{"id":"https://openalex.org/W4415538056","doi":"https://doi.org/10.1145/3746027.3754936","title":"Addressing Granularity-induced Semantic Drift in OvOD via Graph-guided semantically consistent representation","display_name":"Addressing Granularity-induced Semantic Drift in OvOD via Graph-guided semantically consistent representation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538056","doi":"https://doi.org/10.1145/3746027.3754936"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754936","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754936","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100578416","display_name":"Hongyan Xu","orcid":"https://orcid.org/0000-0003-3846-5236"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyan Xu","raw_affiliation_strings":["Central South University, Changsha, China and The University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3846-5236","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China and The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhongze Wu","orcid":"https://orcid.org/0009-0009-0307-5597"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongze Wu","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0009-0307-5597","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101476181","display_name":"Ang He","orcid":"https://orcid.org/0009-0009-9853-1953"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ang He","raw_affiliation_strings":["Shanghai Maritime University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-9853-1953","affiliations":[{"raw_affiliation_string":"Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106746347","display_name":"Xi Lin","orcid":"https://orcid.org/0000-0001-5303-1191"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Lin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5303-1191","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103285702","display_name":"Yi Chen","orcid":"https://orcid.org/0000-0003-4283-7485"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yi Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4283-7485","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011334334","display_name":"Xiu Su","orcid":"https://orcid.org/0000-0002-9863-5404"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Su","raw_affiliation_strings":["Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-9863-5404","affiliations":[{"raw_affiliation_string":"Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14489093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7548","last_page":"7557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9990000128746033,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9990000128746033,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9897000193595886,"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/embedding","display_name":"Embedding","score":0.7279000282287598},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.546999990940094},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48080000281333923},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4580000042915344},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.382099986076355},{"id":"https://openalex.org/keywords/laplace-operator","display_name":"Laplace operator","score":0.38199999928474426},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3472999930381775},{"id":"https://openalex.org/keywords/graph-embedding","display_name":"Graph embedding","score":0.3425999879837036},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.3262999951839447},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.31940001249313354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870000004768372},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7279000282287598},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.546999990940094},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48080000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C165700671","wikidata":"https://www.wikidata.org/wiki/Q203484","display_name":"Laplace operator","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.375},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3467999994754791},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.3425999879837036},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30889999866485596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C115178988","wikidata":"https://www.wikidata.org/wiki/Q772067","display_name":"Laplacian matrix","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.25369998812675476},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754936","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754936","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:repository.hkust.edu.hk:1783.1-167580","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167580","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7148658183","display_name":null,"funder_award_id":"No. 62406347 and No. 62202302","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2886641317","https://openalex.org/W2948672349","https://openalex.org/W3034974675","https://openalex.org/W3138516171","https://openalex.org/W3168298428","https://openalex.org/W3173966474","https://openalex.org/W4312424618","https://openalex.org/W4312563428","https://openalex.org/W4312747482","https://openalex.org/W4312956471","https://openalex.org/W4386076396","https://openalex.org/W4402727267"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1],"detection":[2,55],"(OvOD)":[3],"uses":[4],"Vision-Language":[5],"Models":[6],"(VLMs)":[7],"to":[8,90],"detect":[9],"arbitrary":[10],"categories":[11],"specified":[12],"by":[13,25],"natural":[14],"language.":[15],"However,":[16],"existing":[17],"methods":[18],"often":[19],"struggle":[20],"with":[21,69],"performance":[22],"instability":[23],"caused":[24],"granularity-induced":[26],"semantic":[27],"drift,":[28],"which":[29],"arises":[30],"from":[31,73],"misaligned":[32],"label":[33],"embeddings":[34],"across":[35,137],"varying":[36],"levels":[37],"of":[38,158],"specificity.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,103],"propose":[44],"GraSecon,":[45],"a":[46,63,105],"Graph-guided":[47],"Semantically":[48],"Consistent":[49],"representation":[50],"framework":[51],"that":[52,111,148],"enhances":[53],"zero-shot":[54],"robustness":[56],"without":[57],"requiring":[58],"additional":[59],"training.":[60],"We":[61],"construct":[62],"hierarchical":[64],"Fine-grained":[65],"Semantic":[66,107,124],"Graph":[67],"enriched":[68],"visually":[70],"grounded":[71],"attributes":[72],"large":[74],"language":[75],"models":[76],"(LLMs).":[77],"This":[78],"graph":[79],"captures":[80],"hierarchical,":[81],"sibling":[82],"and":[83,95,113,133,144,160],"cross-level":[84],"relations,":[85],"enabling":[86],"controlled":[87],"Laplacian":[88,126],"refinement":[89],"harmonize":[91],"the":[92,142],"embedding":[93,135],"space":[94],"improve":[96],"visual-semantic":[97],"alignment.":[98],"To":[99],"strengthen":[100],"fine-grained":[101],"discriminability,":[102],"introduce":[104],"Key":[106],"Node":[108],"Mining":[109],"module":[110],"identifies":[112],"anchors":[114],"semantically":[115],"sensitive":[116],"nodes,":[117],"ensuring":[118],"robust":[119],"feature":[120],"representation.":[121],"Furthermore,":[122],"our":[123],"Relevance-Driven":[125],"Propagation":[127],"adaptively":[128],"propagates":[129],"information,":[130],"promoting":[131],"coherent":[132],"context-aware":[134],"alignment":[136],"granularities.":[138],"Extensive":[139],"experiments":[140],"on":[141],"iNatLoc":[143],"FSOD":[145],"datasets":[146],"demonstrate":[147],"GraSecon":[149],"outperforms":[150],"prior":[151],"SOTA":[152],"methods,":[153],"achieving":[154],"average":[155],"mAP50":[156],"improvements":[157],"6.5%":[159],"5.4%.":[161],"Code":[162],"is":[163],"publicly":[164],"available":[165],"at:":[166],"https://github.com/minoslab-csu/GraSecon.":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}