{"id":"https://openalex.org/W4404371481","doi":"https://doi.org/10.1109/tnnls.2024.3487200","title":"Advancing Causal Intervention in Image Captioning With Causal Prompt","display_name":"Advancing Causal Intervention in Image Captioning With Causal Prompt","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404371481","doi":"https://doi.org/10.1109/tnnls.2024.3487200","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030378"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3487200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3487200","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5067319464","display_name":"Youngjoon Yu","orcid":"https://orcid.org/0000-0002-3188-2080"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjoon Yu","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","School of Electrical Engineering, Image and Video Systems Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-3188-2080","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, Image and Video Systems Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043898799","display_name":"Yeonju Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeonju Kim","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","School of Electrical Engineering, Image and Video Systems Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, Image and Video Systems Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","School of Electrical Engineering, Image and Video Systems Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-5306-6853","affiliations":[{"raw_affiliation_string":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, Image and Video Systems Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18723814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"12631","last_page":"12642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9825000166893005,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9366000294685364,"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":0.9097909927368164},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.5860303640365601},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.514432966709137},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.39824461936950684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3959577679634094},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35751211643218994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3016255497932434},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10821789503097534},{"id":"https://openalex.org/keywords/psychiatry","display_name":"Psychiatry","score":0.07203507423400879}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9097909927368164},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.5860303640365601},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.514432966709137},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.39824461936950684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3959577679634094},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35751211643218994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3016255497932434},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10821789503097534},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.07203507423400879}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3487200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3487200","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40030378","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030378","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2149528412","https://openalex.org/W2578613799","https://openalex.org/W2745461083","https://openalex.org/W2796354110","https://openalex.org/W2962735233","https://openalex.org/W2962749469","https://openalex.org/W2962938439","https://openalex.org/W2963084599","https://openalex.org/W2963528347","https://openalex.org/W2963686907","https://openalex.org/W2978477568","https://openalex.org/W2986670728","https://openalex.org/W3018074695","https://openalex.org/W3019023591","https://openalex.org/W3034655362","https://openalex.org/W3035103424","https://openalex.org/W3035145964","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035651653","https://openalex.org/W3119438769","https://openalex.org/W3167939936","https://openalex.org/W3171353004","https://openalex.org/W3173220247","https://openalex.org/W3175824375","https://openalex.org/W3195541832","https://openalex.org/W3205607545","https://openalex.org/W3206022579","https://openalex.org/W4220899212","https://openalex.org/W4221163971","https://openalex.org/W4283722434","https://openalex.org/W4285186657","https://openalex.org/W4287020098","https://openalex.org/W4307965990","https://openalex.org/W4308455108","https://openalex.org/W4312232840","https://openalex.org/W4312651322","https://openalex.org/W4312924260","https://openalex.org/W4312975593","https://openalex.org/W4319777846","https://openalex.org/W4375868878","https://openalex.org/W4379929708","https://openalex.org/W4385245566","https://openalex.org/W4385338579","https://openalex.org/W4385572884","https://openalex.org/W4385757404","https://openalex.org/W4386075538","https://openalex.org/W4388189274","https://openalex.org/W4388543952","https://openalex.org/W4389317971","https://openalex.org/W4396609326","https://openalex.org/W4399360161","https://openalex.org/W4401163318","https://openalex.org/W4402753999","https://openalex.org/W6631190155","https://openalex.org/W6676647902","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6752946794","https://openalex.org/W6776786843","https://openalex.org/W6779945560","https://openalex.org/W6782868315","https://openalex.org/W6809536152","https://openalex.org/W6838865580","https://openalex.org/W6851333437","https://openalex.org/W6854256677"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"a":[3],"novel":[4],"approach,":[5],"called":[6],"causal":[7,14,39,56,74,102],"prompting":[8],"network":[9],"(CPNet),":[10],"to":[11,34,79,96,108,116],"enhance":[12,97],"the":[13,17,28,81,89,93,110,122,134,147,152,159,163],"intervention":[15,40],"in":[16,27,38,139],"context":[18,140],"of":[19,64,68,92,113,129,165],"image":[20,58,117,169],"captioning.":[21],"By":[22],"leveraging":[23],"visual":[24,65],"prompt":[25,71,76],"engineering":[26],"feature":[29,82,91,95],"space,":[30],"this":[31],"method":[32],"aims":[33],"achieve":[35],"superior":[36],"performance":[37,164],"tasks.":[41,119],"Since":[42],"CPNet":[43,161],"is":[44,86,106],"highly":[45],"flexible":[46],"and":[47,73,143,146],"adaptable,":[48],"it":[49],"can":[50],"be":[51],"incorporated":[52],"into":[53],"any":[54],"existing":[55],"intervention-based":[57],"captioning":[59,118,170],"framework.":[60],"Specifically,":[61],"two":[62],"types":[63],"prompts-causal":[66],"region":[67],"interest":[69],"(RoI)":[70],"(CRP)":[72],"matching":[75],"(CMP)-are":[77],"employed":[78],"refine":[80],"representations":[83],"effectively.":[84],"CRP":[85],"utilized":[87],"on":[88,133],"RoI":[90,98],"object":[94],"features":[99],"with":[100],"deconfounded":[101],"features.":[103],"Meanwhile,":[104],"CMP":[105],"used":[107],"strengthen":[109],"contextual":[111],"representation":[112],"confounders":[114],"linked":[115],"To":[120],"evaluate":[121],"proposed":[123,160],"CPNet's":[124],"effectiveness,":[125],"an":[126],"extensive":[127],"range":[128],"experiments":[130],"are":[131,149],"conducted":[132],"popular":[135],"microsoft":[136],"common":[137],"objects":[138],"dataset":[141],"(MS-COCO)":[142],"Flickr30k":[144],"datasets,":[145],"results":[148,156],"validated":[150],"using":[151],"Karpathy":[153],"split.":[154],"Experimental":[155],"demonstrate":[157],"that":[158],"surpasses":[162],"other":[166],"state-of-the-art":[167],"(SOTA)":[168],"methods.":[171]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}