{"id":"https://openalex.org/W4405030226","doi":"https://doi.org/10.1109/iccv51701.2025.02045","title":"Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation","display_name":"Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405030226","doi":"https://doi.org/10.1109/iccv51701.2025.02045"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02045","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/2411.19331","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035092680","display_name":"Luca Barsellotti","orcid":"https://orcid.org/0000-0001-8845-8523"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Barsellotti","raw_affiliation_strings":["University of Modena and Reggio Emilia,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia,Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084290670","display_name":"Lorenzo Bianchi","orcid":"https://orcid.org/0000-0001-7321-1536"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Bianchi","raw_affiliation_strings":["ISTI-CNR,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR,Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007125882","display_name":"Nicola Messina","orcid":"https://orcid.org/0000-0003-3011-2487"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Messina","raw_affiliation_strings":["ISTI-CNR,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR,Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059447545","display_name":"Fabio Carrara","orcid":"https://orcid.org/0000-0001-5014-5089"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Carrara","raw_affiliation_strings":["ISTI-CNR,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR,Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066519737","display_name":"Marcella Cornia","orcid":"https://orcid.org/0000-0001-9640-9385"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcella Cornia","raw_affiliation_strings":["University of Modena and Reggio Emilia,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia,Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048928616","display_name":"Lorenzo Baraldi","orcid":"https://orcid.org/0000-0001-5125-4957"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Baraldi","raw_affiliation_strings":["University of Modena and Reggio Emilia,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia,Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047189288","display_name":"Fabrizio Falchi","orcid":"https://orcid.org/0000-0001-6258-5313"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Falchi","raw_affiliation_strings":["ISTI-CNR,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISTI-CNR,Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948871","display_name":"Rita Cucchiara","orcid":"https://orcid.org/0000-0002-2239-283X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rita Cucchiara","raw_affiliation_strings":["University of Modena and Reggio Emilia,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia,Italy","institution_ids":["https://openalex.org/I122346577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78227033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"22025","last_page":"22035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9678999781608582,"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":0.9678999781608582,"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":0.9627000093460083,"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/bridging","display_name":"Bridging (networking)","score":0.9371281862258911},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6609693169593811},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6127265691757202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.57082599401474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5473844408988953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4540981352329254},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3960428535938263},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08627709746360779},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.048517853021621704}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.9371281862258911},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6609693169593811},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6127265691757202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57082599401474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5473844408988953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4540981352329254},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3960428535938263},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08627709746360779},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.048517853021621704}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/iccv51701.2025.02045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02045","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:2411.19331","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19331","pdf_url":"https://arxiv.org/pdf/2411.19331","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"pmh:oai:iris.unimore.it:11380/1381190","is_oa":false,"landing_page_url":"https://hdl.handle.net/11380/1381190","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:zenodo.org:17315245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arXiv.2411.19331","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"ICCV, International Conference con Computer Vision, Honolulu, Hawaii, USA, October 19 \u2013 23","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.48550/arxiv.2411.19331","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.19331","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:2411.19331","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19331","pdf_url":"https://arxiv.org/pdf/2411.19331","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2084768720","https://openalex.org/W2043010663","https://openalex.org/W4248308508"],"abstract_inverted_index":{"Open-Vocabulary":[0],"Segmentation":[1],"(OVS)":[2],"aims":[3],"at":[4],"segmenting":[5],"images":[6],"from":[7,31,170],"free-form":[8],"textual":[9,94,134],"concepts":[10],"without":[11,109],"predefined":[12],"training":[13,118],"classes.":[14],"While":[15],"existing":[16],"vision-language":[17],"models":[18,53,189],"such":[19],"as":[20],"CLIP":[21,97],"can":[22,147,164],"generate":[23],"segmentation":[24,150],"masks":[25],"by":[26],"leveraging":[27],"coarse":[28],"spatial":[29,38,80],"information":[30],"Vision":[32],"Transformers,":[33],"they":[34],"face":[35],"challenges":[36],"in":[37,57,153],"localization":[39,143],"due":[40],"to":[41,98,112,127],"their":[42],"global":[43],"alignment":[44],"of":[45,82,88,96,102,125,145],"image":[46],"and":[47,142,156,160,188],"text":[48],"features.":[49],"Conversely,":[50],"self-supervised":[51],"visual":[52,59,131],"like":[54],"DINO":[55],"excel":[56],"fine-grained":[58],"encoding":[60],"but":[61],"lack":[62],"integration":[63],"with":[64,84,133],"language.":[65],"To":[66],"bridge":[67],"this":[68],"gap,":[69],"we":[70,120],"present":[71],"Talk2DINO,":[72],"a":[73,105],"novel":[74],"hybrid":[75],"approach":[76,91,163],"that":[77,138,161,176],"combines":[78],"the":[79,85,93,99,110,114,122,139,149,171],"accuracy":[81],"DINOv2":[83,103,126],"language":[86],"understanding":[87],"CLIP.":[89],"Our":[90],"aligns":[92],"embeddings":[95],"patch-level":[100],"features":[101],"through":[104],"learned":[106],"mapping":[107],"function":[108],"need":[111],"fine-tune":[113],"underlying":[115],"backbones.":[116],"At":[117],"time,":[119],"exploit":[121],"attention":[123],"maps":[124],"selectively":[128],"align":[129],"local":[130],"patches":[132],"embeddings.":[135],"We":[136],"show":[137],"powerful":[140],"semantic":[141],"abilities":[144],"Talk2DINO":[146,177],"enhance":[148],"process,":[151],"resulting":[152],"more":[154],"natural":[155],"less":[157],"noisy":[158],"segmentations,":[159],"our":[162],"also":[165],"effectively":[166],"distinguish":[167],"foreground":[168],"objects":[169],"background.":[172],"Experimental":[173],"results":[174],"demonstrate":[175],"achieves":[178],"state-of-the-art":[179],"performance":[180],"across":[181],"several":[182],"unsupervised":[183],"OVS":[184],"benchmarks.":[185],"Source":[186],"code":[187],"are":[190],"publicly":[191],"available":[192],"at:":[193],"https://lorebianchi98.github.io/Talk2DINO/.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
