{"id":"https://openalex.org/W4406233682","doi":"https://doi.org/10.1145/3711868","title":"Multi-Grained Contrastive Learning for Text-Supervised Open-Vocabulary Semantic Segmentation","display_name":"Multi-Grained Contrastive Learning for Text-Supervised Open-Vocabulary Semantic Segmentation","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4406233682","doi":"https://doi.org/10.1145/3711868"},"language":"en","primary_location":{"id":"doi:10.1145/3711868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711868","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5103015234","display_name":"Yajie Liu","orcid":"https://orcid.org/0000-0002-0879-5894"},"institutions":[{"id":"https://openalex.org/I4210086551","display_name":"Academic Degrees & Graduate Education","ror":"https://ror.org/002e3sm06","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210086551","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yajie Liu","raw_affiliation_strings":["State Key Laboratory of Complex and Critical Software Environment and School of Computer Science and Engineering, Beihang University, Beijing, China","School of Computer Science and Engineering, China","State Key Laboratory of Complex and Critical Software Environment; and School of Computer Science and Engineering, China"],"raw_orcid":"https://orcid.org/0000-0002-0879-5894","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex and Critical Software Environment and School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, China","institution_ids":["https://openalex.org/I4210086551"]},{"raw_affiliation_string":"State Key Laboratory of Complex and Critical Software Environment; and School of Computer Science and Engineering, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059707268","display_name":"Pu Ge","orcid":"https://orcid.org/0000-0002-4444-3159"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pu Ge","raw_affiliation_strings":["Hangzhou Innovation Institute, Beihang University, Hangzhou, China","Hangzhou Innovation Institute, Beihang University, China"],"raw_orcid":"https://orcid.org/0000-0002-4444-3159","affiliations":[{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, Hangzhou, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Hangzhou Innovation Institute, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449049","display_name":"Guodong Wang","orcid":"https://orcid.org/0009-0003-8642-396X"},"institutions":[{"id":"https://openalex.org/I4210086551","display_name":"Academic Degrees & Graduate Education","ror":"https://ror.org/002e3sm06","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210086551","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Wang","raw_affiliation_strings":["State Key Laboratory of Complex and Critical Software Environment and School of Computer Science and Engineering, Beihang University, Beijing, China","School of Computer Science and Engineering, China","State Key Laboratory of Complex and Critical Software Environment; and School of Computer Science and Engineering, China"],"raw_orcid":"https://orcid.org/0009-0003-8642-396X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex and Critical Software Environment and School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, China","institution_ids":["https://openalex.org/I4210086551"]},{"raw_affiliation_string":"State Key Laboratory of Complex and Critical Software Environment; and School of Computer Science and Engineering, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056847110","display_name":"Qingjie Liu","orcid":"https://orcid.org/0000-0002-5181-6451"},"institutions":[{"id":"https://openalex.org/I4210086551","display_name":"Academic Degrees & Graduate Education","ror":"https://ror.org/002e3sm06","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210086551","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingjie Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Beihang University, Beijing, China","School of Computer Science and Engineering, China"],"raw_orcid":"https://orcid.org/0000-0002-5181-6451","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, China","institution_ids":["https://openalex.org/I4210086551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056972984","display_name":"Di Huang","orcid":"https://orcid.org/0000-0002-2412-9330"},"institutions":[{"id":"https://openalex.org/I4210086551","display_name":"Academic Degrees & Graduate Education","ror":"https://ror.org/002e3sm06","country_code":"CN","type":"education","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210086551","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Huang","raw_affiliation_strings":["State Key Laboratory of Complex and Critical Software Environment and School of Computer Science and Engineering, Beihang University, Beijing, China","School of Computer Science and Engineering, China","State Key Laboratory of Complex and Critical Software Environment; and School of Computer Science and Engineering, China"],"raw_orcid":"https://orcid.org/0000-0002-2412-9330","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex and Critical Software Environment and School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engineering, China","institution_ids":["https://openalex.org/I4210086551"]},{"raw_affiliation_string":"State Key Laboratory of Complex and Critical Software Environment; and School of Computer Science and