{"id":"https://openalex.org/W4293519460","doi":"https://doi.org/10.1109/icme52920.2022.9859777","title":"Multimodal Crowd Counting with Mutual Attention Transformers","display_name":"Multimodal Crowd Counting with Mutual Attention Transformers","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293519460","doi":"https://doi.org/10.1109/icme52920.2022.9859777"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859777","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","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/A5003956776","display_name":"Zhengtao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengtao Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,China","School of Computer Science and Engineering, Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102971183","display_name":"Lingbo Liu","orcid":"https://orcid.org/0000-0001-8179-6685"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lingbo Liu","raw_affiliation_strings":["Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731922","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0001-7123-5315"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,China","School of Computer Science and Engineering, Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057897875","display_name":"Mingzhi Mao","orcid":"https://orcid.org/0000-0001-9369-7828"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhi Mao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,China","School of Computer Science and Engineering, Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,China","School of Computer Science and Engineering, Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042965510","display_name":"Guanbin Li","orcid":"https://orcid.org/0000-0002-4805-0926"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanbin Li","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,China","School of Computer Science and Engineering, Sun Yat-sen University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003956776"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.6751,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.89368346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","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/T10331","display_name":"Video Surveillance and Tracking Methods","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.998199999332428,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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":0.7517633438110352},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6567111611366272},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6502887606620789},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6401450037956238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6208752989768982},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5240471363067627},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4958387315273285},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47210660576820374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47146517038345337},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4364357888698578},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3849223256111145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3633459210395813},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09026756882667542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7517633438110352},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6567111611366272},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6502887606620789},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6401450037956238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208752989768982},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5240471363067627},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4958387315273285},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47210660576820374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47146517038345337},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4364357888698578},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3849223256111145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3633459210395813},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09026756882667542},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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:10.1109/icme52920.2022.9859777","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859777","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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 Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2952538351","display_name":null,"funder_award_id":"2020B1515020048","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G3625185452","display_name":null,"funder_award_id":"61976250,U1811463","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"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1203557841","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2463631526","https://openalex.org/W2808519136","https://openalex.org/W2886443245","https://openalex.org/W2949333977","https://openalex.org/W2955171701","https://openalex.org/W2963420272","https://openalex.org/W2964203052","https://openalex.org/W2964209782","https://openalex.org/W2965247173","https://openalex.org/W2982007926","https://openalex.org/W3004672782","https://openalex.org/W3030520226","https://openalex.org/W3032910121","https://openalex.org/W3035633116","https://openalex.org/W3094502228","https://openalex.org/W3095336680","https://openalex.org/W3097053213","https://openalex.org/W3108822985","https://openalex.org/W3143320354","https://openalex.org/W3171516518","https://openalex.org/W3177211876","https://openalex.org/W3210983250","https://openalex.org/W4214561053","https://openalex.org/W4226141461","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6739901393","https://openalex.org/W6748343077","https://openalex.org/W6754034799","https://openalex.org/W6766530877","https://openalex.org/W6775668102","https://openalex.org/W6778485988","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6786708909"],"related_works":["https://openalex.org/W2004195487","https://openalex.org/W2003125512","https://openalex.org/W4313488044","https://openalex.org/W1996541855","https://openalex.org/W1987859285","https://openalex.org/W3195168932","https://openalex.org/W2543725295","https://openalex.org/W4287995534","https://openalex.org/W2897195263","https://openalex.org/W2998168123"],"abstract_inverted_index":{"Crowd":[0],"counting":[1],"is":[2,133],"a":[3,55,74,109],"fundamental":[4],"yet":[5],"challenging":[6],"task":[7],"that":[8,129],"aims":[9],"to":[10,41,61,79,86,94],"automatically":[11],"estimate":[12],"the":[13,22,47,64,81,88,91,130],"number":[14],"of":[15,25,49,67,83,90],"people":[16],"in":[17,45],"crowded":[18],"scenes.":[19],"Nowadays,":[20],"with":[21],"rapid":[23],"development":[24],"thermal":[26,30],"and":[27,32,102,126,135],"depth":[28,33],"sensors,":[29],"images":[31],"maps":[34],"become":[35],"more":[36],"accessible,":[37],"which":[38],"are":[39],"proven":[40],"be":[42],"beneficial":[43],"information":[44,66],"boosting":[46],"performance":[48,96],"crowd":[50,139],"counting.":[51],"Consequently,":[52],"we":[53,107],"propose":[54],"Mutual":[56],"Attention":[57],"Transformer":[58],"(MAT)":[59],"module":[60],"fully":[62],"leverage":[63],"complementary":[65],"different":[68],"modalities.":[69],"Specifically,":[70],"our":[71],"MAT":[72],"employs":[73],"cross-modal":[75,115],"mutual":[76],"attention":[77],"mechanism":[78],"utilize":[80],"features":[82,89],"one":[84],"modality":[85],"enhance":[87],"other.":[92],"Moreover,":[93],"improve":[95],"by":[97],"learning":[98],"better":[99],"visual":[100],"representation":[101],"further":[103],"exploiting":[104],"modality-wise":[105],"comple-mentarity,":[106],"design":[108],"self-supervised":[110],"pre-training":[111],"method":[112,132],"based":[113],"on":[114,120],"image":[116],"reconstruction.":[117],"Extensive":[118],"experiments":[119],"two":[121],"standard":[122],"benchmarks":[123],"(i.e.,":[124],"RGBT-CC":[125],"ShanghaiTechRGBD)":[127],"show":[128],"proposed":[131],"effective":[134],"universal":[136],"for":[137],"multimodal":[138],"counting,":[140],"outper-forming":[141],"previous":[142],"state-of-the-art":[143],"methods.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}