{"id":"https://openalex.org/W4403780521","doi":"https://doi.org/10.1145/3664647.3681458","title":"See or Guess: Counterfactually Regularized Image Captioning","display_name":"See or Guess: Counterfactually Regularized Image Captioning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780521","doi":"https://doi.org/10.1145/3664647.3681458"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681458","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/A5102081080","display_name":"Qian Cao","orcid":"https://orcid.org/0000-0003-3288-1714"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qian Cao","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3288-1714","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101755392","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0003-0144-1775"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0144-1775","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505570","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0001-6036-9035"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6036-9035","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101524540","display_name":"Xiting Wang","orcid":"https://orcid.org/0000-0001-5768-1095"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiting Wang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5768-1095","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102524460","display_name":"Xinting Huang","orcid":"https://orcid.org/0000-0001-6827-7426"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinting Huang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-6827-7426","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuchen Ren","orcid":"https://orcid.org/0009-0003-3301-6113"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Ren","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-3301-6113","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102081080"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.9523,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77027588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"965","last_page":"974"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9894999861717224,"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":0.989300012588501,"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":0.8879663944244385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6794896721839905},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6195283532142639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47171327471733093},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3865639865398407}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8879663944244385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794896721839905},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6195283532142639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47171327471733093},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3865639865398407}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681458","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":33,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1593271688","https://openalex.org/W1773149199","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2185175083","https://openalex.org/W2486285194","https://openalex.org/W2890531016","https://openalex.org/W2962735233","https://openalex.org/W2990818246","https://openalex.org/W2997591391","https://openalex.org/W3034655362","https://openalex.org/W3099884329","https://openalex.org/W3103542727","https://openalex.org/W3106544837","https://openalex.org/W3174966920","https://openalex.org/W3176716813","https://openalex.org/W3177934633","https://openalex.org/W3202965415","https://openalex.org/W3206022579","https://openalex.org/W3208343573","https://openalex.org/W4287077836","https://openalex.org/W4296935086","https://openalex.org/W4297644311","https://openalex.org/W4312232840","https://openalex.org/W4312933868","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4385565270","https://openalex.org/W4386566667","https://openalex.org/W4390873264","https://openalex.org/W4394625777","https://openalex.org/W6774562791"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Image":[0],"captioning,":[1],"which":[2],"generates":[3],"natural":[4,118],"language":[5],"descriptions":[6],"of":[7,28,52,102],"images,":[8,41,154],"is":[9,167],"a":[10,87],"crucial":[11],"task":[12,22],"in":[13,63,76],"vision-language":[14],"research.":[15],"Previous":[16],"models":[17,99,128],"have":[18],"typically":[19],"addressed":[20],"this":[21,83],"by":[23],"aligning":[24],"the":[25,53,124,150],"generative":[26],"capabilities":[27],"machines":[29],"with":[30,78],"humans":[31,60],"through":[32],"statistical":[33],"fitting":[34],"existing":[35,98],"datasets.":[36],"While":[37],"effective":[38],"for":[39],"normal":[40],"they":[42],"may":[43],"struggle":[44],"to":[45,96,129,153],"accurately":[46],"describe":[47],"those":[48],"where":[49],"certain":[50],"parts":[51],"image":[54,89],"are":[55],"obscured":[56],"or":[57,117],"edited,":[58],"unlike":[59],"who":[61],"excel":[62],"such":[64],"cases.":[65],"These":[66],"weaknesses,":[67],"including":[68],"hallucinations":[69,147],"and":[70,105,148,161],"limited":[71],"interpretability,":[72],"often":[73],"hinder":[74],"performance":[75],"scenarios":[77],"shifted":[79],"association":[80],"patterns.":[81],"In":[82],"paper,":[84],"we":[85],"present":[86],"generic":[88],"captioning":[90],"framework":[91],"that":[92,142],"employs":[93],"causal":[94],"inference":[95],"make":[97],"more":[100],"capable":[101],"interventional":[103],"tasks,":[104],"counterfactually":[106],"explainable.":[107],"Our":[108],"approach":[109],"includes":[110],"two":[111],"variants":[112],"leveraging":[113],"either":[114],"total":[115],"effect":[116],"direct":[119],"effect.":[120],"Integrating":[121],"them":[122],"into":[123],"training":[125],"process":[126],"enables":[127],"handle":[130],"counterfactual":[131],"scenarios,":[132],"increasing":[133],"their":[134],"generalizability.":[135],"Extensive":[136],"experiments":[137],"on":[138],"various":[139],"datasets":[140],"show":[141],"our":[143],"method":[144],"effectively":[145],"reduces":[146],"improves":[149],"model's":[151],"faithfulness":[152],"demonstrating":[155],"high":[156],"portability":[157],"across":[158],"both":[159],"small-scale":[160],"large-scale":[162],"image-to-text":[163],"models.":[164],"The":[165],"code":[166],"available":[168],"at":[169],"https://github.com/Aman-4-Real/See-or-Guess.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}