{"id":"https://openalex.org/W4417479127","doi":"https://doi.org/10.1007/s44267-025-00102-0","title":"Visual-guided human-object interaction detection","display_name":"Visual-guided human-object interaction detection","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4417479127","doi":"https://doi.org/10.1007/s44267-025-00102-0"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-025-00102-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00102-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00102-0.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00102-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010125792","display_name":"Fang Nan","orcid":"https://orcid.org/0000-0001-5969-7066"},"institutions":[{"id":"https://openalex.org/I4210131919","display_name":"Xi'an University of Technology","ror":"https://ror.org/038avdt50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Nan","raw_affiliation_strings":["Xi\u2019an University of Technology, Xi\u2019an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an University of Technology, Xi\u2019an, China","institution_ids":["https://openalex.org/I4210131919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319347","display_name":"Ni Zhang","orcid":"https://orcid.org/0000-0002-6645-3366"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni Zhang","raw_affiliation_strings":["Xi\u2019an Jiaotong University, Xi\u2019an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377352","display_name":"Nian Liu","orcid":"https://orcid.org/0000-0002-0825-6081"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nian Liu","raw_affiliation_strings":["Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101119626","display_name":"Haochen Han","orcid":"https://orcid.org/0000-0002-0479-8932"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haochen Han","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043220498","display_name":"Binglu Wang","orcid":"https://orcid.org/0000-0002-9266-4685"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Binglu Wang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi\u2019an, China"],"raw_orcid":"https://orcid.org/0000-0002-9266-4685","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043220498"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37977383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9927999973297119,"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":0.9927999973297119,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0006000000284984708,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0006000000284984708,"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/leverage","display_name":"Leverage (statistics)","score":0.715499997138977},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5810999870300293},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5569000244140625},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5432999730110168},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5174000263214111},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4512999951839447},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.44909998774528503},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.40959998965263367}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.715499997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406000256538391},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5432999730110168},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5339999794960022},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5174000263214111},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2897999882698059},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2513999938964844},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-025-00102-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00102-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00102-0.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2544c6a924f441a4aa46a6d2aab59bd3","is_oa":true,"landing_page_url":"https://doaj.org/article/2544c6a924f441a4aa46a6d2aab59bd3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 3, Iss 1, Pp 1-13 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-025-00102-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00102-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00102-0.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2208624130","display_name":null,"funder_award_id":"2024CY2-GJHX08","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G6214012649","display_name":null,"funder_award_id":"62401447","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"},{"id":"https://openalex.org/G6713625503","display_name":null,"funder_award_id":"2024GX-YBXM-051","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G858926059","display_name":null,"funder_award_id":"62401447","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417479127.pdf","grobid_xml":"https://content.openalex.org/works/W4417479127.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2963078159","https://openalex.org/W3047258141","https://openalex.org/W3049440217","https://openalex.org/W3115935967","https://openalex.org/W3209102402","https://openalex.org/W4312695182","https://openalex.org/W4391248741","https://openalex.org/W4397026441","https://openalex.org/W4400188621"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"The":[1],"aim":[2],"of":[3,14,97,126,157,178],"human-object":[4],"interaction":[5],"(HOI)":[6],"detection":[7,81],"is":[8],"to":[9,30,40,70,144,152,191],"identify":[10],"the":[11,42,72,84,124,154,179,184,189],"triplets":[12],"consisting":[13],"a":[15,17,77,94,108,131,140,163],"human,":[16],"verb,":[18],"and":[19,56,117,139,149],"an":[20,67],"object.":[21],"Although":[22],"existing":[23],"methods":[24],"leverage":[25],"vision-language":[26],"models":[27],"(e.g.,":[28],"CLIP)":[29],"transfer":[31],"textual":[32],"information":[33],"for":[34,49,83,172],"unseen":[35,90],"compositions,":[36],"they":[37],"often":[38],"fail":[39],"capture":[41],"fine-grained":[43],"visual":[44,64],"cues":[45,151],"that":[46,183],"are":[47],"essential":[48],"complex":[50],"interactions,":[51],"such":[52],"as":[53,66],"spatial":[54],"configurations":[55],"object":[57],"affordances.":[58],"In":[59],"this":[60,102],"paper,":[61],"we":[62,105,129,161],"introduce":[63],"guidance":[65,98,165,170],"alternative":[68],"approach":[69],"achieving":[71],"desired":[73],"outcome.":[74],"We":[75],"define":[76],"new":[78,103,109,164],"visual-guided":[79,195],"HOI":[80,91,147],"task":[82],"first":[85],"time,":[86],"aiming":[87],"at":[88],"detecting":[89,194],"categories":[92],"using":[93],"small":[95],"number":[96],"examples.":[99],"To":[100],"support":[101],"task,":[104],"have":[106],"constructed":[107],"benchmark":[110],"dataset,":[111],"which":[112],"contains":[113],"one":[114],"base":[115],"set":[116],"four":[118],"novel":[119],"sets,":[120],"taking":[121],"into":[122],"account":[123],"peculiarities":[125],"HOI.":[127,196],"Then,":[128],"propose":[130],"VG-HOI":[132],"model":[133,186],"with":[134],"progressive":[135],"guidance,":[136],"query":[137],"reconstruction,":[138],"conditional":[141],"uncoupling":[142],"decoder":[143],"supplement":[145],"common":[146],"knowledge":[148],"task-specific":[150],"improve":[153,188],"generalization":[155],"capability":[156],"our":[158],"model.":[159],"Besides,":[160],"explore":[162],"sampling":[166],"strategy":[167],"\u2014":[168,171],"disentangled":[169],"real-world":[173],"scenarios.":[174],"Our":[175],"in-depth":[176],"analysis":[177],"experimental":[180],"results":[181],"shows":[182],"proposed":[185],"can":[187],"ability":[190],"generalize":[192],"when":[193]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-12-19T00:00:00"}