{"id":"https://openalex.org/W4405778884","doi":"https://doi.org/10.1109/tmm.2024.3521851","title":"MENSA: Multi-Dataset Harmonized Pretraining for Semantic Segmentation","display_name":"MENSA: Multi-Dataset Harmonized Pretraining for Semantic Segmentation","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405778884","doi":"https://doi.org/10.1109/tmm.2024.3521851"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521851","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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/A5101614377","display_name":"Bowen Shi","orcid":"https://orcid.org/0000-0002-9169-7055"},"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":"Bowen Shi","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9169-7055","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614065","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0001-6337-5748"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Zhang","raw_affiliation_strings":["Huawei, Shenzhen, China","Huawei, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-6337-5748","affiliations":[{"raw_affiliation_string":"Huawei, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049554440","display_name":"Yaoming Wang","orcid":"https://orcid.org/0000-0002-0026-4247"},"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":"Yaoming Wang","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0026-4247","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045342512","display_name":"Wenrui Dai","orcid":"https://orcid.org/0000-0003-2522-5778"},"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":"Wenrui Dai","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2522-5778","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016006337","display_name":"Junni Zou","orcid":"https://orcid.org/0000-0002-9694-9880"},"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":"Junni Zou","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9694-9880","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"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":"Hongkai Xiong","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4552-0029","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2778,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65505124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"27","issue":null,"first_page":"2127","last_page":"2140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4715000092983246,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.4715000092983246,"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":0.43689998984336853,"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":0.8674848079681396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6114347577095032},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5777822136878967},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.525789737701416},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49840426445007324},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37444573640823364},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35556793212890625},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10211309790611267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8674848079681396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6114347577095032},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5777822136878967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.525789737701416},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49840426445007324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37444573640823364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35556793212890625},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10211309790611267}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521851","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G1080903817","display_name":null,"funder_award_id":"62320106003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3438946646","display_name":null,"funder_award_id":"61932022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6094063813","display_name":null,"funder_award_id":"62125109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7123918047","display_name":null,"funder_award_id":"62120106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7931220373","display_name":null,"funder_award_id":"62371288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8700549466","display_name":null,"funder_award_id":"61931023","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":59,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2037227137","https://openalex.org/W2117539524","https://openalex.org/W2144794286","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2507296351","https://openalex.org/W2561196672","https://openalex.org/W2781228439","https://openalex.org/W2787091153","https://openalex.org/W2895281799","https://openalex.org/W2908138940","https://openalex.org/W2962843773","https://openalex.org/W2963150697","https://openalex.org/W2963318290","https://openalex.org/W2963524571","https://openalex.org/W3035086574","https://openalex.org/W3035524453","https://openalex.org/W3094502228","https://openalex.org/W3113328489","https://openalex.org/W3122412340","https://openalex.org/W3138516171","https://openalex.org/W3168822201","https://openalex.org/W3172615411","https://openalex.org/W3198377975","https://openalex.org/W4212987071","https://openalex.org/W4226058394","https://openalex.org/W4301146083","https://openalex.org/W4312422436","https://openalex.org/W4312563428","https://openalex.org/W4312804044","https://openalex.org/W4312815172","https://openalex.org/W4312833717","https://openalex.org/W4312890493","https://openalex.org/W4312912313","https://openalex.org/W4313156423","https://openalex.org/W4390872859","https://openalex.org/W4390889737","https://openalex.org/W4396553738","https://openalex.org/W6639480849","https://openalex.org/W6683633756","https://openalex.org/W6726497184","https://openalex.org/W6745111092","https://openalex.org/W6745136726","https://openalex.org/W6745156673","https://openalex.org/W6754038005","https://openalex.org/W6762226699","https://openalex.org/W6767680423","https://openalex.org/W6774670964","https://openalex.org/W6791353385","https://openalex.org/W6792268172","https://openalex.org/W6796761347","https://openalex.org/W6802517928","https://openalex.org/W6804229649","https://openalex.org/W6807286953","https://openalex.org/W6810362786","https://openalex.org/W6811013733","https://openalex.org/W6811433417","https://openalex.org/W6838393215"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W4398146871","https://openalex.org/W3112772842"],"abstract_inverted_index":{"Existing":[0],"pretraining":[1,16,23,71],"methods":[2],"for":[3,73,106,140,165],"semantic":[4],"segmentation":[5,34,153],"are":[6],"hampered":[7],"by":[8,51,183],"the":[9,93,97],"task":[10],"gap":[11],"between":[12],"global":[13],"image":[14],"-level":[15],"and":[17,42,45,86,100,133,136,180],"local":[18],"pixel-level":[19,137,185],"finetuning.":[20],"Joint":[21],"dense-level":[22],"is":[24,149,173],"a":[25,61,150],"promising":[26],"alternative":[27],"to":[28,90,112,128,175,187],"exploit":[29],"off-the-shelf":[30],"annotations":[31],"from":[32,38],"diverse":[33],"datasets":[35,50],"but":[36],"suffers":[37],"low-quality":[39],"class":[40,94],"embeddings":[41,85,89],"inconsistent":[43,130],"data":[44,142],"supervision":[46,104,131],"signals":[47,132],"across":[48],"multiple":[49,113],"directly":[52],"employing":[53],"CLIP.":[54],"To":[55,109],"overcome":[56],"these":[57],"challenges,":[58],"we":[59,115],"propose":[60],"novel":[62],"<underline":[63,74],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[64,66,69,75,78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</u>ulti-datas<underline":[65],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">E</u>t":[67],"harmo<underline":[68],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">N</u>ized":[70],"framework":[72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S</u>emantic":[76],"s<underline":[77],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">E</u>gmentation":[79],"(MENSA).":[80],"MENSA":[81,148,172],"incorporates":[82],"high-quality":[83],"language":[84],"momentum-updated":[87],"visual":[88],"effectively":[91],"model":[92,154],"relationships":[95],"in":[96],"embedding":[98],"space":[99],"thereby":[101],"provide":[102],"reliable":[103],"information":[105,126],"each":[107],"category.":[108],"further":[110],"adapt":[111],"datasets,":[114],"achieve":[116],"one-to-many":[117],"pixel-embedding":[118],"pairing":[119],"with":[120],"cross-dataset":[121,138],"multi-label":[122],"mapping":[123],"through":[124],"cross-modal":[125],"exchange":[127],"mitigate":[129],"introduce":[134],"region-level":[135],"mixing":[139],"varying":[141],"distribution.":[143],"Experimental":[144],"results":[145],"demonstrate":[146],"that":[147,155],"powerful":[151],"foundation":[152],"consistently":[156],"outperforms":[157],"popular":[158],"supervised":[159],"or":[160],"unsupervised":[161],"ImageNet":[162],"pretrained":[163],"models":[164],"various":[166],"benchmarks":[167],"under":[168],"standard":[169],"fine-tuning.":[170],"Furthermore,":[171],"shown":[174],"significantly":[176],"benefit":[177],"frozen-backbone":[178],"fine-tuning":[179],"zero-shot":[181],"learning":[182],"endowing":[184],"distinctiveness":[186],"learned":[188],"representations.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}