{"id":"https://openalex.org/W4389665280","doi":"https://doi.org/10.1109/tpami.2023.3339661","title":"X2-VLM: All-in-One Pre-Trained Model for Vision-Language Tasks","display_name":"X2-VLM: All-in-One Pre-Trained Model for Vision-Language Tasks","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4389665280","doi":"https://doi.org/10.1109/tpami.2023.3339661","pmid":"https://pubmed.ncbi.nlm.nih.gov/38090826"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3339661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3339661","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045428404","display_name":"Yan Zeng","orcid":"https://orcid.org/0000-0003-1872-7534"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zeng","raw_affiliation_strings":["ByteDance Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1872-7534","affiliations":[{"raw_affiliation_string":"ByteDance Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101869403","display_name":"Xinsong Zhang","orcid":"https://orcid.org/0000-0001-9173-7400"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinsong Zhang","raw_affiliation_strings":["ByteDance Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9173-7400","affiliations":[{"raw_affiliation_string":"ByteDance Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011508837","display_name":"Hang Li","orcid":"https://orcid.org/0000-0001-9628-3487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["ByteDance Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9628-3487","affiliations":[{"raw_affiliation_string":"ByteDance Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032557170","display_name":"Jiawei Wang","orcid":"https://orcid.org/0000-0002-0606-5214"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Wang","raw_affiliation_strings":["ByteDance Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0606-5214","affiliations":[{"raw_affiliation_string":"ByteDance Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622779","display_name":"Jipeng Zhang","orcid":"https://orcid.org/0000-0002-3269-6992"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jipeng Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3269-6992","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074508950","display_name":"Wangchunshu Zhou","orcid":"https://orcid.org/0000-0003-4668-3348"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Wangchunshu Zhou","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4668-3348","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0795,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97765664,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"46","issue":"5","first_page":"3156","last_page":"3168"},"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":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.9768000245094299,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7816147804260254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.631501317024231},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6214208602905273},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5664830207824707},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5609475374221802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5206212997436523},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4831487536430359},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33831727504730225},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3285656273365021},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14170321822166443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816147804260254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.631501317024231},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6214208602905273},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5664830207824707},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5609475374221802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5206212997436523},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4831487536430359},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33831727504730225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3285656273365021},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14170321822166443},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2023.3339661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3339661","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:38090826","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38090826","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:repository.hkust.edu.hk:1783.1-135017","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-135017","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":100,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2425121537","https://openalex.org/W2489434015","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2765716052","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2962766617","https://openalex.org/W2963518342","https://openalex.org/W2963527096","https://openalex.org/W2963530300","https://openalex.org/W2963778889","