{"id":"https://openalex.org/W7126429335","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.14","title":"An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics","display_name":"An Examination of the Robustness of Reference-Free Image Captioning Evaluation Metrics","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126429335","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.14"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.14","pdf_url":"https://aclanthology.org/2024.findings-eacl.14.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.14.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044755624","display_name":"Saba Ahmadi","orcid":"https://orcid.org/0000-0002-1046-9940"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Saba Ahmadi","raw_affiliation_strings":["Universit de Montral Mila Universit de Montral Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit de Montral Mila Universit de Montral Canada","institution_ids":["https://openalex.org/I4210155582"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063960231","display_name":"Aishwarya Agrawal","orcid":"https://orcid.org/0000-0002-8620-8077"},"institutions":[{"id":"https://openalex.org/I4210155582","display_name":"Centre Universitaire de Mila","ror":"https://ror.org/05s3cw058","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210155582"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Aishwarya Agrawal","raw_affiliation_strings":["Universit de Montral Mila Universit de Montral Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit de Montral Mila Universit de Montral Canada","institution_ids":["https://openalex.org/I4210155582"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210155582"],"apc_list":null,"apc_paid":null,"fwci":0.2142,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56800448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9117000102996826,"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":0.9117000102996826,"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":0.030799999833106995,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.016899999231100082,"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":0.7261000275611877},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.722100019454956},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38690000772476196},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.31220000982284546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29820001125335693}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7261000275611877},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.722100019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6090999841690063},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5055000185966492},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24580000340938568}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.14","pdf_url":"https://aclanthology.org/2024.findings-eacl.14.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.14","pdf_url":"https://aclanthology.org/2024.findings-eacl.14.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126429335.pdf","grobid_xml":"https://content.openalex.org/works/W7126429335.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"reference-free":[1,26,165],"metrics":[2,39,76,96,135],"such":[3],"as":[4],"CLIP-Score":[5,142],"(Hessel":[6],"et":[7,12,18],"al.,":[8,13,19],"2021),":[9,14],"UMIC":[10],"(Lee":[11],"and":[15,68,113,141,143,171],"PAC-S":[16,69,114,144],"(Sarto":[17],"2023)":[20],"have":[21],"been":[22],"proposed":[23],"for":[24],"automatic":[25],"evaluation":[27,166],"of":[28,37,104,121,123,131,139,150,167],"image":[29,168],"captions.Our":[30],"focus":[31],"lies":[32],"in":[33,40,101,108,126,164],"evaluating":[34],"the":[35,102,109,119,127,148,151],"robustness":[36],"these":[38],"scenarios":[41],"that":[42,58,94],"require":[43],"distinguishing":[44],"between":[45],"two":[46],"captions":[47],"with":[48,63],"high":[49,61],"lexical":[50],"overlap":[51],"but":[52],"very":[53],"different":[54],"meanings.Our":[55],"findings":[56,159],"reveal":[57],"despite":[59],"their":[60,84],"correlation":[62],"human":[64],"judgments,":[65],"CLIPScore,":[66],"UMIC,":[67],"struggle":[70],"to":[71,80,86,99,118,147,153],"identify":[72],"fine-grained":[73],"errors.While":[74],"all":[75,95,134],"exhibit":[77],"strong":[78],"sensitivity":[79,85],"visual":[81],"grounding":[82],"errors,":[83],"caption":[87,152],"implausibility":[88],"errors":[89],"is":[90],"limited.Furthermore,":[91],"we":[92],"found":[93],"are":[97,115,145,173],"sensitive":[98,117],"variations":[100],"size":[103],"image-relevant":[105],"objects":[106,125],"mentioned":[107],"caption,":[110,133],"while":[111],"CLIPScore":[112],"also":[116],"number":[120],"mentions":[122],"imagerelevant":[124],"caption.Regarding":[128],"linguistic":[129],"aspects":[130],"a":[132,154],"show":[136],"weak":[137],"comprehension":[138],"negation,":[140],"insensitive":[146],"structure":[149],"great":[155],"extent.We":[156],"hope":[157],"our":[158],"will":[160],"guide":[161],"further":[162],"improvements":[163],"captioning.Our":[169],"code":[170],"dataset":[172],"publicly":[174],"available":[175],"at:":[176],"https://github.com/saba96/img-cap-metricsrobustness.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-02-02T00:00:00"}
