{"id":"https://openalex.org/W3187679738","doi":"https://doi.org/10.24963/ijcai.2021/312","title":"Dependent Multi-Task Learning with Causal Intervention for Image Captioning","display_name":"Dependent Multi-Task Learning with Causal Intervention for Image Captioning","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3187679738","doi":"https://doi.org/10.24963/ijcai.2021/312","mag":"3187679738"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/312","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/312","pdf_url":"https://www.ijcai.org/proceedings/2021/0312.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0312.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100628705","display_name":"Wenqing Chen","orcid":"https://orcid.org/0000-0002-8739-2216"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I59499333","display_name":"Optica","ror":"https://ror.org/00jypd850","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I59499333"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wenqing Chen","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I59499333"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110766031","display_name":"Jidong Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I59499333","display_name":"Optica","ror":"https://ror.org/00jypd850","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I59499333"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jidong Tian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I59499333"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006419976","display_name":"Caoyun Fan","orcid":"https://orcid.org/0000-0001-7360-3468"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I59499333","display_name":"Optica","ror":"https://ror.org/00jypd850","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I59499333"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Caoyun Fan","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I59499333"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074745823","display_name":"Hao He","orcid":"https://orcid.org/0000-0003-0832-8310"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I59499333","display_name":"Optica","ror":"https://ror.org/00jypd850","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I59499333"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Hao He","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I59499333"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085787425","display_name":"Yaohui Jin","orcid":"https://orcid.org/0000-0001-6158-6277"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I59499333","display_name":"Optica","ror":"https://ror.org/00jypd850","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I59499333"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yaohui Jin","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I59499333"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3819,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.66697541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2263","last_page":"2270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955000281333923,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9694662690162659},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.7507116794586182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7410517334938049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6021554470062256},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.515821635723114},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.508754312992096},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4622516334056854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3977994918823242},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39024457335472107}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9694662690162659},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7507116794586182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410517334938049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6021554470062256},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.515821635723114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.508754312992096},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4622516334056854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3977994918823242},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39024457335472107},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/312","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/312","pdf_url":"https://www.ijcai.org/proceedings/2021/0312.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/312","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/312","pdf_url":"https://www.ijcai.org/proceedings/2021/0312.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G2440522462","display_name":null,"funder_award_id":"2018YFC0830400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187679738.pdf","grobid_xml":"https://content.openalex.org/works/W3187679738.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1956340063","https://openalex.org/W1959608418","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2176263492","https://openalex.org/W2250378130","https://openalex.org/W2481240925","https://openalex.org/W2506483933","https://openalex.org/W2547875792","https://openalex.org/W2745461083","https://openalex.org/W2908747729","https://openalex.org/W2951183276","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2976658881","https://openalex.org/W2986670728","https://openalex.org/W2998496456","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3035651653","https://openalex.org/W3036790639","https://openalex.org/W3091588028","https://openalex.org/W3098487628","https://openalex.org/W4289542422","https://openalex.org/W4295097398","https://openalex.org/W4385245566"],"related_works":["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/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W1564680838"],"abstract_inverted_index":{"Recent":[0],"work":[1],"for":[2],"image":[3,19,111],"captioning":[4,20],"mainly":[5],"followed":[6],"an":[7,102],"extract-then-generate":[8],"paradigm,":[9],"pre-extracting":[10],"a":[11,22,57,89,185],"sequence":[12],"of":[13,53,79],"object-based":[14],"features":[15,72,78,124,147],"and":[16,73,82,125,148,151,195,212],"then":[17],"formulating":[18],"as":[21,168],"single":[23],"sequence-to-sequence":[24],"task.":[25],"Although":[26],"promising,":[27],"we":[28,87,100,133,183],"observed":[29],"two":[30],"problems":[31],"in":[32,178],"generated":[33],"captions:":[34],"1)":[35],"content":[36,129],"inconsistency":[37,130],"where":[38,48,172],"models":[39,49,64,154,211],"would":[40,50,116],"generate":[41],"contradicting":[42],"facts;":[43],"2)":[44],"not":[45],"informative":[46],"enough":[47],"miss":[51],"parts":[52],"important":[54],"information.":[55],"From":[56],"causal":[58,96,158],"perspective,":[59],"the":[60,95,108,118,122,128,138,142,145,157,162,169,173,179,197,209],"reason":[61],"is":[62,166],"that":[63,205],"have":[65],"captured":[66],"spurious":[67],"statistical":[68],"correlations":[69],"between":[70,144],"visual":[71,77,123,146,159],"certain":[74],"expressions":[75],"(e.g.,":[76],"\"long":[80],"hair\"":[81],"\"woman\").":[83],"In":[84],"this":[85],"paper,":[86],"propose":[88],"dependent":[90],"multi-task":[91],"learning":[92,188],"framework":[93],"with":[94,216],"intervention":[97],"(DMTCI).":[98],"Firstly,":[99],"involve":[101],"intermediate":[103,114],"task,":[104,110],"bag-of-categories":[105],"generation,":[106],"before":[107],"final":[109],"captioning.":[112],"The":[113,201],"task":[115],"help":[117],"model":[119,207],"better":[120],"understand":[121],"thus":[126,152],"alleviate":[127],"problem.":[131],"Secondly,":[132],"apply":[134],"Pearl's":[135],"do-calculus":[136],"on":[137,156],"model,":[139],"cutting":[140],"off":[141],"link":[143],"possible":[149],"confounders":[150,171,175],"letting":[153],"focus":[155],"features.":[160],"Specifically,":[161],"high-frequency":[163],"concept":[164],"set":[165],"considered":[167],"proxy":[170],"real":[174],"are":[176],"inferred":[177],"continuous":[180],"space.":[181],"Finally,":[182],"use":[184],"multi-agent":[186],"reinforcement":[187],"(MARL)":[189],"strategy":[190],"to":[191],"enable":[192],"end-to-end":[193],"training":[194],"reduce":[196],"inter-task":[198],"error":[199],"accumulations.":[200],"extensive":[202],"experiments":[203],"show":[204],"our":[206],"outperforms":[208],"baseline":[210],"achieves":[213],"competitive":[214],"performance":[215],"state-of-the-art":[217],"models.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}