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2983943451","https://openalex.org/W2984008963","https://openalex.org/W3014611590","https://openalex.org/W3035390927","https://openalex.org/W3035497460","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3126721948","https://openalex.org/W3133825286","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3168640669","https://openalex.org/W3173220247","https://openalex.org/W3174010726","https://openalex.org/W3175961224","https://openalex.org/W3176641147","https://openalex.org/W3176740717","https://openalex.org/W3176824248","https://openalex.org/W3177654849","https://openalex.org/W3193402170","https://openalex.org/W3200411758","https://openalex.org/W3204588463","https://openalex.org/W3208314443","https://openalex.org/W3212456749","https://openalex.org/W3213148312","https://openalex.org/W3217059257","https://openalex.org/W4221151248","https://openalex.org/W4223578995","https://openalex.org/W4226182655","https://openalex.org/W4229042118","https://openalex.org/W4281623693","https://openalex.org/W4283066680","https://openalex.org/W4288083516","https://openalex.org/W4295990387","https://openalex.org/W4296151206","https://openalex.org/W4301914798","https://openalex.org/W4306820534","https://openalex.org/W4307079201","https://openalex.org/W4312261477","https://openalex.org/W4312784228","https://openalex.org/W4313186260","https://openalex.org/W4385245566","https://openalex.org/W4385569837","https://openalex.org/W4385571308","https://openalex.org/W4386071687","https://openalex.org/W4386076661","https://openalex.org/W4386076683","https://openalex.org/W6620707391","https://openalex.org/W6639432524","https://openalex.org/W6676497082","https://openalex.org/W6762122294","https://openalex.org/W6766904570","https://openalex.org/W6767279747","https://openalex.org/W6775188310","https://openalex.org/W6779473860","https://openalex.org/W6789753369","https://openalex.org/W6790904380","https://openalex.org/W6791353385","https://openalex.org/W6797109355","https://openalex.org/W6798805250","https://openalex.org/W6800139874","https://openalex.org/W6803316292","https://openalex.org/W6803953248","https://openalex.org/W6804095316","https://openalex.org/W6805349323","https://openalex.org/W6809616361","https://openalex.org/W6810090734","https://openalex.org/W6811013733","https://openalex.org/W6811072154","https://openalex.org/W6838434436","https://openalex.org/W6838580846","https://openalex.org/W6839015040","https://openalex.org/W6843018836","https://openalex.org/W6843263998","https://openalex.org/W6845452229","https://openalex.org/W6846007759","https://openalex.org/W6847076894"],"related_works":["https://openalex.org/W2378076731","https://openalex.org/W4390516098","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2088988140","https://openalex.org/W2103019253","https://openalex.org/W2142795561","https://openalex.org/W2951529875"],"abstract_inverted_index":{"Vision":[0],"language":[1,10,33,48,151],"pre-training":[2,53,83,86],"aims":[3],"to":[4,30,44,93,146],"learn":[5,21,45,94],"alignments":[6,34,49],"between":[7,126],"vision":[8,32,47],"and":[9,59,84,113,119,128,177],"from":[11],"a":[12,51,73,123],"large":[13,114],"amount":[14],"of":[15,138],"data.":[16],"Most":[17],"existing":[18],"methods":[19],"only":[20],"image-text":[22,82,118],"alignments.":[23],"Some":[24],"others":[25],"utilize":[26],"pre-trained":[27,169,178],"object":[28,37],"detectors":[29],"leverage":[31],"at":[35,182],"the":[36,109,135,159],"level.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,66,79,132],"propose":[43],"multi-grained":[46,57,60],"by":[50,156],"unified":[52],"framework":[54],"that":[55,106,134],"learns":[56],"aligning":[58],"localization":[61],"simultaneously.":[62],"Based":[63],"on":[64,111],"it,":[65],"present":[67],"X2-VLM,":[68],"an":[69],"all-in-one":[70],"model":[71,129],"with":[72,99,162],"flexible":[74],"modular":[75,136],"architecture,":[76],"in":[77,87,141,149],"which":[78],"further":[80],"unify":[81],"video-text":[85,120],"one":[88],"model.":[89],"X2-VLM":[90,107,139,164],"is":[91],"able":[92],"unlimited":[95],"visual":[96],"concepts":[97],"associated":[98],"diverse":[100],"text":[101,160],"descriptions.":[102],"Experiment":[103],"results":[104,140],"show":[105,133],"performs":[108],"best":[110],"base":[112],"scale":[115],"for":[116,144],"both":[117],"tasks,":[121],"making":[122],"good":[124],"trade-off":[125],"performance":[127],"scale.":[130],"Moreover,":[131],"design":[137],"high":[142],"transferability":[143],"it":[145],"be":[147],"utilized":[148],"any":[150,172],"or":[152],"domain.":[153],"For":[154],"example,":[155],"simply":[157],"replacing":[158],"encoder":[161],"XLM-R,":[163],"outperforms":[165],"state-of-the-art":[166],"multilingual":[167,173],"multi-modal":[168],"models":[170,179],"without":[171],"pre-training.":[174],"The":[175],"code":[176],"are":[180],"available":[181],"<uri":[183],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/zengyan-97/X2-VLM</uri>":[185],".":[186]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2023-12-14T00:00:00"}