{"id":"https://openalex.org/W4415708524","doi":"https://doi.org/10.1109/icme59968.2025.11210107","title":"MPT-CLIP: Multi-modal Patch-level Prompt Alignment in CLIP for Zero-shot Semantic Segmentation","display_name":"MPT-CLIP: Multi-modal Patch-level Prompt Alignment in CLIP for Zero-shot Semantic Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708524","doi":"https://doi.org/10.1109/icme59968.2025.11210107"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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":null,"display_name":"Boliang Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I1328775524","display_name":"Zhejiang Sci-Tech University","ror":"https://ror.org/03893we55","country_code":"CN","type":"education","lineage":["https://openalex.org/I1328775524"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boliang Hao","raw_affiliation_strings":["School of Computer Science and Technology Zhejiang Sci-Tech University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology Zhejiang Sci-Tech University,Hangzhou,China","institution_ids":["https://openalex.org/I1328775524"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026986847","display_name":"Fangyu Wu","orcid":"https://orcid.org/0000-0001-9618-8965"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyu Wu","raw_affiliation_strings":["Xi’an Jiaotong-Liverpool University,Department of Intelligent Science,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong-Liverpool University,Department of Intelligent Science,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021868890","display_name":"Yifan Lu","orcid":"https://orcid.org/0000-0002-8045-9932"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I159389169","display_name":"Ningbo University of Technology","ror":"https://ror.org/037dym702","country_code":"CN","type":"education","lineage":["https://openalex.org/I159389169"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Lu","raw_affiliation_strings":["College of Computer Science and Big Data Engineering NingboTech University,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Big Data Engineering NingboTech University,Ningbo,China","institution_ids":["https://openalex.org/I159389169","https://openalex.org/I109935558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086628680","display_name":"Bailing Zhang","orcid":"https://orcid.org/0000-0002-5472-2100"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I159389169","display_name":"Ningbo University of Technology","ror":"https://ror.org/037dym702","country_code":"CN","type":"education","lineage":["https://openalex.org/I159389169"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bailing Zhang","raw_affiliation_strings":["Computer Science NingboTech University,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science NingboTech University,Ningbo,China","institution_ids":["https://openalex.org/I159389169","https://openalex.org/I109935558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1489183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.708899974822998,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.708899974822998,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10119999945163727,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0771000012755394,"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/segmentation","display_name":"Segmentation","score":0.7024999856948853},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5932999849319458},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5206000208854675},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5099999904632568},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5030999779701233},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44040000438690186},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3443000018596649},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165000081062317},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7024999856948853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6290000081062317},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44040000438690186},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30640000104904175},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1594039573","https://openalex.org/W2924485953","https://openalex.org/W3035242260","https://openalex.org/W3171581326","https://openalex.org/W3198377975","https://openalex.org/W4226058394","https://openalex.org/W4312651322","https://openalex.org/W4312815172","https://openalex.org/W4312935996","https://openalex.org/W4312960937","https://openalex.org/W4386065874","https://openalex.org/W4386071547","https://openalex.org/W4386075882","https://openalex.org/W4403843568"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,122],"zero-shot":[3,104,140],"semantic":[4,29,51,105,110,141],"segmentation":[5,63,142],"have":[6],"demonstrated":[7],"that":[8,82,134],"the":[9,33,103,118],"large-scale":[10],"Contrastive":[11],"Language-Image":[12],"Pre-training":[13],"(CLIP)":[14],"model":[15],"can":[16],"effectively":[17],"transfer":[18],"multimodal":[19],"knowledge":[20],"to":[21,61,86,102],"pixel-level":[22],"classification.":[23],"However,":[24],"existing":[25],"single-stage":[26],"solutions":[27],"generate":[28],"masks":[30],"by":[31,117],"comparing":[32],"similarity":[34,114],"between":[35],"text":[36],"and":[37,49,56,88,112],"patch":[38],"embeddings":[39],"extracted":[40],"from":[41],"CLIP.":[42],"These":[43],"methods":[44],"typically":[45],"focus":[46],"on":[47,139],"single-mode":[48],"holistic-level":[50],"alignment,":[52],"overlooking":[53],"sample":[54],"diversities":[55],"fine-grained":[57,113],"information,":[58],"which":[59,107],"leads":[60],"suboptimal":[62],"results,":[64],"especially":[65],"for":[66],"complex":[67],"samples.":[68],"To":[69],"address":[70],"this":[71],"issue,":[72],"we":[73,96,125],"propose":[74],"MPT-CLIP,":[75],"a":[76],"multi-modal":[77,98],"Patch-level":[78,99],"prompt":[79,90,100],"alignment":[80,101],"method":[81],"leverages":[83],"optimal":[84],"transport":[85],"learn":[87],"align":[89],"token":[91],"sets":[92],"across":[93,145],"modalities.":[94],"Specifically,":[95],"apply":[97],"segmentation,":[106],"facilitates":[108],"diverse":[109],"representations":[111],"exploration.":[115],"Inspired":[116],"success":[119],"of":[120],"Sinkformers":[121],"attention":[123],"mechanisms,":[124],"introduce":[126],"Multi-Prompt":[127],"Sinkhorn":[128],"Attention":[129],"(MPSA).":[130],"Extensive":[131],"experiments":[132],"demonstrate":[133],"MPT-CLIP":[135],"achieves":[136],"superior":[137],"performance":[138],"(ZS3)":[143],"tasks":[144],"benchmark":[146],"datasets.Our":[147],"code":[148],"will":[149],"be":[150],"available":[151],"at":[152],"https://github.com/hbl66/MPTclip.":[153]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-30T00:00:00"}