{"id":"https://openalex.org/W4308236449","doi":"https://doi.org/10.1109/icip46576.2022.9897323","title":"CMA-CLIP: Cross-Modality Attention Clip for Text-Image Classification","display_name":"CMA-CLIP: Cross-Modality Attention Clip for Text-Image Classification","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308236449","doi":"https://doi.org/10.1109/icip46576.2022.9897323"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897323","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070138894","display_name":"Jinmiao Fu","orcid":"https://orcid.org/0009-0002-2230-3662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinmiao Fu","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071261572","display_name":"Shaoyuan Xu","orcid":"https://orcid.org/0000-0003-3740-2276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoyuan Xu","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101717680","display_name":"Huidong Liu","orcid":"https://orcid.org/0000-0003-3833-9475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huidong Liu","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355762","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-9982-9887"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746427","display_name":"Ning Xie","orcid":"https://orcid.org/0000-0002-0116-1426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Xie","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013934000","display_name":"Chien-Chih Wang","orcid":"https://orcid.org/0000-0002-7869-3965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chien-Chih Wang","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411571","display_name":"Yi Sun","orcid":"https://orcid.org/0000-0002-7636-0200"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Sun","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101432451","display_name":"Bryan Wang","orcid":"https://orcid.org/0000-0001-9016-038X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Wang","raw_affiliation_strings":["Amazon Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2846","last_page":"2850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7710739374160767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.691322922706604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5893441438674927},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5245407223701477},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.445813924074173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3316957950592041}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7710739374160767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691322922706604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5893441438674927},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5245407223701477},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.445813924074173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3316957950592041}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897323","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W2808747415","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969876226","https://openalex.org/W2972119347","https://openalex.org/W3001555892","https://openalex.org/W3014611590","https://openalex.org/W3035060554","https://openalex.org/W3035485997","https://openalex.org/W3036224891","https://openalex.org/W3090449556","https://openalex.org/W3091546937","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3100859887","https://openalex.org/W3126337491","https://openalex.org/W3165938948","https://openalex.org/W3166396011","https://openalex.org/W3182683290","https://openalex.org/W3213100861","https://openalex.org/W4249477935","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6752422777","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6767908396","https://openalex.org/W6773248631","https://openalex.org/W6775188310","https://openalex.org/W6779326418","https://openalex.org/W6779977557","https://openalex.org/W6779997284","https://openalex.org/W6784185929","https://openalex.org/W6784333009","https://openalex.org/W6790019176","https://openalex.org/W6791353385"],"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":{"Multi-modal":[0],"learning":[1],"with":[2,42,124],"both":[3],"text":[4,77],"and":[5,47,65,78,120],"images":[6],"benefits":[7],"multiple":[8],"applications,":[9],"such":[10],"as":[11],"attribute":[12,147],"extraction":[13],"for":[14,142],"e-commerce":[15],"products.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20],"propose":[21],"Cross-Modality":[22],"Attention":[23],"Contrastive":[24],"Language-Image":[25],"Pre-training":[26],"(CMA-CLIP),":[27],"a":[28,43,48,83],"new":[29],"multi-modal":[30],"architecture":[31],"to":[32,56,71,87,94],"jointly":[33],"learn":[34,88],"the":[35,58,62,67,73,89,98,106,125,143],"fine-grained":[36,74],"inter-modality":[37,59],"relationship.":[38],"It":[39],"fuses":[40],"CLIP":[41,55],"sequence-wise":[44,68],"attention":[45,50,69,85],"module":[46,70,86],"modality-wise":[49,84],"module.":[51],"The":[52],"network":[53,99],"uses":[54,66],"bridge":[57],"gap":[60],"at":[61],"global":[63],"level,":[64],"capture":[72],"alignment":[75],"between":[76],"images.":[79],"Besides,":[80],"it":[81],"leverages":[82],"relevance":[90],"of":[91,145],"each":[92],"modality":[93],"downstream":[95],"tasks,":[96],"making":[97],"robust":[100],"against":[101,135],"irrelevant":[102,136],"modalities.":[103],"CMA-CLIP":[104],"outperforms":[105],"state-of-the-art":[107,126],"method":[108,127],"on":[109,118,122,128,138],"Fashion-Gen":[110],"by":[111],"5.5%":[112],"in":[113],"accuracy,":[114],"achieves":[115],"competitive":[116],"performance":[117,121],"Food101":[119],"par":[123],"MM-IMDb.":[129],"We":[130],"also":[131],"demonstrate":[132],"CMA-CLIP\u2019s":[133],"robustness":[134],"modalities":[137],"an":[139],"Amazon":[140],"dataset":[141],"task":[144],"product":[146],"extraction.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}