{"id":"https://openalex.org/W4409366451","doi":"https://doi.org/10.1609/aaai.v39i8.32888","title":"TdAttenMix: Top-Down Attention Guided Mixup","display_name":"TdAttenMix: Top-Down Attention Guided Mixup","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409366451","doi":"https://doi.org/10.1609/aaai.v39i8.32888"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i8.32888","doi":"https://doi.org/10.1609/aaai.v39i8.32888","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i8.32888","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32888/35043","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,"listed_in":["jufo-2","norway-1"],"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"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32888/35043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101919187","display_name":"Zhiming Wang","orcid":"https://orcid.org/0009-0008-7832-1484","observed_orcids":["https://orcid.org/0009-0008-7832-1484"]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiming Wang","raw_affiliation_strings":["State Key Laboratory of VR Technology and Systems, School of CSE, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of VR Technology and Systems, School of CSE, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053647594","display_name":"Lin Gu","orcid":"https://orcid.org/0000-0002-7419-6240","observed_orcids":["https://orcid.org/0000-0002-7419-6240"]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lin Gu","raw_affiliation_strings":["RIKEN AIP\nThe University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN AIP\nThe University of Tokyo, Japan","institution_ids":["https://openalex.org/I4210110652","https://openalex.org/I4210126580","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101480749","display_name":"Feng Lu","orcid":"https://orcid.org/0000-0001-6573-2550","observed_orcids":["https://orcid.org/0000-0001-6573-2550","https://orcid.org/0009-0002-3907-9812"]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lu","raw_affiliation_strings":["State Key Laboratory of VR Technology and Systems, School of CSE, Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of VR Technology and Systems, School of CSE, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7983,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69025549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"39","issue":"8","first_page":"8232","last_page":"8240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6923999786376953,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6923999786376953,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.14249999821186066,"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":0.07289999723434448,"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/mixup","display_name":"mixup","score":0.7269999980926514},{"id":"https://openalex.org/keywords/cutmix","display_name":"CutMix","score":0.8650000095367432},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/top-down-attention","display_name":"top-down attention","score":0.8460000157356262},{"id":"https://openalex.org/keywords/human-gaze","display_name":"human gaze","score":0.8109999895095825},{"id":"https://openalex.org/keywords/patch-choice","display_name":"patch selection","score":0.5820000171661377},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-attention","display_name":"top-down and bottom-up attention","score":0.7699999809265137}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38954585790634155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36995041370391846},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3402920365333557}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v39i8.32888","doi":"https://doi.org/10.1609/aaai.v39i8.32888","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i8.32888","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32888/35043","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,"listed_in":["jufo-2","norway-1"],"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"},{"id":"pmh:oai:arXiv.org:2501.15409","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.15409","pdf_url":"https://arxiv.org/pdf/2501.15409","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/32888","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/32888","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2501.15409","doi":"https://doi.org/10.48550/arxiv.2501.15409","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.15409","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i8.32888","doi":"https://doi.org/10.1609/aaai.v39i8.32888","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i8.32888","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32888/35043","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,"listed_in":["jufo-2","norway-1"],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G556986091","display_name":null,"funder_award_id":"JP-MJMS2011","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409366451.pdf","grobid_xml":"https://content.openalex.org/works/W4409366451.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"CutMix":[0],"is":[1,52],"a":[2,63,71,121],"data":[3],"augmentation":[4],"strategy":[5],"that":[6,94,106],"cuts":[7],"and":[8,58,78,88,129],"pastes":[9],"image":[10],"patches":[11,87],"to":[12,28,42,69,99,133],"mixup":[13,112],"training":[14,33],"data.":[15],"Existing":[16],"methods":[17,113],"pick":[18],"either":[19],"random":[20],"or":[21],"salient":[22],"areas":[23],"which":[24,75],"are":[25],"often":[26],"inconsistent":[27],"labels,":[29],"thus":[30],"misguiding":[31],"the":[32,46,86,90,100,126,135],"model.":[34],"By":[35],"our":[36,107],"knowledge,":[37],"we":[38,61,119],"integrate":[39],"human":[40,50,127],"gaze":[41,128],"guide":[43],"cutmix":[44],"for":[45],"first":[47],"time.":[48],"Since":[49],"attention":[51,74],"driven":[53],"by":[54],"both":[55],"high-level":[56],"recognition":[57],"low-level":[59],"clues,":[60],"propose":[62],"controllable":[64],"Top-down":[65],"Attention":[66],"Guided":[67],"Module":[68],"obtain":[70],"general":[72],"artificial":[73],"balances":[76],"top-down":[77],"bottom-up":[79],"attention.":[80],"The":[81],"proposed":[82],"TdATttenMix":[83],"then":[84],"picks":[85],"adjust":[89],"label":[91],"mixing":[92],"ratio":[93],"focuses":[95],"on":[96,125],"regions":[97],"relevant":[98],"current":[101],"label.":[102],"Experimental":[103],"results":[104],"demonstrate":[105],"TdAttenMix":[108],"outperforms":[109],"existing":[110],"state-of-the-art":[111],"across":[114],"eight":[115],"different":[116],"benchmarks.":[117],"Additionally,":[118],"introduce":[120],"new":[122],"metric":[123,132],"based":[124],"use":[130],"this":[131],"investigate":[134],"issue":[136],"of":[137],"image-label":[138],"inconsistency.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}