{"id":"https://openalex.org/W3205618423","doi":"https://doi.org/10.1145/3474085.3475191","title":"M3TR: Multi-modal Multi-label Recognition with Transformer","display_name":"M3TR: Multi-modal Multi-label Recognition with Transformer","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205618423","doi":"https://doi.org/10.1145/3474085.3475191","mag":"3205618423"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475191","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5103002792","display_name":"Jiawei Zhao","orcid":"https://orcid.org/0000-0002-9513-6108"},"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":"Jiawei Zhao","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063066022","display_name":"Yifan Zhao","orcid":"https://orcid.org/0000-0002-5691-013X"},"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":"Yifan Zhao","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684702","display_name":"Li Jia","orcid":"https://orcid.org/0000-0002-5566-9209"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"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":"Jia Li","raw_affiliation_strings":["Beihang University & Peng Cheng Laboratory, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University & Peng Cheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"469","last_page":"477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"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":0.7489840984344482},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5502890348434448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.546678364276886},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5360949635505676},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5354245901107788},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5126494765281677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489840984344482},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5502890348434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.546678364276886},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5360949635505676},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5354245901107788},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5126494765281677},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475191","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4309793126","display_name":null,"funder_award_id":"61922006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1567302070","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1962468782","https://openalex.org/W2031489346","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2410641892","https://openalex.org/W2518918709","https://openalex.org/W2521365688","https://openalex.org/W2549365021","https://openalex.org/W2560096627","https://openalex.org/W2738853914","https://openalex.org/W2899771611","https://openalex.org/W2932399282","https://openalex.org/W2957702778","https://openalex.org/W2963300078","https://openalex.org/W2963306618","https://openalex.org/W2963403868","https://openalex.org/W2963676620","https://openalex.org/W2963697527","https://openalex.org/W2963745697","https://openalex.org/W2963875806","https://openalex.org/W2982112268","https://openalex.org/W2986821660","https://openalex.org/W2995888011","https://openalex.org/W2997136715","https://openalex.org/W2998420437","https://openalex.org/W3034564678","https://openalex.org/W3035665101","https://openalex.org/W3096609285","https://openalex.org/W3099518117","https://openalex.org/W3109067582","https://openalex.org/W3170841864","https://openalex.org/W3174336354","https://openalex.org/W3174396085","https://openalex.org/W6600704668"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W4306353150","https://openalex.org/W2026860389","https://openalex.org/W8219677","https://openalex.org/W3216879894","https://openalex.org/W2890132085","https://openalex.org/W4301143707","https://openalex.org/W2952745240","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multi-label":[0,73],"image":[1],"recognition":[2,74,172],"aims":[3],"to":[4,14,26,125,144],"recognize":[5],"multiple":[6],"objects":[7],"simultaneously":[8],"in":[9,47],"one":[10],"image.":[11],"Recent":[12],"ideas":[13],"solve":[15],"this":[16],"problem":[17],"have":[18],"focused":[19],"on":[20,168],"learning":[21,81,106,158],"dependencies":[22],"of":[23,40,56,93,148,159],"label":[24],"co-occurrences":[25],"enhance":[27,145],"the":[28,37,53,71,78,86,102,107,112,115,127,132,146,156],"high-level":[29,103,149],"semantic":[30,108],"representations.":[31],"However,":[32],"these":[33],"methods":[34],"usually":[35],"neglect":[36],"important":[38],"relations":[39],"intrinsic":[41],"visual":[42,57,64,99,116,133],"structures":[43,100],"and":[44,66,95,117,136],"face":[45],"difficulties":[46],"understanding":[48],"contextual":[49],"relationships.":[50],"To":[51],"build":[52],"global":[54],"scope":[55],"context":[58],"as":[59,61],"well":[60],"interactions":[62,113],"between":[63,114],"modality":[65],"linguistic":[67,118,123,129,140],"modality,":[68],"we":[69,89,120],"propose":[70,121],"Multi-Modal":[72],"TRansformers":[75],"(M3TR)":[76],"with":[77,155],"ternary":[79,160],"relationship":[80],"for":[82],"inter-and":[83],"intra-modalities.":[84],"For":[85,110],"intra-modal":[87],"relationship,":[88,161],"make":[90],"insightful":[91],"conjunction":[92],"CNNs":[94],"Transformers,":[96],"which":[97],"embeds":[98],"into":[101,131],"features":[104],"by":[105],"cross-attention.":[109],"constructing":[111],"modalities,":[119],"a":[122,139],"cross-attention":[124],"embed":[126],"class-wise":[128],"information":[130],"structure":[134],"learning,":[135],"finally":[137],"present":[138],"guided":[141],"enhancement":[142],"module":[143],"representation":[147],"semantics.":[150],"Experimental":[151],"evidence":[152],"reveals":[153],"that":[154],"collaborative":[157],"our":[162],"proposed":[163],"M3TR":[164],"achieves":[165],"new":[166],"state-of-the-art":[167],"two":[169],"public":[170],"multi-label":[171],"benchmarks.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}