{"id":"https://openalex.org/W4402753532","doi":"https://doi.org/10.1109/cvpr52733.2024.02663","title":"Disentangled Pre-Training for Human-Object Interaction Detection","display_name":"Disentangled Pre-Training for Human-Object Interaction Detection","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402753532","doi":"https://doi.org/10.1109/cvpr52733.2024.02663"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.02663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5037772907","display_name":"Zhuolong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuolong Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032087629","display_name":"Xing\u2019ao Li","orcid":"https://orcid.org/0000-0002-7016-8883"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingao Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038748720","display_name":"Changxing Ding","orcid":"https://orcid.org/0000-0001-7232-3181"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxing Ding","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007354180","display_name":"Xiangmin Xu","orcid":"https://orcid.org/0000-0003-4573-5820"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmin Xu","raw_affiliation_strings":["School of Future Technology, South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28191","last_page":"28201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.741838812828064},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7165199518203735},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6072553992271423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5262191295623779},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49772360920906067},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4223429262638092},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2809917628765106},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05106744170188904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741838812828064},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7165199518203735},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6072553992271423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5262191295623779},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49772360920906067},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4223429262638092},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2809917628765106},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05106744170188904},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.02663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G6413689652","display_name":null,"funder_award_id":"62076101","funder_id":"https://openalex.org/F4320320885","funder_display_name":"European Research Consortium for Informatics and Mathematics"}],"funders":[{"id":"https://openalex.org/F4320320885","display_name":"European Research Consortium for Informatics and Mathematics","ror":"https://ror.org/055zrhj18"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":98,"referenced_works":["https://openalex.org/W1551928752","https://openalex.org/W1861492603","https://openalex.org/W2077069816","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2480418144","https://openalex.org/W2888096830","https://openalex.org/W2888814092","https://openalex.org/W2890531016","https://openalex.org/W2908510526","https://openalex.org/W2961193895","https://openalex.org/W2962766617","https://openalex.org/W2962844592","https://openalex.org/W2963097937","https://openalex.org/W2963351448","https://openalex.org/W2964225075","https://openalex.org/W2982232158","https://openalex.org/W2983943451","https://openalex.org/W2984933298","https://openalex.org/W2990599624","https://openalex.org/W3009811369","https://openalex.org/W3034563158","https://openalex.org/W3034895839","https://openalex.org/W3034934229","https://openalex.org/W3034951775","https://openalex.org/W3035047011","https://openalex.org/W3035392611","https://openalex.org/W3035517717","https://openalex.org/W3035598501","https://openalex.org/W3047999543","https://openalex.org/W3086541756","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3097802466","https://openalex.org/W3101631402","https://openalex.org/W3106121867","https://openalex.org/W3106988096","https://openalex.org/W3107081247","https://openalex.org/W3109754877","https://openalex.org/W3109813419","https://openalex.org/W3165924482","https://openalex.org/W3166396011","https://openalex.org/W3168279596","https://openalex.org/W3168488421","https://openalex.org/W3169575272","https://openalex.org/W3171169846","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3181762391","https://openalex.org/W3195860412","https://openalex.org/W3202576436","https://openalex.org/W3212153990","https://openalex.org/W4200630800","https://openalex.org/W4226451294","https://openalex.org/W4297632532","https://openalex.org/W4297808394","https://openalex.org/W4312241193","https://openalex.org/W4312343844","https://openalex.org/W4312446811","https://openalex.org/W4312538795","https://openalex.org/W4312613394","https://openalex.org/W4312770707","https://openalex.org/W4312848112","https://openalex.org/W4312960102","https://openalex.org/W4312979210","https://openalex.org/W4313057390","https://openalex.org/W4313057876","https://openalex.org/W4313155487","https://openalex.org/W4313169234","https://openalex.org/W4323076451","https://openalex.org/W4382240040","https://openalex.org/W4386057783","https://openalex.org/W4386071869","https://openalex.org/W4386076270","https://openalex.org/W4386076271","https://openalex.org/W4386076501","https://openalex.org/W4387225628","https://openalex.org/W4389179984","https://openalex.org/W4389364035","https://openalex.org/W4390872009","https://openalex.org/W4390872886","https://openalex.org/W4390873185","https://openalex.org/W4390873645","https://openalex.org/W4390874582","https://openalex.org/W6639102338","https://openalex.org/W6754152559","https://openalex.org/W6757817989","https://openalex.org/W6781548975","https://openalex.org/W6781639750","https://openalex.org/W6784923837","https://openalex.org/W6785527955","https://openalex.org/W6785593291","https://openalex.org/W6786217690","https://openalex.org/W6791353385","https://openalex.org/W6799822930","https://openalex.org/W6809665980","https://openalex.org/W6843484045","https://openalex.org/W6856783258"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Detecting":[0],"human-object":[1],"interaction":[2,78,129],"(HOI)":[3],"has":[4],"long":[5],"been":[6],"limited":[7],"by":[8,20],"the":[9,75,90,96,107,128,137,143,158,171],"amount":[10],"of":[11,173,182],"supervised":[12],"data":[13],"available.":[14],"Recent":[15],"approaches":[16],"address":[17,61],"this":[18,62],"issue":[19],"pre-training":[21,44,54,91],"according":[22],"to":[23,60,73,157],"pseudo-labels,":[24],"which":[25],"align":[26],"object":[27,67],"regions":[28],"with":[29,95],"HOI":[30,43,57,98,159,175],"triplets":[31],"parsed":[32],"from":[33],"image":[34,145],"captions.":[35],"However,":[36],"pseudo-labeling":[37],"is":[38,93],"tricky":[39],"and":[40,69,77,124,146,187],"noisy,":[41],"making":[42],"a":[45,179],"complex":[46],"process.":[47],"Therefore,":[48,167],"we":[49,83,135],"propose":[50],"an":[51],"efficient":[52,103],"disentangled":[53],"method":[55],"for":[56,131],"detection":[58,68,76,99,108,160,176],"(DP-HOI)":[59],"problem.":[63],"First,":[64],"DP-HOI":[65,151],"utilizes":[66],"action":[70,116],"recognition":[71,117],"datasets":[72],"pre-train":[74],"decoder":[79,86,109,130],"layers,":[80],"respectively.":[81],"Then,":[82],"arrange":[84],"these":[85],"layers":[87],"so":[88],"that":[89],"architecture":[92],"consistent":[94],"downstream":[97],"task.":[100],"This":[101],"facilitates":[102],"knowledge":[104],"transfer.":[105],"Specifically,":[106],"identifies":[110],"reliable":[111],"human":[112,138],"instances":[113],"in":[114,142],"each":[115],"dataset":[118],"image,":[119],"generates":[120],"one":[121],"corresponding":[122],"query,":[123],"feeds":[125],"it":[126,168],"into":[127],"verb":[132,140],"classification.":[133],"Next,":[134],"combine":[136],"instance":[139],"predictions":[141],"same":[144],"impose":[147],"image-level":[148],"supervision.":[149],"The":[150,185],"structure":[152],"can":[153],"be":[154],"easily":[155],"adapted":[156],"task,":[161],"enabling":[162],"effective":[163],"model":[164],"parameter":[165],"initialization.":[166],"significantly":[169],"enhances":[170],"performance":[172],"existing":[174],"models":[177],"on":[178],"broad":[180],"range":[181],"rare":[183],"categories.":[184],"code":[186],"pre-trained":[188],"weight":[189],"are":[190],"available":[191],"at":[192],"https://github.com/xingaoliIDP-HOI.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}