{"id":"https://openalex.org/W4416036784","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.477","title":"SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation","display_name":"SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036784","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.477"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.477","pdf_url":"https://aclanthology.org/2025.emnlp-main.477.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.477.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003078440","display_name":"Xiaofu Chen","orcid":"https://orcid.org/0009-0001-3896-4433"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaofu Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065946161","display_name":"Israfel Salazar","orcid":"https://orcid.org/0000-0001-9360-0192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Israfel Salazar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048127182","display_name":"Yova Kementchedjhieva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yova Kementchedjhieva","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003078440"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35267531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9406","last_page":"9418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9194999933242798,"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":0.9194999933242798,"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":0.010999999940395355,"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":0.00839999970048666,"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/image","display_name":"Image (mathematics)","score":0.4235999882221222},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3122999966144562},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2660999894142151},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2361000031232834},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2296999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5719000101089478},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5619000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.527400016784668},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3122999966144562},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2361000031232834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2296999990940094},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.22949999570846558},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.20919999480247498}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.477","pdf_url":"https://aclanthology.org/2025.emnlp-main.477.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.477","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.477","pdf_url":"https://aclanthology.org/2025.emnlp-main.477.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036784.pdf","grobid_xml":"https://content.openalex.org/works/W4416036784.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"interest":[1],"grows":[2],"in":[3,43,117],"generating":[4],"long,":[5],"detailed":[6],"image":[7,89,137],"captions,":[8],"standard":[9],"evaluation":[10,135],"metrics":[11,15,55,116],"become":[12],"increasingly":[13],"unreliable.N-gram-based":[14],"though":[16],"efficient,":[17],"fail":[18],"to":[19,27,35,49,52,87,119],"capture":[20],"semantic":[21],"correctness.Representational":[22],"Similarity":[23],"(RS)":[24],"metrics,":[25],"designed":[26],"address":[28],"this,":[29],"initially":[30],"saw":[31],"limited":[32],"use":[33,74],"due":[34,48],"high":[36],"computational":[37],"costs,":[38],"while":[39,122],"today,":[40],"despite":[41],"advances":[42],"hardware,":[44],"they":[45],"remain":[46,69],"unpopular":[47],"low":[50],"correlation":[51,64,118],"human":[53,66,120],"judgments.Meanwhile,":[54],"based":[56],"on":[57],"large":[58],"language":[59],"models":[60],"(LLMs)":[61],"show":[62,107],"strong":[63],"with":[65,93],"judgments,":[67,121],"but":[68],"too":[70],"expensive":[71],"for":[72,132],"iterative":[73,133],"during":[75,136],"model":[76,139],"development.We":[77],"introduce":[78],"SPECS":[79,109],"(Specificity-Enhanced":[80],"CLIP-Score),":[81],"a":[82,94,129],"reference-free":[83],"RS":[84],"metric":[85],"tailored":[86],"long":[88],"captioning.SPECS":[90],"modifies":[91],"CLIP":[92],"new":[95],"objective":[96],"that":[97,108],"emphasizes":[98],"specificity:":[99],"rewarding":[100],"correct":[101],"details":[102],"and":[103],"penalizing":[104],"incorrect":[105],"ones.We":[106],"matches":[110],"the":[111],"performance":[112],"of":[113],"open-source":[114],"LLMbased":[115],"being":[123],"far":[124],"more":[125],"efficient.This":[126],"makes":[127],"it":[128],"practical":[130],"alternative":[131],"checkpoint":[134],"captioning":[138],"development.":[140]},"counts_by_year":[],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-11-08T00:00:00"}