{"id":"https://openalex.org/W4390479148","doi":"https://doi.org/10.1145/3595916.3626437","title":"Generic Attention-model Explainability by Weighted Relevance Accumulation","display_name":"Generic Attention-model Explainability by Weighted Relevance Accumulation","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390479148","doi":"https://doi.org/10.1145/3595916.3626437"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626437","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626437","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626437","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626437","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045034384","display_name":"Yiming Huang","orcid":"https://orcid.org/0000-0002-6888-9622"},"institutions":[{"id":"https://openalex.org/I139221136","display_name":"Centro Universit\u00e1rio FEI","ror":"https://ror.org/007kf5222","country_code":"BR","type":"education","lineage":["https://openalex.org/I139221136"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["BR","CN"],"is_corresponding":true,"raw_author_name":"Yiming Huang","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, CN"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, CN","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I139221136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101451380","display_name":"Aozhe Jia","orcid":"https://orcid.org/0009-0004-9019-4087"},"institutions":[{"id":"https://openalex.org/I139221136","display_name":"Centro Universit\u00e1rio FEI","ror":"https://ror.org/007kf5222","country_code":"BR","type":"education","lineage":["https://openalex.org/I139221136"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["BR","CN"],"is_corresponding":false,"raw_author_name":"Aozhe Jia","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, CN"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, CN","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I139221136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356742","display_name":"Xiaodan Zhang","orcid":"https://orcid.org/0000-0001-7002-5447"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]},{"id":"https://openalex.org/I139221136","display_name":"Centro Universit\u00e1rio FEI","ror":"https://ror.org/007kf5222","country_code":"BR","type":"education","lineage":["https://openalex.org/I139221136"]}],"countries":["BR","CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhang","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, CN"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, CN","institution_ids":["https://openalex.org/I37796252","https://openalex.org/I139221136"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100462825","display_name":"Jiawei Zhang","orcid":"https://orcid.org/0000-0002-2292-4592"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Zhang","raw_affiliation_strings":["Sensetime Research, CN"],"affiliations":[{"raw_affiliation_string":"Sensetime Research, CN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045034384"],"corresponding_institution_ids":["https://openalex.org/I139221136","https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.4913,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66966215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9947999715805054,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.8096685409545898},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.8078609704971313},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6656765341758728},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6376500129699707},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5602949261665344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5194270610809326},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5033013224601746},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4677337110042572},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42125487327575684},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4187540113925934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38210564851760864},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22839421033859253},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08431750535964966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8096685409545898},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8078609704971313},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6656765341758728},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6376500129699707},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5602949261665344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194270610809326},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5033013224601746},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4677337110042572},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42125487327575684},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4187540113925934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38210564851760864},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22839421033859253},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08431750535964966},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626437","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626437","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626437","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626437","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626437","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626437","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390479148.pdf","grobid_xml":"https://content.openalex.org/works/W4390479148.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2282821441","https://openalex.org/W2481240925","https://openalex.org/W2745461083","https://openalex.org/W2883409523","https://openalex.org/W2946794439","https://openalex.org/W2962858109","https://openalex.org/W2963609017","https://openalex.org/W2964345214","https://openalex.org/W2970726176","https://openalex.org/W3016211260","https://openalex.org/W3035422918","https://openalex.org/W3091588028","https://openalex.org/W3153469116","https://openalex.org/W3176196997","https://openalex.org/W3197394194","https://openalex.org/W3199057778","https://openalex.org/W3201264086","https://openalex.org/W4225323055","https://openalex.org/W4225592884","https://openalex.org/W4225683910","https://openalex.org/W4225832925","https://openalex.org/W4229042118","https://openalex.org/W4230405732","https://openalex.org/W4285191490","https://openalex.org/W4288096733"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Attention-based":[0],"Transformer":[1],"models":[2],"have":[3],"achieved":[4],"remarkable":[5],"progress":[6],"in":[7],"multi-modal":[8],"tasks,":[9],"such":[10],"as":[11,25],"visual":[12,142],"question":[13,143],"answering.":[14],"The":[15],"explainability":[16,136,152],"of":[17,32,61,82,120],"attention-based":[18],"methods":[19,42],"has":[20],"recently":[21],"attracted":[22],"wide":[23],"interest":[24],"it":[26,128],"can":[27],"explain":[28],"the":[29,49,55,59,80],"inner":[30],"changes":[31],"attention":[33,39,56],"tokens":[34],"by":[35,46],"accumulating":[36,48,92],"relevancy":[37,45,51,76],"across":[38],"layers.":[40],"Current":[41],"simply":[43],"update":[44],"equally":[47,91],"token":[50,62,83],"before":[52],"and":[53,114,124,145],"after":[54],"processes.":[57],"However,":[58],"importance":[60,81],"values":[63,84],"is":[64,129],"usually":[65],"different":[66],"during":[67],"relevance":[68],"accumulation.In":[69],"this":[70],"paper,":[71],"we":[72,98],"propose":[73,99],"a":[74,100,115],"weighted":[75],"strategy,":[77],"which":[78],"takes":[79],"into":[85],"consideration,":[86],"to":[87,107],"reduce":[88],"distortion":[89],"when":[90],"relevance.":[93],"To":[94],"evaluate":[95],"our":[96,134,151],"method,":[97],"unified":[101],"CLIP-based":[102],"two-stage":[103],"model,":[104],"named":[105],"CLIPmapper,":[106],"process":[108],"Vision-and-Language":[109],"tasks":[110,148],"through":[111],"CLIP":[112],"encoder":[113],"following":[116],"mapper.":[117],"CLIPmapper":[118],"consists":[119],"self-attention,":[121],"cross-attention,":[122],"single-modality,":[123],"cross-modality":[125],"attention,":[126],"thus":[127],"more":[130],"suitable":[131],"for":[132],"evaluating":[133],"generic":[135],"method.":[137],"Extensive":[138],"perturbation":[139],"tests":[140],"on":[141],"answering":[144],"image":[146],"captioning":[147],"validate":[149],"that":[150],"method":[153],"outperforms":[154],"existing":[155],"methods.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}