{"id":"https://openalex.org/W4400526093","doi":"https://doi.org/10.1109/tpami.2024.3425768","title":"TCFormer: Visual Recognition via Token Clustering Transformer","display_name":"TCFormer: Visual Recognition via Token Clustering Transformer","publication_year":2024,"publication_date":"2024-07-11","ids":{"openalex":"https://openalex.org/W4400526093","doi":"https://doi.org/10.1109/tpami.2024.3425768","pmid":"https://pubmed.ncbi.nlm.nih.gov/38990751"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3425768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3425768","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hub.hku.hk/handle/10722/348565","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038497162","display_name":"Wang Zeng","orcid":"https://orcid.org/0000-0003-1562-6332"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wang Zeng","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960326","display_name":"Sheng Jin","orcid":"https://orcid.org/0000-0001-5736-7434"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sheng Jin","raw_affiliation_strings":["University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032828647","display_name":"Lumin Xu","orcid":"https://orcid.org/0000-0003-2125-2760"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lumin Xu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451376","display_name":"Wentao Liu","orcid":"https://orcid.org/0000-0001-6587-9878"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Liu","raw_affiliation_strings":["SenseTime Research, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shatin, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657544","display_name":"Chen Qian","orcid":"https://orcid.org/0000-0002-8761-5563"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Qian","raw_affiliation_strings":["SenseTime Research, Shatin, Hong Kong"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shatin, Hong Kong","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wanli Ouyang","raw_affiliation_strings":["University of Sydney, Camperdown, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752686","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6685-7950"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040565849","display_name":"Xiaogang Wang","orcid":"https://orcid.org/0000-0002-8402-7504"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaogang Wang","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5038497162"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":4.051,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94352818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"46","issue":"12","first_page":"9521","last_page":"9535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.8787999749183655,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.8787999749183655,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.8626000285148621,"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/T13579","display_name":"Image and Video Stabilization","score":0.8410999774932861,"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":0.7281378507614136},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.65067058801651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6446317434310913},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6337437033653259},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5099591016769409},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.47122514247894287},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46637704968452454},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4564017355442047},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.412389874458313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3327970504760742},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13511589169502258},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08931535482406616},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08486735820770264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281378507614136},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.65067058801651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6446317434310913},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6337437033653259},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5099591016769409},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.47122514247894287},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46637704968452454},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4564017355442047},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.412389874458313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3327970504760742},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13511589169502258},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08931535482406616},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08486735820770264},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2024.3425768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3425768","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38990751","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38990751","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:hub.hku.hk:10722/348565","is_oa":true,"landing_page_url":"https://hub.hku.hk/handle/10722/348565","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:hub.hku.hk:10722/348565","is_oa":true,"landing_page_url":"https://hub.hku.hk/handle/10722/348565","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2113325037","https://openalex.org/W2117539524","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2268194897","https://openalex.org/W2307770531","https://openalex.org/W2549139847","https://openalex.org/W2559085405","https://openalex.org/W2565639579","https://openalex.org/W2578797046","https://openalex.org/W2737258237","https://openalex.org/W2910628332","https://openalex.org/W2916798096","https://openalex.org/W2962730651","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963402313","https://openalex.org/W2963598138","https://openalex.org/W2964221239","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3034399482","https://openalex.org/W3034429256","https://openalex.org/W3096609285","https://openalex.org/W3108572544","https://openalex.org/W3109769043","https://openalex.org/W3110017807","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3175515048","https://openalex.org/W3176892444","https://openalex.org/W3188427387","https://openalex.org/W3203020760","https://openalex.org/W3203925315","https://openalex.org/W4214493665","https://openalex.org/W4214508443","https://openalex.org/W4214634256","https://openalex.org/W4214709605","https://openalex.org/W4214713996","https://openalex.org/W4214893857","https://openalex.org/W4221146106","https://openalex.org/W4224992933","https://openalex.org/W4229890965","https://openalex.org/W4246193833","https://openalex.org/W4280496682","https://openalex.org/W4288325606","https://openalex.org/W4290715204","https://openalex.org/W4306886919","https://openalex.org/W4312290555","https://openalex.org/W4312530435","https://openalex.org/W4312815172","https://openalex.org/W4312820606","https://openalex.org/W4313156423","https://openalex.org/W4320167334","https://openalex.org/W4385656546","https://openalex.org/W4389666313","https://openalex.org/W6631190155","https://openalex.org/W6726497184","https://openalex.org/W6730410022","https://openalex.org/W6745136726","https://openalex.org/W6757817989","https://openalex.org/W6760424586","https://openalex.org/W6764322716","https://openalex.org/W6768970301","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6794345597","https://openalex.org/W6796494063","https://openalex.org/W6797399245","https://openalex.org/W6802996638","https://openalex.org/W6803650990","https://openalex.org/W6809664228","https://openalex.org/W6809665764","https://openalex.org/W6838393215","https://openalex.org/W6838697126","https://openalex.org/W6845607375","https://openalex.org/W6846577953","https://openalex.org/W6848935878"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4387768015","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Transformers":[0],"are":[1,90],"widely":[2],"used":[3],"in":[4,43],"computer":[5],"vision":[6,28,60,84],"areas":[7],"and":[8,21,93,101,121],"have":[9],"achieved":[10],"remarkable":[11],"success.":[12],"Most":[13],"state-of-the-art":[14],"approaches":[15],"split":[16],"images":[17],"into":[18],"regular":[19],"grids":[20],"represent":[22,102],"each":[23],"grid":[24],"region":[25],"with":[26,77,98],"a":[27],"token.":[29],"However,":[30],"fixed":[31],"token":[32],"distribution":[33],"disregards":[34],"the":[35,52,82,126],"semantic":[36,64,79,119],"meaning":[37],"of":[38,128],"different":[39],"image":[40,75,114],"regions,":[41],"resulting":[42],"sub-optimal":[44],"performance.":[45],"To":[46],"address":[47],"this":[48],"issue,":[49],"we":[50,124],"propose":[51],"Token":[53],"Clustering":[54],"Transformer":[55],"(TCFormer),":[56],"which":[57],"generates":[58],"dynamic":[59,67],"tokens":[61,68],"based":[62],"on":[63,96],"meaning.":[65],"Our":[66],"possess":[69],"two":[70],"crucial":[71],"characteristics:":[72],"(1)":[73],"Representing":[74],"regions":[76,89,97],"similar":[78],"meanings":[80],"using":[81,104],"same":[83],"token,":[85],"even":[86],"if":[87],"those":[88],"not":[91],"adjacent,":[92],"(2)":[94],"concentrating":[95],"valuable":[99],"details":[100],"them":[103],"fine":[105],"tokens.":[106],"Through":[107],"extensive":[108],"experimentation":[109],"across":[110],"various":[111],"applications,":[112],"including":[113],"classification,":[115],"human":[116],"pose":[117],"estimation,":[118],"segmentation,":[120],"object":[122],"detection,":[123],"demonstrate":[125],"effectiveness":[127],"our":[129],"TCFormer.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}