{"id":"https://openalex.org/W7123345922","doi":"https://doi.org/10.1109/lsp.2026.3652953","title":"Semantic-Spatial Guided Reasoning for Human-Object Interaction Detection","display_name":"Semantic-Spatial Guided Reasoning for Human-Object Interaction Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123345922","doi":"https://doi.org/10.1109/lsp.2026.3652953"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3652953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3652953","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101977096","display_name":"Ping Cao","orcid":"https://orcid.org/0000-0002-2120-1392"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Cao","raw_affiliation_strings":["Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2120-1392","affiliations":[{"raw_affiliation_string":"Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020066993","display_name":"C. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunjie Zhang","raw_affiliation_strings":["Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1161-8995","affiliations":[{"raw_affiliation_string":"Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122882576","display_name":"Xiaolong Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Zheng","raw_affiliation_strings":["State Key Laboratory of Multimodal Artifical Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0405-5458","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artifical Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122864064","display_name":"Yao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhao","raw_affiliation_strings":["Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8581-9554","affiliations":[{"raw_affiliation_string":"Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.04436616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"551","last_page":"555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9211999773979187,"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":0.9211999773979187,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.022299999371170998,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.008299999870359898,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/spatial-intelligence","display_name":"Spatial intelligence","score":0.6521999835968018},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6521000266075134},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5162000060081482},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5130000114440918},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4196999967098236},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.41449999809265137},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40639999508857727},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.3538999855518341},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3368000090122223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789900004863739},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.6521999835968018},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6521000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.632099986076355},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5130000114440918},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3546999990940094},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3652953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3652953","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.762606680393219,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2606856552","display_name":null,"funder_award_id":"72225011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3775132284","display_name":null,"funder_award_id":"72434005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5100775866","display_name":null,"funder_award_id":"2025JBZX062","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8992985131","display_name":null,"funder_award_id":"62476021","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2796314858","https://openalex.org/W2964225075","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3151099711","https://openalex.org/W3174164794","https://openalex.org/W3181762391","https://openalex.org/W4226372179","https://openalex.org/W4312446811","https://openalex.org/W4312848112","https://openalex.org/W4312960102","https://openalex.org/W4313009108","https://openalex.org/W4386071869","https://openalex.org/W4386076270","https://openalex.org/W4386076271","https://openalex.org/W4387042228","https://openalex.org/W4388283443","https://openalex.org/W4389473932","https://openalex.org/W4390872886","https://openalex.org/W4402389306","https://openalex.org/W4402716073","https://openalex.org/W4402968873","https://openalex.org/W4404562945","https://openalex.org/W4408305026","https://openalex.org/W4409326045","https://openalex.org/W4409368444","https://openalex.org/W4409911506","https://openalex.org/W4410949684","https://openalex.org/W4413145972","https://openalex.org/W4414008358","https://openalex.org/W4414404745","https://openalex.org/W4415195679","https://openalex.org/W4415708341","https://openalex.org/W4415797444"],"related_works":[],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"(HOI)":[2],"detection":[3],"requires":[4],"not":[5],"only":[6],"recognizingwhatthe":[7],"interaction":[8,54,105],"is":[9,33],"but":[10],"also":[11],"understandingwhereit":[12],"occurs.":[13],"Although":[14],"recent":[15],"methods":[16,119],"have":[17],"achieved":[18],"remarkable":[19],"progress,":[20],"they":[21],"often":[22],"lack":[23],"effective":[24],"joint":[25],"modeling":[26,58],"of":[27,129],"spatial":[28,64,70,75],"and":[29,62,77,102,111,123],"semantic":[30,60,81,86],"information,":[31],"which":[32],"essential":[34],"for":[35],"accurate":[36],"reasoning":[37,55,91,101,132],"in":[38],"complex":[39],"scenes.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"propose":[45],"a":[46,79],"Semantic-Spatial":[47],"Guided":[48],"Reasoning":[49],"(SSGR)":[50],"framework":[51],"that":[52,114],"performs":[53],"by":[56],"jointly":[57],"global":[59,80],"cues":[61],"fine-grained":[63],"priors.":[65],"Specifically,":[66],"SSGR":[67,115],"constructs":[68],"pair-specific":[69],"layouts":[71],"to":[72,83],"encode":[73],"detailed":[74],"relationships":[76],"introduces":[78],"decoder":[82],"learn":[84],"category-aware":[85],"representations.":[87],"A":[88],"semantic-spatial":[89,131],"guided":[90],"module":[92],"further":[93],"adaptively":[94],"fuses":[95],"these":[96],"complementary":[97],"cues,":[98],"enabling":[99],"unified":[100],"more":[103],"discriminative":[104],"understanding.":[106],"Extensive":[107],"experiments":[108],"on":[109],"HICO-DET":[110],"V-COCO":[112],"demonstrate":[113],"consistently":[116],"outperforms":[117],"prior":[118],"under":[120],"both":[121],"standard":[122],"zero-shot":[124],"settings,":[125],"validating":[126],"the":[127],"effectiveness":[128],"our":[130],"paradigm.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-01-14T00:00:00"}