{"id":"https://openalex.org/W7138141536","doi":"https://doi.org/10.1609/aaai.v40i9.37705","title":"Negative Entity Suppression for Zero-Shot Captioning with Synthetic Images","display_name":"Negative Entity Suppression for Zero-Shot Captioning with Synthetic Images","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138141536","doi":"https://doi.org/10.1609/aaai.v40i9.37705"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i9.37705","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37705","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i9.37705","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083675972","display_name":"Zimao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zimao Lu","raw_affiliation_strings":["School of Computer Science and Technology/ School of Artificial Intelligence,China University of Mining and Technology, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology/ School of Artificial Intelligence,China University of Mining and Technology, Jiangsu, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129685659","display_name":"Hui Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xu","raw_affiliation_strings":["School of Computer Science and Technology/ School of Artificial Intelligence,China University of Mining and Technology, Jiangsu, China\nMine Digitization Engineering Research Center of the Ministry of Education"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology/ School of Artificial Intelligence,China University of Mining and Technology, Jiangsu, China\nMine Digitization Engineering Research Center of the Ministry of Education","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697086","display_name":"Bing Jie Darius Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Liu","raw_affiliation_strings":["School of Computer Science and Technology/ School of Artificial Intelligence,China University of Mining and Technology, Jiangsu, China\nMine Digitization Engineering Research Center of the Ministry of Education"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology/ School of Artificial Intelligence,China University of Mining and Technology, Jiangsu, China\nMine Digitization Engineering Research Center of the Ministry of Education","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129727326","display_name":"Ke Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["School of Computer Science and Technology/ School of Artificial Intelligence,China University of Mining and Technology, Jiangsu, China\nMine Digitization Engineering Research Center of the Ministry of Education"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology/ School of Artificial Intelligence,China University of Mining and Technology, Jiangsu, China\nMine Digitization Engineering Research Center of the Ministry of Education","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25250678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7636","last_page":"7643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9235000014305115,"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":0.9235000014305115,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.031599998474121094,"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":0.007400000002235174,"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":0.9228000044822693},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.845300018787384},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.36419999599456787},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3544999957084656},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34299999475479126},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3400999903678894}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9228000044822693},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.845300018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185999870300293},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i9.37705","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37705","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37705","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37705","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4241960644721985,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-only":[0],"training":[1,31,118],"provides":[2],"an":[3],"attractive":[4],"approach":[5],"to":[6,51,71,97,111,129,142],"address":[7],"data":[8],"scarcity":[9],"challenges":[10],"in":[11,83,173],"zero-shot":[12],"image":[13],"captioning":[14],"(ZIC),":[15],"avoiding":[16],"the":[17,72,76,90,145],"expense":[18],"of":[19,78,147],"collecting":[20],"paired":[21],"image-text":[22],"annotations.":[23],"However,":[24],"although":[25],"these":[26],"approaches":[27],"perform":[28],"well":[29],"within":[30],"domains,":[32],"they":[33,60],"suffer":[34],"from":[35,89,126],"poor":[36],"cross-domain":[37,163],"generalization,":[38],"often":[39],"producing":[40],"hallucinated":[41],"content":[42,128],"when":[43,65],"encountering":[44],"novel":[45],"visual":[46],"environments.":[47],"Retrieval-based":[48],"methods":[49],"attempt":[50],"mitigate":[52],"this":[53,99],"limitation":[54],"by":[55],"leveraging":[56],"external":[57],"knowledge,":[58],"but":[59,86],"can":[61],"paradoxically":[62],"exacerbate":[63],"hallucination":[64,167],"retrieved":[66,127],"captions":[67],"contain":[68],"entities":[69,125,141],"irrelevant":[70],"inputs.":[73],"We":[74],"introduce":[75],"concept":[77],"negative":[79,124,140],"entities\u2014objects":[80],"that":[81,155],"appear":[82],"generated":[84],"caption":[85],"are":[87],"absent":[88],"input\u2014and":[91],"propose":[92],"Negative":[93],"Entity":[94],"Suppression":[95],"(NES)":[96],"tackle":[98],"challenge.":[100],"NES":[101,156],"seamlessly":[102],"integrates":[103],"three":[104],"stages:":[105],"(1)":[106],"it":[107,122,134],"employs":[108],"synthetic":[109],"images":[110],"ensure":[112],"consistent":[113],"image-to-text":[114],"retrieval":[115],"across":[116,151],"both":[117],"and":[119,132,165],"inference;":[120],"(2)":[121],"filters":[123],"enhance":[130],"accuracy;":[131],"(3)":[133],"applies":[135],"attention-level":[136],"suppression":[137],"using":[138],"identified":[139],"further":[143],"minimize":[144],"impact":[146],"hallucination-prone":[148],"features.":[149],"Evaluation":[150],"multiple":[152],"benchmarks":[153],"demonstrates":[154],"maintains":[157],"competitive":[158],"in-domain":[159],"performance":[160],"while":[161],"improving":[162],"transfer":[164],"reducing":[166],"rates,":[168],"achieving":[169],"new":[170],"state-of-the-art":[171],"results":[172],"ZIC.":[174]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}
