{"id":"https://openalex.org/W7137936294","doi":"https://doi.org/10.1609/aaai.v40i8.37590","title":"From Scene to Object: Enhancing Open-Vocabulary Object Detection via Foreground-Background Context Reasoning","display_name":"From Scene to Object: Enhancing Open-Vocabulary Object Detection via Foreground-Background Context Reasoning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137936294","doi":"https://doi.org/10.1609/aaai.v40i8.37590"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37590","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37590","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37590/41552","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37590/41552","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129703115","display_name":"Yanqi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqi Li","raw_affiliation_strings":["Beihang University\nZhongguancun Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University\nZhongguancun Laboratory","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733903","display_name":"Jianwei Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Niu","raw_affiliation_strings":["Beihang University\nZhongguancun Laboratory\nHangzhou Innovation Institute of Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University\nZhongguancun Laboratory\nHangzhou Innovation Institute of Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125697327","display_name":"Ningbo Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningbo Gu","raw_affiliation_strings":["Beihang University\nHangzhou Innovation Institute of Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University\nHangzhou Innovation Institute of Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129708721","display_name":"Tao Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Ren","raw_affiliation_strings":["University of the Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23492981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6601","last_page":"6609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9585000276565552,"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":0.9585000276565552,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.021900000050663948,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.007699999958276749,"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/object-detection","display_name":"Object detection","score":0.6754999756813049},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5612999796867371},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5408999919891357},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5375999808311462},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.43619999289512634},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.364300012588501},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3522000014781952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960000038146973},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6754999756813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6407999992370605},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5408999919891357},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.43619999289512634},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.364300012588501},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37590","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37590","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37590/41552","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37590","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37590","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37590","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37590/41552","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.648176372051239,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2344760762","display_name":null,"funder_award_id":"62372027","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137936294.pdf","grobid_xml":"https://content.openalex.org/works/W7137936294.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-Vocabulary":[0],"Object":[1],"Detection":[2],"(OVOD)":[3],"aims":[4],"to":[5,105,124,143],"detect":[6],"both":[7],"known":[8],"and":[9,54,86,138,159,168],"novel":[10,64,91,127,164],"categories":[11,165],"in":[12,25,96],"complex":[13],"visual":[14,37],"scenes,":[15],"surpassing":[16],"the":[17,78,107,115],"limitations":[18],"of":[19,63,81,117],"conventional":[20],"closed-set":[21],"detectors.":[22],"Recent":[23],"advances":[24],"vision-language":[26],"models":[27],"(VLMs)":[28],"like":[29],"CLIP":[30],"have":[31],"enabled":[32],"zero-shot":[33],"recognition":[34],"by":[35,50,120],"aligning":[36],"features":[38],"with":[39],"large-scale":[40],"textual":[41],"embeddings.":[42],"However,":[43],"current":[44],"OVOD":[45],"approaches":[46],"often":[47],"fall":[48],"short":[49],"overlooking":[51],"critical":[52],"contextual":[53],"semantic":[55],"cues":[56],"necessary":[57],"for":[58],"discovering":[59],"a":[60,72,90,149],"broader":[61],"range":[62],"objects.":[65],"To":[66],"address":[67],"this,":[68],"we":[69],"propose":[70],"BFDet,":[71],"scene-to-object":[73,92],"reasoning":[74,93],"framework":[75],"that":[76],"leverages":[77],"complementary":[79],"strengths":[80],"Large":[82],"Language":[83],"Models":[84],"(LLMs)":[85],"VLMs.":[87],"BFDet":[88,152],"introduces":[89],"mechanism":[94],"grounded":[95],"foreground-background":[97],"context":[98],"interaction.":[99],"It":[100],"first":[101],"uses":[102],"high-confidence":[103],"objects":[104,119],"infer":[106],"scene-level":[108],"background.":[109],"This":[110],"scene":[111],"background":[112],"then":[113],"guides":[114],"discovery":[116],"foreground":[118],"prompting":[121],"an":[122],"LLM":[123],"generate":[125],"scene-sensitive":[126],"object":[128],"candidates.":[129],"These":[130],"candidates":[131],"are":[132],"subsequently":[133],"verified":[134],"through":[135],"cross-modal":[136],"alignment":[137],"used":[139],"as":[140,148],"high-quality":[141],"pseudo-labels":[142],"enrich":[144],"detector":[145],"training.":[146],"Designed":[147],"plug-and-play":[150],"module,":[151],"integrates":[153],"seamlessly":[154],"into":[155],"existing":[156],"detection":[157],"pipelines":[158],"consistently":[160],"improves":[161],"performance":[162],"on":[163],"across":[166],"COCO":[167],"LVIS":[169],"benchmarks.":[170]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}