[40,49],"Powerpoint.":[41],"However,":[42],"even":[43],"cutting-edge":[45],"(e.g.,":[48,55],"Azure":[50],"Cognitive":[51],"Services)":[52],"algorithms":[54],"OFA)":[56],"could":[57],"produce":[58],"erroneous":[59,245],"captions,":[60],"leading":[61],"incorrect":[63],"important":[66],"objects,":[67,130],"misunderstanding,":[68],"threats":[70],"personal":[72],"safety.":[73],"The":[74,201],"existing":[75,122],"testing":[76,114,219],"approaches":[77,123],"either":[78],"fail":[79],"handle":[81],"complex":[83],"form":[84],"system":[87],"output":[88],"(i.e.,":[89,140],"sentences":[90],"natural":[92,214],"language)":[93],"or":[94],"unnatural":[96],"images":[97,136],"test":[99,126,190,206,233,257],"cases.":[100],"To":[101],"address":[102],"these":[103],"problems,":[104],"we":[105,253],"introduce":[106],"Recursive":[107],"Object":[108],"MElting":[109],"(ROME),":[110],"novel":[112],"metamorphic":[113],"approach":[115,220],"validating":[117],"systems.":[119],"Different":[120],"from":[121],"that":[124,147,204],"cases":[127,207,258],"by":[128,209,231,260],"inserting":[129],"which":[131,266],"easily":[132],"make":[133],"generated":[135,166,208,259],"unnatural,":[137],"ROME":[138,145,174,188,210,239,261],"melts":[139],"remove":[141,177],"inpaint)":[143],"objects.":[144],"assumes":[146],"object":[149,159,169],"set":[150,160],"caption":[153,163],"image":[156,167,193],"includes":[157],"after":[168],"melting.":[170],"Given":[171],"image,":[173],"can":[175],"recursively":[176],"its":[178,268],"different":[182],"pairs":[183,234],"images.":[185,229],"We":[186],"use":[187],"one":[191],"widely-adopted":[192],"API":[195],"four":[197],"state-of-the-art":[198],"(SOTA)":[199],"algorithms.":[200],"results":[202],"show":[203],"look":[211],"much":[212],"more":[213],"than":[215],"SOTA":[217],"they":[222],"achieve":[223],"comparable":[224],"naturalness":[225],"original":[228],"Meanwhile,":[230],"generating":[232],"using":[235],"226":[236],"seed":[237],"images,":[238],"reports":[240],"total":[242],"9,121":[244],"issues":[246],"with":[247],"high":[248],"precision":[249],"(86.47%-92.17%).":[250],"addition,":[252],"further":[254],"utilize":[255],"retrain":[263],"Oscar,":[265],"improves":[267],"performance":[269],"across":[270],"multiple":[271],"evaluation":[272],"metrics.":[273]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}