{"id":"https://openalex.org/W4413050942","doi":"https://doi.org/10.1109/tpami.2025.3596776","title":"EMOv2: Pushing 5M Vision Model Frontier","display_name":"EMOv2: Pushing 5M Vision Model Frontier","publication_year":2025,"publication_date":"2025-08-07","ids":{"openalex":"https://openalex.org/W4413050942","doi":"https://doi.org/10.1109/tpami.2025.3596776","pmid":"https://pubmed.ncbi.nlm.nih.gov/40773393"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3596776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3596776","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/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8891-6766","affiliations":[{"raw_affiliation_string":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Teng Hu","orcid":"https://orcid.org/0009-0008-1247-5931"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Hu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-1247-5931","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyang He","orcid":"https://orcid.org/0009-0003-2771-5196"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang He","raw_affiliation_strings":["Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-2771-5196","affiliations":[{"raw_affiliation_string":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068890959","display_name":"Zhucun Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhucun Xue","raw_affiliation_strings":["Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2627-4397","affiliations":[{"raw_affiliation_string":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Youtu Lab, Tencent, Shenzhen, China","Youtu Lab, Tencent, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834700","display_name":"Chengjie Wang","orcid":"https://orcid.org/0000-0003-4216-8090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengjie Wang","raw_affiliation_strings":["Youtu Lab, Tencent, Shenzhen, China","Youtu Lab, Tencent, China"],"raw_orcid":"https://orcid.org/0000-0003-4216-8090","affiliations":[{"raw_affiliation_string":"Youtu Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Youtu Lab, Tencent, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4822-8939","affiliations":[{"raw_affiliation_string":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiangtai Li","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0550-8247","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0621,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.92117394,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"47","issue":"11","first_page":"10560","last_page":"10576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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/T10036","display_name":"Advanced Neural Network 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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9933000206947327,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9908000230789185,"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":0.8040479421615601},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.676519513130188},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.655514121055603},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5472890138626099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5017297267913818},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4663381278514862},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.432489812374115},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4222649931907654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3496355414390564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27546098828315735},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23906317353248596},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.13895732164382935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040479421615601},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.676519513130188},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.655514121055603},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5472890138626099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5017297267913818},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4663381278514862},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.432489812374115},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4222649931907654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3496355414390564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27546098828315735},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23906317353248596},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.13895732164382935},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2025.3596776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3596776","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:40773393","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40773393","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:dr.ntu.edu.sg:10356/218209","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/218209","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2129098176","