{"id":"https://openalex.org/W4404650228","doi":"https://doi.org/10.1109/iccv51701.2025.02154","title":"CLIPeR: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation","display_name":"CLIPeR: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404650228","doi":"https://doi.org/10.1109/iccv51701.2025.02154"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.13836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070657531","display_name":"Lin Sun","orcid":"https://orcid.org/0000-0003-2923-3281"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Sun","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037129512","display_name":"Jiale Cao","orcid":"https://orcid.org/0000-0002-5160-6841"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Cao","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733501","display_name":"Jin Xie","orcid":"https://orcid.org/0000-0002-1268-1363"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["Chongqing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060665015","display_name":"Xiaoheng Jiang","orcid":"https://orcid.org/0000-0002-5770-0417"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoheng Jiang","raw_affiliation_strings":["Zhengzhou University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhengzhou University","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086887025","display_name":"Yanwei Pang","orcid":"https://orcid.org/0000-0001-6670-3727"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23199","last_page":"23209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9883000254631042,"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/T12031","display_name":"Speech and dialogue systems","score":0.9866999983787537,"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/vocabulary","display_name":"Vocabulary","score":0.6747030019760132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6586053371429443},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6327672004699707},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6300949454307556},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4718085527420044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46121180057525635},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38896432518959045},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22477734088897705},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.0699324905872345}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6747030019760132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6586053371429443},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6327672004699707},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6300949454307556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4718085527420044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46121180057525635},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38896432518959045},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22477734088897705},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0699324905872345},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.13836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13836","pdf_url":"https://arxiv.org/pdf/2411.13836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.13836","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.13836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.13836","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13836","pdf_url":"https://arxiv.org/pdf/2411.13836","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5135811258","display_name":null,"funder_award_id":"2022ZD0160400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7301489333","display_name":null,"funder_award_id":"62271346,62206031,U21B2037","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404650228.pdf","grobid_xml":"https://content.openalex.org/works/W4404650228.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W2381983017"],"abstract_inverted_index":{"Contrastive":[0],"Language-Image":[1],"Pre-training":[2],"(CLIP)":[3],"exhibits":[4],"strong":[5],"zero-shot":[6],"classification":[7],"ability":[8],"on":[9,144,155,170],"various":[10],"image-level":[11,36],"tasks,":[12],"leading":[13],"to":[14,17,31,113,128],"the":[15,91,109,130,134,142,152,164],"research":[16],"adapt":[18],"CLIP":[19],"for":[20],"pixel-level":[21],"open-vocabulary":[22],"semantic":[23],"segmentation":[24,115,146],"without":[25],"additional":[26],"training.":[27],"The":[28,75],"key":[29],"is":[30],"improve":[32],"spatial":[33,71,101,119],"representation":[34,72],"of":[35,73,137,166],"CLIP,":[37],"such":[38],"as":[39],"replacing":[40],"self-attention":[41,135],"map":[42,49,116],"at":[43,96],"last":[44],"layer":[45],"with":[46,117],"self-self":[47],"attention":[48,55,94],"or":[50],"vision":[51],"foundation":[52],"model":[53],"based":[54],"map.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,107,122],"present":[61],"a":[62,84,124],"novel":[63],"hierarchical":[64],"framework,":[65],"named":[66],"CLIPer,":[67],"that":[68],"hierarchically":[69],"improves":[70],"CLIP.":[74],"proposed":[76,149],"CLIPer":[77,150,162],"includes":[78],"an":[79],"early-layer":[80,110],"fusion":[81,111],"module":[82,112,127],"and":[83,93,168,172,179],"fine-grained":[85,125],"compensation":[86,126],"module.":[87],"We":[88,140],"observe":[89],"that,":[90],"embeddings":[92],"maps":[95,136],"early":[97],"layers":[98],"can":[99],"preserve":[100],"structural":[102],"information.":[103],"Inspired":[104],"by":[105,177],"this,":[106],"design":[108],"generate":[114],"better":[118],"coherence.":[120],"Afterwards,":[121],"employ":[123],"compensate":[129],"local":[131],"details":[132],"using":[133,160],"diffusion":[138],"model.":[139],"conduct":[141],"experiments":[143],"seven":[145],"datasets.":[147,157],"Our":[148],"achieves":[151],"state-of-the-art":[153],"performance":[154],"these":[156],"For":[158],"instance,":[159],"ViT-L,":[161],"has":[163],"mIoU":[165],"69.8%":[167],"43.3%":[169],"VOC":[171],"COCO":[173],"Object,":[174],"outperforming":[175],"ProxyCLIP":[176],"9.2%":[178],"4.1%":[180],"respectively.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2024-11-24T00:00:00"}