{"id":"https://openalex.org/W4415428903","doi":"https://doi.org/10.3233/faia250887","title":"Investigating Mask-Text Contrastive Alignment in Semantic Segmentation","display_name":"Investigating Mask-Text Contrastive Alignment in Semantic Segmentation","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428903","doi":"https://doi.org/10.3233/faia250887"},"language":null,"primary_location":{"id":"doi:10.3233/faia250887","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250887","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250887","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106709207","display_name":"Federico D\u2019Asaro","orcid":"https://orcid.org/0009-0003-8727-3393"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]},{"id":"https://openalex.org/I2803087260","display_name":"Space Foundation","ror":"https://ror.org/029hj0c48","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2803087260"]}],"countries":["IT","US"],"is_corresponding":true,"raw_author_name":"Federico D\u2019Asaro","raw_affiliation_strings":["LINKS Foundation \u2013 AI, Data & Space (ADS)","Politecnico di Torino \u2013 Dipartimento di Automatica e Informatica (DAUIN)"],"raw_orcid":"https://orcid.org/0009-0003-8727-3393","affiliations":[{"raw_affiliation_string":"LINKS Foundation \u2013 AI, Data & Space (ADS)","institution_ids":["https://openalex.org/I2803087260"]},{"raw_affiliation_string":"Politecnico di Torino \u2013 Dipartimento di Automatica e Informatica (DAUIN)","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040856490","display_name":"A. Bottino","orcid":"https://orcid.org/0000-0002-8894-5089"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Bottino","raw_affiliation_strings":["Politecnico di Torino \u2013 Dipartimento di Automatica e Informatica (DAUIN)"],"raw_orcid":"https://orcid.org/0000-0002-8894-5089","affiliations":[{"raw_affiliation_string":"Politecnico di Torino \u2013 Dipartimento di Automatica e Informatica (DAUIN)","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088463134","display_name":"Giuseppe Rizzo","orcid":"https://orcid.org/0000-0003-0083-813X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]},{"id":"https://openalex.org/I2803087260","display_name":"Space Foundation","ror":"https://ror.org/029hj0c48","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2803087260"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Giuseppe Rizzo","raw_affiliation_strings":["LINKS Foundation \u2013 AI, Data & Space (ADS)","Politecnico di Torino \u2013 Dipartimento di Automatica e Informatica (DAUIN)"],"raw_orcid":"https://orcid.org/0000-0003-0083-813X","affiliations":[{"raw_affiliation_string":"LINKS Foundation \u2013 AI, Data & Space (ADS)","institution_ids":["https://openalex.org/I2803087260"]},{"raw_affiliation_string":"Politecnico di Torino \u2013 Dipartimento di Automatica e Informatica (DAUIN)","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5106709207"],"corresponding_institution_ids":["https://openalex.org/I177477856","https://openalex.org/I2803087260"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49121833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.978600025177002,"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":0.978600025177002,"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":0.9747999906539917,"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/segmentation","display_name":"Segmentation","score":0.6552000045776367},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5454000234603882},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5285999774932861},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.43880000710487366},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.41449999809265137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41290000081062317},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.39879998564720154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820900022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6590999960899353},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6552000045776367},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5285999774932861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45260000228881836},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38109999895095825},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.32440000772476196},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250887","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250887","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250887","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250887","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Pretrained":[1],"Models":[2],"(VLPs)":[3],"have":[4],"shown":[5],"remarkable":[6],"success":[7],"in":[8,33,119,206,226],"transferring":[9],"knowledge":[10],"to":[11,22,59,67],"various":[12],"downstream":[13,228],"tasks,":[14],"ranging":[15],"from":[16],"image-level":[17],"tasks":[18,24,38,230],"such":[19,25,208,231],"as":[20,26,167,209,232],"classification":[21],"pixel-level":[23],"Semantic":[27],"Segmentation.":[28],"However,":[29],"a":[30,68,110,124,153,168,184],"persistent":[31],"challenge":[32],"the":[34,40,80,87,94,101,105,164,199],"latter":[35],"dense":[36,229],"prediction":[37],"is":[39,90,143,223,244],"misalignment":[41],"between":[42,52,114,134],"pixel":[43,95,148],"and":[44,54,57,73,116,137,149,188,213,235],"text":[45,106,117,150],"features.":[46,107],"This":[47,142],"mismatch":[48],"hinders":[49],"effective":[50,225],"fusion":[51],"visual":[53],"textual":[55],"representations,":[56],"leads":[58],"suboptimal":[60],"predictions.":[61],"While":[62],"some":[63],"studies":[64],"attribute":[65],"this":[66,120,242],"Modality":[69],"Gap,":[70],"where":[71,93,156],"vision":[72],"language":[74],"modalities":[75],"form":[76],"distinct":[77],"clusters":[78],"within":[79],"shared":[81],"feature":[82],"space,":[83],"we":[84,122],"argue":[85],"that":[86,129,198,221],"key":[88],"issue":[89],"semantic":[91,112,140,161],"misalignment,":[92],"features":[96,151],"do":[97],"not":[98],"accurately":[99],"reflect":[100],"concepts":[102],"encoded":[103],"by":[104,145],"To":[108],"achieve":[109],"stronger":[111],"alignment":[113,133],"pixels":[115],"embeddings,":[118],"work":[121,243],"propose":[123],"Mask-Text":[125],"Contrastive":[126],"(MTC)":[127],"module":[128,201],"explicitly":[130],"enforces":[131],"an":[132,157],"image":[135],"regions":[136],"their":[138],"corresponding":[139],"concepts.":[141],"achieved":[144],"projecting":[146],"both":[147],"into":[152,177],"common":[154],"space":[155],"InfoNCE-based":[158],"loss":[159],"promotes":[160],"correspondence,":[162],"reducing":[163],"modality":[165],"gap":[166],"side":[169],"effect.":[170],"Our":[171],"approach":[172],"can":[173],"be":[174],"seamlessly":[175],"integrated":[176],"state-of-the-art":[178],"VLP-based":[179],"segmentation":[180,204],"architectures,":[181],"requiring":[182],"only":[183],"lightweight":[185],"linear":[186],"projection":[187],"introducing":[189],"minimal":[190],"computational":[191],"overhead":[192],"at":[193,246],"inference":[194],"time.":[195],"Experiments":[196],"show":[197,220],"MTC":[200,222],"consistently":[202],"improves":[203],"performance":[205],"benchmarks":[207],"ADE20K,":[210],"COCO-Stuff":[211],"10k":[212],"Pascal":[214],"Context.":[215],"Further":[216],"experiments":[217],"with":[218,241],"COCO":[219],"also":[224],"other":[227],"object":[233],"detection":[234],"instance":[236],"segmentation.":[237],"The":[238],"repository":[239],"associated":[240],"available":[245],"https://github.com/fedasaro62/mask-text-contrastive-fully-seg.":[247]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-24T00:00:00"}