{"id":"https://openalex.org/W4415538135","doi":"https://doi.org/10.1145/3746027.3755751","title":"AlignCAT: Visual-Linguistic Alignment of Category and Attribute for Weakly Supervised Visual Grounding","display_name":"AlignCAT: Visual-Linguistic Alignment of Category and Attribute for Weakly Supervised Visual Grounding","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538135","doi":"https://doi.org/10.1145/3746027.3755751"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11572/467772","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048404371","display_name":"Yidan Wang","orcid":"https://orcid.org/0009-0007-9439-5291"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidan Wang","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0007-9439-5291","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045956356","display_name":"Chenyi Zhuang","orcid":"https://orcid.org/0009-0004-0700-5645"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Chenyi Zhuang","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0009-0004-0700-5645","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113306693","display_name":"Wutao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wutao Liu","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-5376-5289","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019391901","display_name":"Pan Gao","orcid":"https://orcid.org/0000-0002-4492-5430"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Gao","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-4492-5430","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6597-7248","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8211,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8781193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5100","last_page":"5109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9940000176429749,"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/matching","display_name":"Matching (statistics)","score":0.5874999761581421},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4634000062942505},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4627000093460083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43369999527931213},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.38339999318122864},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.3684999942779541},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.36500000953674316},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.3614000082015991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343000173568726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6912999749183655},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5569999814033508},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4627000093460083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755751","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755751","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unitn.it:11572/467772","is_oa":true,"landing_page_url":"https://hdl.handle.net/11572/467772","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unitn.it:11572/467772","is_oa":true,"landing_page_url":"https://hdl.handle.net/11572/467772","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4846938419","display_name":null,"funder_award_id":"No. 62272227","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2947312908","https://openalex.org/W2963109634","https://openalex.org/W2964284374","https://openalex.org/W2966683369","https://openalex.org/W2981663434","https://openalex.org/W3035097537","https://openalex.org/W3174965650","https://openalex.org/W4225517085","https://openalex.org/W4226396876","https://openalex.org/W4312815172","https://openalex.org/W4312980231","https://openalex.org/W4386071798","https://openalex.org/W4390873170"],"related_works":[],"abstract_inverted_index":{"Weakly":[0],"supervised":[1,53,136],"visual":[2,110],"grounding":[3],"(VG)":[4],"aims":[5],"to":[6,24,33,91,99],"locate":[7],"objects":[8],"in":[9,29],"images":[10],"based":[11],"on":[12,119,138],"text":[13,30,89],"descriptions.":[14],"Despite":[15],"significant":[16],"progress,":[17],"existing":[18,134],"methods":[19,137],"lack":[20],"strong":[21],"cross-modal":[22],"reasoning":[23],"distinguish":[25],"subtle":[26],"semantic":[27,48],"differences":[28],"expressions":[31],"due":[32],"category-based":[34],"and":[35,69,86,112,126],"attribute-based":[36],"ambiguity.":[37],"To":[38,55],"address":[39],"these":[40],"challenges,":[41],"we":[42,59],"introduce":[43],"AlignCAT,":[44],"a":[45,61,79],"novel":[46],"query-based":[47],"matching":[49],"framework":[50],"for":[51],"weakly":[52,135],"VG.":[54],"enhance":[56],"visual-linguistic":[57],"alignment,":[58],"propose":[60],"coarse-grained":[62],"alignment":[63,81],"module":[64,82],"that":[65],"utilizes":[66],"category":[67],"information":[68,85],"global":[70],"context,":[71],"effectively":[72],"mitigating":[73],"interference":[74],"from":[75],"category-inconsistent":[76],"objects.":[77],"Subsequently,":[78],"fine-grained":[80],"leverages":[83],"descriptive":[84],"captures":[87],"word-level":[88],"features":[90],"achieve":[92],"attribute":[93],"consistency.":[94],"By":[95],"exploiting":[96],"linguistic":[97],"cues":[98],"their":[100],"fullest":[101],"extent,":[102],"our":[103],"proposed":[104],"AlignCAT":[105,132],"progressively":[106],"filters":[107],"out":[108],"misaligned":[109],"queries":[111],"enhances":[113],"contrastive":[114],"learning":[115],"efficiency.":[116],"Extensive":[117],"experiments":[118],"three":[120],"VG":[121,140],"benchmarks,":[122],"namely":[123],"RefCOCO,":[124],"RefCOCO+,":[125],"RefCOCOg,":[127],"verify":[128],"the":[129],"superiority":[130],"of":[131],"against":[133],"two":[139],"tasks.":[141],"Our":[142],"code":[143],"is":[144],"available":[145],"at:":[146],"https://github.com/I2-Multimedia-Lab/AlignCAT.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-25T00:00:00"}