{"id":"https://openalex.org/W4407129516","doi":"https://doi.org/10.1109/cbmi62980.2024.10859215","title":"Is CLIP the main roadblock for fine-grained open-world perception?","display_name":"Is CLIP the main roadblock for fine-grained open-world perception?","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4407129516","doi":"https://doi.org/10.1109/cbmi62980.2024.10859215"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi62980.2024.10859215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi62980.2024.10859215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107640606","display_name":"Lorenzo Bianchi","orcid":"https://orcid.org/0009-0005-3519-2991"},"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":["CNR-ISTI,Pisa,Italy"],"raw_orcid":"https://orcid.org/0009-0005-3519-2991","affiliations":[{"raw_affiliation_string":"CNR-ISTI,Pisa,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":["CNR-ISTI,Pisa,Italy"],"raw_orcid":"https://orcid.org/0000-0001-5014-5089","affiliations":[{"raw_affiliation_string":"CNR-ISTI,Pisa,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":["CNR-ISTI,Pisa,Italy"],"raw_orcid":"https://orcid.org/0000-0003-3011-2487","affiliations":[{"raw_affiliation_string":"CNR-ISTI,Pisa,Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","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":["CNR-ISTI,Pisa,Italy"],"raw_orcid":"https://orcid.org/0000-0001-6258-5313","affiliations":[{"raw_affiliation_string":"CNR-ISTI,Pisa,Italy","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I122991210"],"apc_list":null,"apc_paid":null,"fwci":1.8405,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9019669,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9882000088691711,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9882000088691711,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9413999915122986,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9345999956130981,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.620582103729248},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5087514519691467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3380468189716339},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1729995310306549}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.620582103729248},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5087514519691467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3380468189716339},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1729995310306549},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cbmi62980.2024.10859215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi62980.2024.10859215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},{"id":"pmh:oai:dnet:iris________::1cfca8cded35a196f926a173c91c67d7","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article"},{"id":"pmh:oai:zenodo.org:17314976","is_oa":true,"landing_page_url":"https://doi.org/10.1109/CBMI62980.2024.10859215","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":"CBMI, International Conference on Content-Based Multimedia Indexing, Reykjavik, Iceland, 18-20 September 2024","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:dnet:iris________::1cfca8cded35a196f926a173c91c67d7","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5899999737739563,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2985951359","https://openalex.org/W2988823324","https://openalex.org/W3083505552","https://openalex.org/W3091588028","https://openalex.org/W3092820619","https://openalex.org/W3094172275","https://openalex.org/W3160179442","https://openalex.org/W3173220247","https://openalex.org/W3205786327","https://openalex.org/W3213100861","https://openalex.org/W4285265603","https://openalex.org/W4303444819","https://openalex.org/W4312424618","https://openalex.org/W4312563428","https://openalex.org/W4312747482","https://openalex.org/W4313026212","https://openalex.org/W4386065383","https://openalex.org/W4386071687","https://openalex.org/W4386076396","https://openalex.org/W4386076683","https://openalex.org/W4390873321","https://openalex.org/W4390873426","https://openalex.org/W4402716047","https://openalex.org/W4402727832","https://openalex.org/W4402754023","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6784333009","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6843071136","https://openalex.org/W6845354634"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Modern":[0],"applications":[1],"increasingly":[2],"demand":[3],"flexible":[4],"computer":[5],"vision":[6],"models":[7],"that":[8,161,222],"adapt":[9],"to":[10,35,37,46,124,184,203,241],"novel":[11],"concepts":[12],"not":[13,195],"encountered":[14],"during":[15],"training.":[16],"This":[17],"necessity":[18],"is":[19,43,167,189,251],"pivotal":[20],"in":[21,95,176,191],"emerging":[22],"domains":[23],"like":[24,68,105],"extended":[25],"reality,":[26],"robotics,":[27],"and":[28,108,156],"autonomous":[29],"driving,":[30],"which":[31,212],"require":[32],"the":[33,44,71,91,126,131,135,150,162,170,177,204,207,232,235],"ability":[34,45],"respond":[36],"open-world":[38,77],"stimuli.":[39],"A":[40],"key":[41],"ingredient":[42],"identify":[47],"objects":[48],"based":[49],"on":[50,83,90],"free-form":[51],"textual":[52],"queries":[53],"defined":[54],"at":[55,197,253],"inference":[56,198],"time":[57,199],"-":[58,98],"a":[59,115,142],"task":[60],"known":[61],"as":[62],"open-vocabulary":[63,96,153],"object":[64,103,121,154,174,216],"detection.":[65],"Multimodal":[66],"backbones":[67,238],"CLIP":[69,178,192,224],"are":[70],"main":[72],"enabling":[73],"technology":[74],"for":[75,100,201,247],"current":[76],"perception":[78],"solutions.":[79],"Despite":[80],"performing":[81],"well":[82],"generic":[84],"queries,":[85],"recent":[86],"studies":[87],"highlighted":[88],"limitations":[89,123,151],"fine-grained":[92,143,165,187,229,243],"recognition":[93,122],"capabilities":[94],"settings":[97],"i.e.,":[99],"distinguishing":[101],"subtle":[102],"features":[104],"color,":[106],"shape,":[107],"material.":[109],"In":[110],"this":[111],"paper,":[112],"we":[113,182],"perform":[114],"detailed":[116],"examination":[117],"of":[118,133,152,164,173,206,237],"these":[119,249],"openvocabulary":[120],"find":[125],"root":[127],"cause.":[128],"We":[129],"evaluate":[130],"performance":[132],"CLIP,":[134],"most":[136],"commonly":[137],"used":[138],"vision-language":[139],"backbone,":[140],"against":[141],"objectmatching":[144],"benchmark,":[145],"revealing":[146],"interesting":[147],"analogies":[148],"between":[149],"detectors":[155],"their":[157],"backbones.":[158],"Experiments":[159],"suggest":[160],"lack":[163],"understanding":[166],"caused":[168],"by":[169],"poor":[171],"separability":[172],"characteristics":[175],"latent":[179],"space.":[180],"Therefore,":[181],"try":[183],"understand":[185],"whether":[186],"knowledge":[188],"present":[190],"embeddings":[193],"but":[194],"exploited":[196],"due,":[200],"example,":[202],"unsuitability":[205],"cosine":[208],"similarity":[209],"matching":[210],"function,":[211],"may":[213],"discard":[214],"important":[215],"characteristics.":[217],"Our":[218],"preliminary":[219],"experiments":[220,250],"show":[221],"simple":[223],"latent-space":[225],"re-projections":[226],"help":[227],"separate":[228],"concepts,":[230],"paving":[231],"way":[233],"towards":[234],"development":[236],"inherently":[239],"able":[240],"process":[242],"details.":[244],"The":[245],"code":[246],"reproducing":[248],"available":[252],"https://github.com/lorebianchi98/FG-CLIP.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}