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2331143823","https://openalex.org/W2507296351","https://openalex.org/W2560023338","https://openalex.org/W2883780447","https://openalex.org/W2910628332","https://openalex.org/W2928165649","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963351448","https://openalex.org/W2966926453","https://openalex.org/W2982083293","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3035414587","https://openalex.org/W3035682985","https://openalex.org/W3110440461","https://openalex.org/W3120129399","https://openalex.org/W3131500599","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3163465952","https://openalex.org/W3172801447","https://openalex.org/W3175515048","https://openalex.org/W3177349073","https://openalex.org/W3190492058","https://openalex.org/W4214493665","https://openalex.org/W4214634256","https://openalex.org/W4312349930","https://openalex.org/W4312443924","https://openalex.org/W4312820606","https://openalex.org/W4312977443","https://openalex.org/W4313007769","https://openalex.org/W4313170858","https://openalex.org/W4315705623","https://openalex.org/W4320036918","https://openalex.org/W4385245566","https://openalex.org/W4386047745","https://openalex.org/W4386076539","https://openalex.org/W4386497700","https://openalex.org/W4389524555","https://openalex.org/W4390872297","https://openalex.org/W4390872550","https://openalex.org/W4390872670","https://openalex.org/W4393404507","https://openalex.org/W4394566113","https://openalex.org/W4401070841","https://openalex.org/W4402703046","https://openalex.org/W4402727538","https://openalex.org/W4402776182","https://openalex.org/W4403840763","https://openalex.org/W4404199198","https://openalex.org/W4409363472","https://openalex.org/W4409366956","https://openalex.org/W4409367296","https://openalex.org/W4409369724","https://openalex.org/W4413147024","https://openalex.org/W4413147759"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W3205506801","https://openalex.org/W4280599700","https://openalex.org/W3183570023","https://openalex.org/W4301867275","https://openalex.org/W4224939635","https://openalex.org/W4292794827","https://openalex.org/W2790610275"],"abstract_inverted_index":{"This":[0],"work":[1,60],"focuses":[2],"on":[3,35,159],"developing":[4],"parameter-efficient":[5],"and":[6,17,68,83,111,138,165,185],"lightweight":[7,33,48,63,92,149],"models":[8,82,132,150,192,239],"for":[9,47,91,127,205],"dense":[10,163],"predictions":[11],"while":[12],"trading":[13],"off":[14],"parameters,":[15],"FLOPs,":[16],"performance.":[18],"Our":[19,59],"goal":[20],"is":[21],"to":[22,80,240],"set":[23],"up":[24],"the":[25,29,45,62,124,144,170,195,211,220,234],"new":[26,242],"frontier":[27],"of":[28,65,148,154,172,236],"5":[30,155],"M":[31,181,199,214],"magnitude":[32,153,238],"model":[34,93,140],"various":[36,160],"downstream":[37],"tasks.":[38],"Inverted":[39,106],"Residual":[40,107],"Block":[41,89,109],"(IRB)":[42],"serves":[43],"as":[44],"infrastructure":[46,64],"CNNs,":[49],"but":[50,97],"no":[51,119],"counterparts":[52],"have":[53],"been":[54],"recognized":[55],"by":[56,215],"attention-based":[57,81],"design.":[58,94],"rethinks":[61],"efficient":[66],"IRB":[67,79],"practical":[69],"components":[70],"in":[71],"Transformer":[72],"from":[73],"a":[74,85,103,113,152,241],"unified":[75],"perspective,":[76],"extending":[77],"CNN-based":[78],"abstracting":[84],"one-residual":[86],"Meta":[87],"Mobile":[88,108],"(MMBlock)":[90],"Following":[95],"neat":[96],"effective":[98],"design":[99],"criterion,":[100],"we":[101,142],"deduce":[102],"modern":[104],"Improved":[105],"(i$^{2}$2RMB)":[110],"improve":[112],"hierarchical":[114],"Efficient":[115],"MOdel":[116],"(EMOv2)":[117],"with":[118,151],"elaborate":[120],"complex":[121],"structures.":[122],"Considering":[123],"imperceptible":[125],"latency":[126],"mobile":[128],"users":[129],"when":[130],"downloading":[131],"under":[133],"4":[134],"G/5":[135],"G":[136],"bandwidth":[137],"ensuring":[139],"performance,":[141],"investigate":[143],"performance":[145,235],"upper":[146],"limit":[147],"M.":[156],"Extensive":[157],"experiments":[158],"vision":[161],"recognition,":[162],"prediction,":[164],"image":[166],"generation":[167],"tasks":[168,208],"demonstrate":[169],"superiority":[171],"our":[173,225],"EMOv2":[174],"over":[175],"state-of-the-art":[176],"methods,":[177],"e.g.,":[178],"EMOv2-1":[179],"M/2M/5":[180],"achieve":[182],"72.3,":[183],"75.8,":[184],"79.4":[186],"Top-1":[187,230],"that":[188,209],"surpass":[189],"equal-order":[190],"CNN-/Attention-based":[191],"significantly.":[193],"At":[194],"same":[196],"time,":[197],"EMOv2-5":[198],"equipped":[200],"RetinaNet":[201],"achieves":[202,228],"41.5":[203],"mAP":[204],"object":[206],"detection":[207],"surpasses":[210],"previous":[212],"EMO-5":[213],"+2.6$\\uparrow$\u2191":[216],".":[217],"When":[218],"employing":[219],"more":[221],"robust":[222],"training":[223],"recipe,":[224],"EMOv2-5M":[226],"eventually":[227],"82.9":[229],"accuracy,":[231],"which":[232],"elevates":[233],"5M":[237],"level.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}