Engineering, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103015234"],"corresponding_institution_ids":["https://openalex.org/I4210086551","https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00326675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9990000128746033,"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":0.9170184135437012},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6397901177406311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6147337555885315},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5287817716598511},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5223104357719421},{"id":"https://openalex.org/keywords/vocabulary-learning","display_name":"Vocabulary learning","score":0.5222048163414001},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14540058374404907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9170184135437012},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6397901177406311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6147337555885315},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5287817716598511},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5223104357719421},{"id":"https://openalex.org/C2984601542","wikidata":"https://www.wikidata.org/wiki/Q48842322","display_name":"Vocabulary learning","level":3,"score":0.5222048163414001},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14540058374404907},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711868","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G1832166106","display_name":null,"funder_award_id":"LQ23F020024","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G2367686565","display_name":null,"funder_award_id":"62176017, 82441024, 62302031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4232962833","display_name":null,"funder_award_id":"82441024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8389390295","display_name":null,"funder_award_id":"62176017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8934315408","display_name":null,"funder_award_id":"62302031","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1999478155","https://openalex.org/W2031489346","https://openalex.org/W2125215748","https://openalex.org/W2250384498","https://openalex.org/W2340897893","https://openalex.org/W2507296351","https://openalex.org/W2886641317","https://openalex.org/W2912083425","https://openalex.org/W2964309882","https://openalex.org/W3133004360","https://openalex.org/W3176641147","https://openalex.org/W3212194243","https://openalex.org/W3214262346","https://openalex.org/W4212804468","https://openalex.org/W4283391360","https://openalex.org/W4308731338","https://openalex.org/W4312960937","https://openalex.org/W4321786075","https://openalex.org/W4385723203","https://openalex.org/W4386075561","https://openalex.org/W4386075766","https://openalex.org/W4386076046","https://openalex.org/W4401525289"],"related_works":["https://openalex.org/W3019875293","https://openalex.org/W2351746492","https://openalex.org/W3204019825","https://openalex.org/W2367621846","https://openalex.org/W2394096350","https://openalex.org/W2091742426","https://openalex.org/W2365662948","https://openalex.org/W1988910916","https://openalex.org/W2380430606","https://openalex.org/W4360597343"],"abstract_inverted_index":{"Learning":[0],"open-vocabulary":[1],"semantic":[2,76,104],"segmentation":[3,138],"(OVSS)":[4],"from":[5,124],"text":[6],"supervision":[7],"has":[8],"recently":[9],"received":[10],"increasing":[11],"attention":[12],"for":[13],"its":[14,151],"promising":[15],"potential":[16],"in":[17],"real-world":[18],"applications.":[19],"However,":[20],"only":[21],"with":[22,50,86],"image-level":[23],"supervision,":[24],"it":[25],"struggles":[26],"to":[27,47,90,115],"achieve":[28],"dense":[29],"and":[30,34,82,84,120,127],"robust":[31],"cross-modal":[32,92,112],"alignment":[33,113],"thus":[35],"limits":[36],"pixel-level":[37,83],"predictions.":[38],"In":[39],"this":[40,48],"article,":[41],"we":[42,100],"present":[43],"a":[44,133],"novel":[45],"approach":[46,143],"task":[49],"M":[51],"ulti-":[52],"G":[53],"rained":[54],"C":[55,57],"ross-modal":[56],"ontrastive":[58],"L":[59],"earning,":[60],"named":[61],"MGCCL.":[62],"Specifically,":[63],"unlike":[64],"current":[65],"solutions":[66],"restricted":[67],"by":[68],"coarse":[69],"image/object-text":[70],"alignment,":[71],"MGCCL":[72],"constructs":[73],"pseudo":[74],"multi-granular":[75],"correspondences":[77],"at":[78],"the":[79,109,118,125],"object-,":[80],"part-,":[81],"collaborates":[85],"hard":[87],"sampling":[88],"strategies":[89],"conduct":[91],"contrastive":[93],"learning,":[94],"significantly":[95],"facilitating":[96],"fine-grained":[97],"alignment.":[98],"Further,":[99],"develop":[101],"an":[102],"adaptive":[103],"unit":[105],"which":[106],"flexibly":[107],"harnesses":[108],"learned":[110],"multi-grained":[111],"capabilities":[114],"effectively":[116],"mitigate":[117],"under-":[119],"over-segmentation":[121],"issues":[122],"arising":[123],"per-group":[126],"per-pixel":[128],"units.":[129],"Extensive":[130],"experiments":[131],"over":[132,147],"broad":[134],"suite":[135],"of":[136],"eight":[137],"benchmarks":[139],"show":[140],"that":[141],"our":[142],"delivers":[144],"significant":[145],"advancements":[146],"state-of-the-art":[148],"counterparts,":[149],"demonstrating":[150],"effectiveness.":[152]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}