{"id":"https://openalex.org/W4415538237","doi":"https://doi.org/10.1145/3746027.3754893","title":"VLHP: Learning Discriminative Vision-Language Hybrid Prototypes for Weakly Supervised Semantic Segmentation","display_name":"VLHP: Learning Discriminative Vision-Language Hybrid Prototypes for Weakly Supervised Semantic Segmentation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538237","doi":"https://doi.org/10.1145/3746027.3754893"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754893","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113260434","display_name":"Jingyuan Fang","orcid":"https://orcid.org/0009-0004-1184-9445"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Fang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0004-1184-9445","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005344412","display_name":"Yang Ning","orcid":"https://orcid.org/0009-0009-6093-6752"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ning","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0009-6093-6752","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019824207","display_name":"Xiushan Nie","orcid":"https://orcid.org/0000-0001-9644-9723"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiushan Nie","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-9644-9723","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651326","display_name":"Xinfeng Liu","orcid":"https://orcid.org/0000-0001-6480-7530"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfeng Liu","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-6480-7530","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068843001","display_name":"Zhiyong Cheng","orcid":"https://orcid.org/0000-0003-1109-5028"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Cheng","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1109-5028","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2939","last_page":"2948"},"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/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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/discriminative-model","display_name":"Discriminative model","score":0.8305000066757202},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7053999900817871},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5062999725341797},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.44690001010894775},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.39160001277923584},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.37779998779296875}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8305000066757202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698000073432922},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7053999900817871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7020999789237976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32519999146461487},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754893","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4186954517","display_name":null,"funder_award_id":"ZR202103010201","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G6317468392","display_name":null,"funder_award_id":"tsqn202103088","funder_id":"https://openalex.org/F4320326189","funder_display_name":"Taishan Scholar Project of Shandong Province"},{"id":"https://openalex.org/G8887579896","display_name":null,"funder_award_id":"62176141 and 62272254","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/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320326189","display_name":"Taishan Scholar Project of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2295107390","https://openalex.org/W2798354744","https://openalex.org/W2897628926","https://openalex.org/W2997851315","https://openalex.org/W3202427362","https://openalex.org/W3202524699","https://openalex.org/W4221115899","https://openalex.org/W4312709262","https://openalex.org/W4313052647","https://openalex.org/W4386071798","https://openalex.org/W4386159669","https://openalex.org/W4394677290","https://openalex.org/W4403791863"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,25,131],"Weakly":[3],"Supervised":[4],"Semantic":[5],"Segmentation":[6],"(WSSS)":[7],"focus":[8],"on":[9,137],"generating":[10,73],"high-quality":[11],"Class":[12],"Activation":[13],"Maps":[14],"(CAMs)":[15],"using":[16],"image-level":[17],"labels.":[18],"However,":[19],"the":[20,35,80],"co-occurrence":[21],"of":[22,37],"foreground-background":[23],"concepts":[24],"a":[26,47,114,132],"single":[27],"image":[28],"often":[29],"induces":[30],"semantic":[31,57,75],"confusion,":[32],"which":[33],"degrades":[34],"quality":[36],"conventional":[38],"CAM-based":[39],"approaches.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,87],"propose":[45],"VLHP,":[46],"novel":[48],"framework":[49],"that":[50,145],"leverages":[51],"vision-language":[52],"hybrid":[53,62],"prototypes":[54,63,122],"to":[55,96,106,126],"overcome":[56],"confusion.":[58],"Specifically,":[59],"VLHP":[60,146],"constructs":[61],"through":[64],"cross-modal":[65,98],"association":[66],"between":[67],"textual":[68],"embeddings":[69],"and":[70,101,110,140],"visual":[71],"features,":[72],"discriminative":[74],"representations":[76],"while":[77],"effectively":[78],"bridging":[79],"modality":[81],"gap.":[82],"To":[83],"further":[84],"improve":[85],"discriminability,":[86],"introduce":[88],"two":[89],"dedicated":[90],"strategies:":[91],"Discriminative":[92],"Explicit":[93],"Alignment":[94],"(DEA)":[95],"explore":[97],"consistent":[99],"discrimination":[100],"Confounding":[102],"Background":[103],"Decoupling":[104],"(CBD)":[105],"model":[107],"co-occurring":[108],"backgrounds":[109],"decouple":[111],"them.":[112],"Finally,":[113],"Prototype-driven":[115],"Class-aware":[116],"Decoder":[117],"(PCD)":[118],"employs":[119],"these":[120],"refined":[121],"as":[123],"category-specific":[124],"priors":[125],"generate":[127],"precise":[128],"segmentation":[129],"masks":[130],"single-stage":[133],"framework.":[134],"Extensive":[135],"experiments":[136],"PASCAL":[138],"VOC":[139],"MS":[141],"COCO":[142],"benchmarks":[143],"demonstrate":[144],"outperforms":[147],"state-of-the-art":[148],"alternatives.":[149],"The":[150],"code":[151],"is":[152],"available":[153],"at":[154],"https://github.com/fjy0105/VLHP.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}