{"id":"https://openalex.org/W4386066500","doi":"https://doi.org/10.1109/cvpr52729.2023.00293","title":"Delving into Shape-aware Zero-shot Semantic Segmentation","display_name":"Delving into Shape-aware Zero-shot Semantic Segmentation","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386066500","doi":"https://doi.org/10.1109/cvpr52729.2023.00293"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.00293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5100446436","display_name":"Xinyu Liu","orcid":"https://orcid.org/0000-0002-5180-6958"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Liu","raw_affiliation_strings":["Xidian University","Institute for AI Industry Research (AIR), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077011386","display_name":"Beiwen Tian","orcid":"https://orcid.org/0000-0002-2651-913X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beiwen Tian","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University","Department of Computer Science and Technology, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422377","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0002-8182-2852"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Didi Chuxing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431257","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0002-4792-1945"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Didi Chuxing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016509766","display_name":"Kehua Sheng","orcid":"https://orcid.org/0009-0008-3370-7711"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Kehua Sheng","raw_affiliation_strings":["Didi Chuxing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335202","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0001-8052-782X"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Didi Chuxing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didi Chuxing","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101213342","display_name":"Hao Zhao","orcid":"https://orcid.org/0000-0002-7578-9910"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhao","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011913905","display_name":"Guyue Zhou","orcid":"https://orcid.org/0000-0002-3894-9858"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guyue Zhou","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.079,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95090322,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2999","last_page":"3009"},"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":0.9987000226974487,"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":0.9987000226974487,"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":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.7673864364624023},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7357397079467773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6250195503234863},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5292719602584839},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5263066291809082},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48891082406044006},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.483505517244339},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.48293182253837585},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45692065358161926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41543373465538025},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37846043705940247},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36887073516845703},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.10760530829429626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673864364624023},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7357397079467773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6250195503234863},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5292719602584839},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5263066291809082},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48891082406044006},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.483505517244339},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.48293182253837585},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45692065358161926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41543373465538025},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37846043705940247},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36887073516845703},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.10760530829429626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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:10.1109/cvpr52729.2023.00293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1526204103","https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2035773017","https://openalex.org/W2037227137","https://openalex.org/W2081580037","https://openalex.org/W2121947440","https://openalex.org/W2144794286","https://openalex.org/W2250539671","https://openalex.org/W2295475768","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2604254608","https://openalex.org/W2806845529","https://openalex.org/W2811296358","https://openalex.org/W2896457183","https://openalex.org/W2924485953","https://openalex.org/W2962850830","https://openalex.org/W2964309882","https://openalex.org/W2971113548","https://openalex.org/W2981787211","https://openalex.org/W2981793666","https://openalex.org/W2991471181","https://openalex.org/W2994827984","https://openalex.org/W3014641072","https://openalex.org/W3036337637","https://openalex.org/W3040318838","https://openalex.org/W3040903310","https://openalex.org/W3047258141","https://openalex.org/W3049293589","https://openalex.org/W3086361745","https://openalex.org/W3103886171","https://openalex.org/W3104749918","https://openalex.org/W3105232955","https://openalex.org/W3106029750","https://openalex.org/W3108187451","https://openalex.org/W3109301572","https://openalex.org/W3112047874","https://openalex.org/W3123982987","https://openalex.org/W3126337491","https://openalex.org/W3149878926","https://openalex.org/W3159481202","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3168227666","https://openalex.org/W3176777339","https://openalex.org/W3202473909","https://openalex.org/W3211490618","https://openalex.org/W4214520160","https://openalex.org/W4226058394","https://openalex.org/W4226173246","https://openalex.org/W4226452378","https://openalex.org/W4240805545","https://openalex.org/W4306175965","https://openalex.org/W4307001578","https://openalex.org/W4309630083","https://openalex.org/W4313129917","https://openalex.org/W4313150877","https://openalex.org/W4320731744","https://openalex.org/W4383109207","https://openalex.org/W4391508113","https://openalex.org/W6631539730","https://openalex.org/W6639102338","https://openalex.org/W6639824700","https://openalex.org/W6748481559","https://openalex.org/W6763578275","https://openalex.org/W6768371451","https://openalex.org/W6781222066","https://openalex.org/W6785351755","https://openalex.org/W6786183582","https://openalex.org/W6786471941","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6793652844","https://openalex.org/W6797399245"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W1556451512","https://openalex.org/W2081900870","https://openalex.org/W4234091740","https://openalex.org/W4213350282","https://openalex.org/W2047973478","https://openalex.org/W2230171082","https://openalex.org/W4295532600","https://openalex.org/W2583128298","https://openalex.org/W2063823869"],"abstract_inverted_index":{"Thanks":[0],"to":[1,31,88,101,169],"the":[2,82,90,116,145,162],"impressive":[3],"progress":[4],"of":[5,93,115,118,164],"large-scale":[6],"vision-language":[7,55],"pretraining,":[8],"recent":[9],"recognition":[10],"models":[11,56,197],"can":[12],"classify":[13],"arbitrary":[14],"objects":[15],"in":[16,73,81],"a":[17,23,128],"zero-shot":[18,70,184],"and":[19,53,108,136,155,159,172,190,196],"open-set":[20],"manner,":[21],"with":[22,59,97,192],"surprisingly":[24],"high":[25],"accuracy.":[26],"However,":[27],"translating":[28],"this":[29,38,65,74,106],"success":[30],"semantic":[32,46,71,185],"segmentation":[33,72,84,186],"is":[34],"not":[35,43,112],"trivial,":[36],"because":[37],"dense":[39],"prediction":[40],"task":[41],"requires":[42],"only":[44],"accurate":[45],"understanding":[47],"but":[48],"also":[49,142],"fine":[50],"shape":[51],"delineation":[52],"existing":[54],"are":[57],"trained":[58],"image-level":[60],"language":[61,173],"descriptions.":[62],"To":[63],"bridge":[64],"gap,":[66],"we":[67,86,123],"pursue":[68],"shape-aware":[69,130],"study.":[75],"Inspired":[76],"by":[77],"classical":[78],"spectral":[79],"methods":[80],"image":[83],"literature,":[85],"propose":[87],"leverage":[89],"eigen":[91],"vectors":[92],"Laplacian":[94],"matrices":[95],"constructed":[96],"self-supervised":[98],"pixel-wise":[99],"features":[100],"promote":[102],"shape-awareness.":[103],"Despite":[104],"that":[105,125,132],"simple":[107],"effective":[109],"technique":[110],"does":[111],"make":[113],"use":[114],"masks":[117],"seen":[119],"classes":[120],"at":[121,201],"all,":[122],"demonstrate":[124],"it":[126],"out-performs":[127],"state-of-the-art":[129,181],"formulation":[131],"aligns":[133],"ground":[134],"truth":[135],"predicted":[137],"edges":[138],"during":[139],"training.":[140],"We":[141],"delve":[143],"into":[144],"performance":[146,182],"gains":[147],"achieved":[148],"on":[149,187],"different":[150,153],"datasets":[151],"using":[152],"backbones":[154],"draw":[156],"several":[157],"interesting":[158],"conclusive":[160],"observations:":[161],"benefits":[163],"promoting":[165],"shape-awareness":[166],"highly":[167],"relates":[168],"mask":[170],"compactness":[171],"embedding":[174],"locality.":[175],"Finally,":[176],"our":[177],"method":[178],"sets":[179],"new":[180],"for":[183],"both":[188],"Pascal":[189],"COCO,":[191],"significant":[193],"margins.":[194],"Code":[195],"will":[198],"be":[199],"accessed":[200],"SAZS.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}