{"id":"https://openalex.org/W4415708175","doi":"https://doi.org/10.1109/icme59968.2025.11209574","title":"SCA-ZegCLIP: Shape- and Context-aware CLIP for Zero-shot Semantic Segmentation","display_name":"SCA-ZegCLIP: Shape- and Context-aware CLIP for Zero-shot Semantic Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708175","doi":"https://doi.org/10.1109/icme59968.2025.11209574"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209574","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":"https://openalex.org/A5025704945","display_name":"Chunrui Li","orcid":"https://orcid.org/0000-0001-5134-7133"},"institutions":[{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]},{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chunrui Li","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388050","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0001-7147-9125"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100687829","display_name":"Shu Hu","orcid":"https://orcid.org/0000-0003-1446-4140"},"institutions":[{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]},{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Hu","raw_affiliation_strings":["Sichuan University,College of Computer Science,Chengdu,China"],"affiliations":[{"raw_affiliation_string":"Sichuan University,College of Computer Science,Chengdu,China","institution_ids":["https://openalex.org/I4210125143","https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025704945"],"corresponding_institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210125143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33760803,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8133999705314636,"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":0.8133999705314636,"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":0.0689999982714653,"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":0.04470000043511391,"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":0.7516000270843506},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6984999775886536},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.44859999418258667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39480000734329224},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.37880000472068787},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3662000000476837},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35679998993873596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588000297546387},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7516000270843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7423999905586243},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6984999775886536},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4551999866962433},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3662000000476837},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.28279998898506165},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209574","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":17,"referenced_works":["https://openalex.org/W2037227137","https://openalex.org/W2561196672","https://openalex.org/W2924485953","https://openalex.org/W2981793666","https://openalex.org/W3049293589","https://openalex.org/W3168227666","https://openalex.org/W3176777339","https://openalex.org/W3198377975","https://openalex.org/W3201755784","https://openalex.org/W3202473909","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4312935996","https://openalex.org/W4312960937","https://openalex.org/W4386066500","https://openalex.org/W4386075882","https://openalex.org/W4402727160"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"large-scale":[1],"Contrastive":[2],"Language-Image":[3],"Pre\u2013training":[4],"model":[5,106],"(CLIP)":[6],"has":[7,16,107],"prevailed":[8],"in":[9,20,42],"multiple":[10],"computer":[11],"vision":[12],"tasks,":[13],"especially":[14],"it":[15],"achieved":[17],"appealing":[18],"results":[19],"zero-shot":[21],"semantic":[22,47],"segmentation":[23,119,138],"(ZSS).":[24],"However,":[25],"existing":[26],"CLIP":[27,97],"models":[28],"lack":[29],"shape":[30],"awareness.":[31],"On":[32],"the":[33,76,81,112,118],"other":[34,148],"hand,":[35],"textual":[36,92],"prompts":[37],"play":[38],"a":[39,55,60,103],"vital":[40],"role":[41],"Visual":[43],"Language":[44],"Model":[45],"based":[46,98],"segmentation.":[48],"Considering":[49],"this,":[50],"we":[51,73],"propose":[52,74],"SCA-ZegCLIP":[53,135],"with":[54,117],"contour":[56],"perception":[57],"module":[58],"and":[59,91,130,140],"multi-granularity":[61],"context-aware":[62],"prompt":[63,84,89,93,114],"learner,":[64],"which":[65],"aim":[66],"to":[67,79,96],"enhance":[68],"dense":[69,99],"prediction":[70,100,116],"ability.":[71],"Besides,":[72],"for":[75],"first":[77],"time":[78],"apply":[80],"dual":[82],"path":[83],"tuning":[85,90,94],"strategy":[86],"(using":[87],"visual":[88],"simultaneously)":[95],"tasks.":[101],"Finally,":[102],"one-stage":[104],"ZSS":[105],"been":[108,124],"developed":[109],"by":[110],"weighting":[111],"obtained":[113],"mask":[115],"results.":[120],"Extensive":[121],"experiments":[122],"have":[123],"carried":[125],"out":[126],"on":[127],"COCO-Stuff":[128],"164K":[129],"PASCAL":[131],"VOC":[132],"2012,":[133],"where":[134],"exhibits":[136],"higher":[137],"accuracy":[139],"stronger":[141],"generalization":[142],"ability":[143],"(for":[144],"unseen":[145],"categories)":[146],"among":[147],"state-of-the-arts":[149],"methods.":[150]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}