{"id":"https://openalex.org/W7137982819","doi":"https://doi.org/10.1609/aaai.v40i15.38264","title":"FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention","display_name":"FaNe: Towards Fine-Grained Cross-Modal Contrast with False-Negative Reduction and Text-Conditioned Sparse Attention","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137982819","doi":"https://doi.org/10.1609/aaai.v40i15.38264"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i15.38264","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38264","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38264/42226","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38264/42226","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129671804","display_name":"Peng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Shenzhen University"],"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129642113","display_name":"Zhihui Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihui Lai","raw_affiliation_strings":["Shenzhen University"],"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680321","display_name":"Wenting Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenting Chen","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666525","display_name":"Xu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Wu","raw_affiliation_strings":["Shenzhen University"],"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129753041","display_name":"Heng Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127213","display_name":"Baotou Central Hospital","ror":"https://ror.org/031pkxq11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210127213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Kong","raw_affiliation_strings":["Baoan Central Hospital of Shenzhen"],"affiliations":[{"raw_affiliation_string":"Baoan Central Hospital of Shenzhen","institution_ids":["https://openalex.org/I4210127213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129671804"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25149254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"15","first_page":"12681","last_page":"12689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7778000235557556,"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":0.7778000235557556,"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":0.08389999717473984,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04839999973773956,"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/pooling","display_name":"Pooling","score":0.722100019454956},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.6347000002861023},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5121999979019165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47440001368522644},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4361000061035156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249000072479248},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.722100019454956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6782000064849854},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.6347000002861023},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5121999979019165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41519999504089355},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40689998865127563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3522000014781952},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C3018302497","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Image contrast","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i15.38264","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38264","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38264/42226","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.v40i15.38264","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38264","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38264/42226","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":0.6397366523742676,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137982819.pdf","grobid_xml":"https://content.openalex.org/works/W7137982819.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"vision-language":[1],"pre-training":[2],"(VLP)":[3],"offers":[4],"significant":[5],"potential":[6],"for":[7],"advancing":[8],"medical":[9,110],"image":[10,120],"understanding":[11],"by":[12,22,27,85],"leveraging":[13],"paired":[14],"image-report":[15],"data.":[16],"However,":[17],"existing":[18],"methods":[19],"are":[20],"limited":[21],"False":[23],"Negatives":[24],"(FaNe)":[25],"induced":[26],"semantically":[28,102],"similar":[29,103],"texts":[30],"and":[31,124],"insufficient":[32],"fine-grained":[33,77],"cross-modal":[34],"alignment.":[35],"To":[36,47,88],"address":[37],"these":[38],"limitations,":[39],"we":[40,51,67,92],"propose":[41],"FaNe,":[42],"a":[43,53,69,94],"semantic-enhanced":[44],"VLP":[45],"framework.":[46,132],"mitigate":[48],"false":[49],"negatives,":[50],"introduce":[52],"semantic-aware":[54],"positive":[55],"pair":[56],"mining":[57],"strategy":[58],"based":[59],"on":[60,107],"text-text":[61],"similarity":[62],"with":[63],"adaptive":[64],"normalization.":[65],"Furthermore,":[66],"design":[68],"text-conditioned":[70],"sparse":[71],"attention":[72],"pooling":[73],"module":[74],"to":[75],"enable":[76],"image-text":[78],"alignment":[79],"through":[80],"localized":[81],"visual":[82],"representations":[83],"guided":[84],"textual":[86],"cues.":[87],"strengthen":[89],"intra-modal":[90],"discrimination,":[91],"develop":[93],"hard-negative":[95],"aware":[96],"contrastive":[97],"loss":[98],"that":[99,114],"adaptively":[100],"reweights":[101],"negatives.":[104],"Extensive":[105],"experiments":[106],"five":[108],"downstream":[109],"imaging":[111],"benchmarks":[112],"demonstrate":[113],"FaNe":[115],"achieves":[116],"state-of-the-art":[117],"performance":[118],"across":[119],"classification,":[121],"object":[122],"detection,":[123],"semantic":[125],"segmentation,":[126],"validating":[127],"the":[128],"effectiveness":[129],"of":[130],"our":[131]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}