{"id":"https://openalex.org/W4403792104","doi":"https://doi.org/10.1145/3664647.3681497","title":"Cross-Modal Coherence-Enhanced Feedback Prompting for News Captioning","display_name":"Cross-Modal Coherence-Enhanced Feedback Prompting for News Captioning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792104","doi":"https://doi.org/10.1145/3664647.3681497"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681497","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681497","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 International Conference on Multimedia","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/A5054900679","display_name":"Ning Xu","orcid":"https://orcid.org/0000-0002-7526-4356"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Xu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114804187","display_name":"Yifei Gao","orcid":"https://orcid.org/0009-0006-0436-5930"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Gao","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325590","display_name":"Tingting Zhang","orcid":"https://orcid.org/0009-0001-7923-2693"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting-Ting Zhang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019994406","display_name":"Hongshuo Tian","orcid":"https://orcid.org/0000-0001-7635-0961"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongshuo Tian","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054900679"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.7502,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73141704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9369","last_page":"9377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9873999953269958,"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":0.7987467646598816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7545886039733887},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7164980173110962},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.615801990032196},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34535813331604004},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34167516231536865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21955591440200806},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06119894981384277}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7987467646598816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545886039733887},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7164980173110962},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.615801990032196},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34535813331604004},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34167516231536865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21955591440200806},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06119894981384277},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681497","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681497","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 International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2308864855","https://openalex.org/W2938603906","https://openalex.org/W2982573303","https://openalex.org/W3081168214","https://openalex.org/W3093088671","https://openalex.org/W3174377922","https://openalex.org/W3176470992","https://openalex.org/W3187369021","https://openalex.org/W3189601601","https://openalex.org/W3206055785","https://openalex.org/W3207004259","https://openalex.org/W3210150990","https://openalex.org/W4206675125","https://openalex.org/W4280590775","https://openalex.org/W4304080167","https://openalex.org/W4367147048","https://openalex.org/W4385574482","https://openalex.org/W4386065596","https://openalex.org/W4386148430","https://openalex.org/W4387968283","https://openalex.org/W4388191278","https://openalex.org/W4388193026","https://openalex.org/W4389523744","https://openalex.org/W4389523981","https://openalex.org/W4390872680","https://openalex.org/W4390873015","https://openalex.org/W4393153810","https://openalex.org/W4393159766"],"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/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"News":[0],"Captioning":[1],"involves":[2],"generating":[3],"the":[4,11,30,38,47,56,63,102,136,173],"descriptions":[5],"for":[6,66],"news":[7,16,67,108,138],"images":[8,105],"based":[9],"on":[10,127,164],"detailed":[12],"content":[13,65],"of":[14,175],"related":[15,28],"articles.":[17,132],"Given":[18],"that":[19,59],"these":[20],"articles":[21],"often":[22],"contain":[23],"extensive":[24,131],"information":[25],"not":[26],"directly":[27],"to":[29,54,74,118,146,157],"image,":[31],"captions":[32,156],"may":[33],"end":[34],"up":[35],"misaligned":[36],"with":[37,62,82,122,140],"visual":[39,64],"content.":[40],"To":[41],"mitigate":[42],"this":[43],"issue,":[44],"we":[45,70,114,134],"propose":[46],"novel":[48],"cross-modal":[49,96],"coherence-enhanced":[50],"feedback":[51,151],"prompting":[52],"method":[53],"clarify":[55],"crucial":[57],"elements":[58],"align":[60],"closely":[61],"captioning.":[68],"Specifically,":[69],"first":[71],"adapt":[72],"CLIP":[73],"develop":[75],"a":[76,89],"news-specific":[77],"image-text":[78],"matching":[79],"module,":[80],"enriched":[81],"insights":[83],"from":[84],"language":[85],"model":[86,121],"MPNet":[87],"using":[88],"matching-score":[90],"comparative":[91],"loss,":[92],"which":[93,153],"facilitates":[94],"effective":[95],"knowledge":[97],"distillation.":[98],"This":[99],"module":[100],"enhance":[101,148],"coherence":[103],"between":[104],"and":[106,169],"each":[107],"sentences":[109],"via":[110],"rating":[111],"confidence.":[112],"Then,":[113],"design":[115],"confidence-aware":[116],"prompts":[117,145],"fine-tune":[119],"LLaVA":[120,149],"by":[123],"LoRa":[124],"strategy,":[125],"focusing":[126],"essential":[128],"details":[129],"in":[130],"Lastly,":[133],"evaluate":[135],"generated":[137],"caption":[139],"refined":[141],"CLIP,":[142],"constructing":[143],"confidence-feedback":[144],"further":[147],"through":[150],"learning,":[152],"iteratively":[154],"refine":[155],"improve":[158],"its":[159],"accuracy.":[160],"Extensive":[161],"experiments":[162],"conduct":[163],"two":[165],"public":[166],"datasets,":[167],"GoodNews":[168],"NYTimes800k,":[170],"have":[171],"validated":[172],"effectiveness":[174],"our":[176],"method.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
