{"id":"https://openalex.org/W7128990694","doi":"https://doi.org/10.1109/tmm.2026.3665006","title":"L-CLIPScore: A Lightweight Embedding-Based Captioning Metric for Evaluating and Training","display_name":"L-CLIPScore: A Lightweight Embedding-Based Captioning Metric for Evaluating and Training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128990694","doi":"https://doi.org/10.1109/tmm.2026.3665006"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3665006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3665006","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5100361041","display_name":"Li Li","orcid":"https://orcid.org/0000-0001-8485-2216"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-1268-6453","affiliations":[{"raw_affiliation_string":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126132631","display_name":"Yingzhe Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingzhe Peng","raw_affiliation_strings":["Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-6077-6704","affiliations":[{"raw_affiliation_string":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126161190","display_name":"Xu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":["Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8276-2679","affiliations":[{"raw_affiliation_string":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125056886","display_name":"Ruoxi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoxi Cheng","raw_affiliation_strings":["Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-3261-642X","affiliations":[{"raw_affiliation_string":"Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications, (Southeast University), Ministry of Education, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126132689","display_name":"Xu Haiyang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Xu","raw_affiliation_strings":["Alibaba Group, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126126339","display_name":"Yan Ming","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":["Alibaba Group, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-4959-8878","affiliations":[{"raw_affiliation_string":"Alibaba Group, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126138541","display_name":"Huang Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":["Alibaba Group, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-3709-5053","affiliations":[{"raw_affiliation_string":"Alibaba Group, Zhejiang, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":4.6258,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91836936,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"5487","last_page":"5496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9700999855995178,"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":0.9700999855995178,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00570000009611249,"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"}},{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8478000164031982},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.652999997138977},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6467000246047974},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5788999795913696},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.515999972820282},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4796000123023987},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.4332999885082245},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.38260000944137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565999865531921},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8478000164031982},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.652999997138977},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5788999795913696},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113000273704529},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C178005623","wikidata":"https://www.wikidata.org/wiki/Q308859","display_name":"Anonymity","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3665006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3665006","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1840098831","display_name":null,"funder_award_id":"62576091","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2506483933","https://openalex.org/W2575842049","https://openalex.org/W2611009517","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2906314281","https://openalex.org/W2913618459","https://openalex.org/W2963084599","https://openalex.org/W2963448089","https://openalex.org/W2963855133","https://openalex.org/W2970120757","https://openalex.org/W2970858040","https://openalex.org/W2981165461","https://openalex.org/W3034417909","https://openalex.org/W3034655362","https://openalex.org/W3095319910","https://openalex.org/W3098358988","https://openalex.org/W3105966348","https://openalex.org/W3107503524","https://openalex.org/W3136792391","https://openalex.org/W3138516171","https://openalex.org/W3153469116","https://openalex.org/W3167596001","https://openalex.org/W3168640669","https://openalex.org/W3173658182","https://openalex.org/W3214192224","https://openalex.org/W4225329158","https://openalex.org/W4226452284","https://openalex.org/W4253028564","https://openalex.org/W4312629998","https://openalex.org/W4312671791","https://openalex.org/W4312769570","https://openalex.org/W4318953563","https://openalex.org/W4385245566","https://openalex.org/W4386071687","https://openalex.org/W4391216079","https://openalex.org/W7133244560"],"related_works":[],"abstract_inverted_index":{"We":[0,134,157],"propose":[1],"a":[2,25,31,68],"novel":[3,69,111],"embedding-based":[4],"captioning":[5,19,170],"metric":[6,180],"termed":[7],"asL-CLIPScorethat":[8],"can":[9],"be":[10,174],"used":[11],"for":[12,53],"efficiently":[13],"evaluating":[14],"caption":[15,155],"quality":[16],"and":[17,35,50,59,96,107,131,143,181],"training":[18,191],"model.":[20],"L-CLIPScore":[21,146,163,186],"is":[22,30,94,103],"calculated":[23],"from":[24,37],"lightweight":[26],"CLIP":[27,124],"(L-CLIP),":[28],"which":[29,46],"dual-encoder":[32],"architecture":[33],"compressed":[34],"distilled":[36],"CLIP.":[38],"To":[39,64],"compress,":[40],"we":[41,66],"apply":[42],"two":[43],"powerful":[44],"techniques":[45],"are":[47],"weight":[48],"multiplexing":[49],"matrix":[51],"decomposition":[52],"reducing":[54],"the":[55,85,90,98,101,122,141,151,165,169],"parameters":[56],"of":[57,145],"encoders":[58],"word":[60],"embedding":[61,87],"matrix,":[62],"respectively.":[63],"distill,":[65],"design":[67],"multi-modal":[70,86,118],"Similarity":[71],"Regulator":[72],"(SR)":[73],"loss":[74,83],"to":[75,121,139,153,167],"transfer":[76],"more":[77],"vision-language":[78],"alignment":[79,119],"knowledge.":[80],"Specifically,":[81],"SR":[82,112],"amplifies":[84],"similarity":[88,99],"if":[89,100],"given":[91],"image-text":[92],"pair":[93,102],"matched":[95],"diminishes":[97],"non-matched.":[104],"By":[105],"compressing":[106],"distilling":[108],"by":[109,177],"this":[110],"loss,":[113],"our":[114],"L-CLIP":[115],"achieves":[116],"comparable":[117],"ability":[120],"original":[123],"while":[125],"it":[126,149,172],"requires":[127],"fewer":[128],"computation":[129],"resources":[130],"running":[132],"time.":[133],"carry":[135],"out":[136],"exhaustive":[137],"experiments":[138],"validate":[140],"efficiency":[142],"effectiveness":[144],"when":[147,161],"using":[148,162,185],"as":[150,164],"judge":[152],"evaluate":[154],"quality.":[156],"also":[158],"discover":[159],"that":[160],"supervisor":[166],"train":[168],"model,":[171],"should":[173],"mixed":[175],"up":[176],"an":[178],"n-gram-based":[179],"meanwhile":[182],"analyze":[183],"why":[184],"only":[187],"will":[188],"cause":[189],"fail":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-02-17T00:00:00"}