{"id":"https://openalex.org/W4387968372","doi":"https://doi.org/10.1145/3581783.3611813","title":"Human-Object-Object Interaction: Towards Human-Centric Complex Interaction Detection","display_name":"Human-Object-Object Interaction: Towards Human-Centric Complex Interaction Detection","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968372","doi":"https://doi.org/10.1145/3581783.3611813"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611813","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611813","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611813","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611813","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101913594","display_name":"Mingxuan Zhang","orcid":"https://orcid.org/0009-0001-7302-5335"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxuan Zhang","raw_affiliation_strings":["Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0001-7302-5335","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011680564","display_name":"Xiao Wu","orcid":"https://orcid.org/0000-0002-8322-8558"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wu","raw_affiliation_strings":["Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-8322-8558","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045800438","display_name":"Zhaoquan Yuan","orcid":"https://orcid.org/0000-0002-4083-5155"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoquan Yuan","raw_affiliation_strings":["Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-4083-5155","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102015293","display_name":"Qi He","orcid":"https://orcid.org/0000-0002-6109-9417"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi He","raw_affiliation_strings":["Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-6109-9417","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079585917","display_name":"Xiang Huang","orcid":"https://orcid.org/0000-0001-5569-4255"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Huang","raw_affiliation_strings":["Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5569-4255","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University & Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4800084"],"apc_list":null,"apc_paid":null,"fwci":0.6056,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77011828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2233","last_page":"2242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9983000159263611,"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":0.8124487400054932},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.638120710849762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6187925934791565},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5622997283935547},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.549519956111908},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5488179922103882},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5136565566062927},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5008373260498047},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42894247174263},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3247755765914917},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.24080494046211243},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08511203527450562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124487400054932},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.638120710849762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187925934791565},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5622997283935547},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.549519956111908},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5488179922103882},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5136565566062927},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5008373260498047},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42894247174263},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3247755765914917},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24080494046211243},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08511203527450562},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611813","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611813","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611813","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3611813","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611813","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611813","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5699999928474426,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G146912938","display_name":null,"funder_award_id":"2020M683353","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G2938193788","display_name":null,"funder_award_id":"62372387,61802053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G444536043","display_name":null,"funder_award_id":"2682022JX007, 2682022KJ044, 2682023ZTPY004","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5269759798","display_name":null,"funder_award_id":"61802053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G701335782","display_name":null,"funder_award_id":"62372387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G713803178","display_name":null,"funder_award_id":"2682022JX007","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7274457630","display_name":null,"funder_award_id":"2682022KJ044","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320327586","display_name":"Institute of Applied Physics and Computational Mathematics","ror":"https://ror.org/03sxpbt26"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968372.pdf","grobid_xml":"https://content.openalex.org/works/W4387968372.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2097073572","https://openalex.org/W2108598243","https://openalex.org/W2193145675","https://openalex.org/W2526377930","https://openalex.org/W2563032747","https://openalex.org/W2611596598","https://openalex.org/W2618799552","https://openalex.org/W2752782242","https://openalex.org/W2806331055","https://openalex.org/W2888814092","https://openalex.org/W2895738954","https://openalex.org/W2903027645","https://openalex.org/W2904019187","https://openalex.org/W2955874753","https://openalex.org/W2962844592","https://openalex.org/W2962899219","https://openalex.org/W2962974137","https://openalex.org/W2963524571","https://openalex.org/W2963529931","https://openalex.org/W2963706010","https://openalex.org/W2964241181","https://openalex.org/W2990503944","https://openalex.org/W2991044292","https://openalex.org/W3034552520","https://openalex.org/W3034895839","https://openalex.org/W3034951775","https://openalex.org/W3035517717","https://openalex.org/W3043680005","https://openalex.org/W3049440217","https://openalex.org/W3096399932","https://openalex.org/W3101631402","https://openalex.org/W3106250896","https://openalex.org/W3107320732","https://openalex.org/W3109173645","https://openalex.org/W3164894587","https://openalex.org/W3171169846","https://openalex.org/W3173407577","https://openalex.org/W3176070213","https://openalex.org/W3184439416","https://openalex.org/W3207158043","https://openalex.org/W4214607465","https://openalex.org/W4281761811","https://openalex.org/W4287077836","https://openalex.org/W4292433237","https://openalex.org/W4304080525","https://openalex.org/W4312241193","https://openalex.org/W4312509322","https://openalex.org/W4312690503","https://openalex.org/W4312770707","https://openalex.org/W4385767582","https://openalex.org/W4390872466","https://openalex.org/W6601700763","https://openalex.org/W6607262404"],"related_works":["https://openalex.org/W2737719445","https://openalex.org/W4239098401","https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257","https://openalex.org/W3196817267","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Localizing":[0],"and":[1,31,37,76,100,144,204,226,243],"recognizing":[2],"interactive":[3],"actions":[4,134,185],"in":[5,23,195],"videos":[6],"is":[7,90],"a":[8,66,78,176,207],"pivotal":[9,192],"yet":[10],"intricate":[11,136],"task":[12,68],"that":[13,231],"paves":[14],"the":[15,33,46,82,108,116,127,158,163,171,181,211,223],"way":[16],"towards":[17],"profound":[18],"video":[19,178],"comprehension.":[20],"Recent":[21],"advancements":[22],"Human-Object":[24],"Interaction":[25,73,84],"(HOI)":[26],"detection,":[27],"which":[28],"involve":[29],"detecting":[30],"localizing":[32],"interactions":[34,137],"between":[35,138],"human":[36],"object":[38],"pairs,":[39],"have":[40],"undeniably":[41],"marked":[42],"significant":[43],"progress.":[44],"However,":[45],"realm":[47],"of":[48,54,92,113,214,240],"human-object-object":[49],"interaction,":[50],"an":[51],"essential":[52],"aspect":[53],"real-world":[55],"industrial":[56,196],"applications,":[57],"remains":[58],"largely":[59],"uncharted.":[60],"In":[61],"this":[62,188],"paper,":[63],"we":[64,168],"introduce":[65],"novel":[67],"referred":[69],"to":[70,131,149,170,191,210],"as":[71,206],"Human-Object-Object":[72,83],"(HOOI)":[74],"detection":[75,217],"present":[77],"cutting-edge":[79],"method":[80,233],"named":[81],"Network":[85],"(H2O-Net).":[86],"The":[87,103,184],"proposed":[88,224],"H2O-Net":[89],"comprised":[91],"two":[93,146],"principal":[94],"modules:":[95],"sequential":[96],"motion":[97],"feature":[98],"extraction":[99],"HOOI":[101,117,133,152,182,225],"modeling.":[102],"former":[104],"module":[105,129],"delves":[106],"into":[107],"gradually":[109],"evolving":[110],"visual":[111],"characteristics":[112],"entities":[114],"throughout":[115],"process,":[118],"harnessing":[119],"spatial-temporal":[120],"features":[121,148],"across":[122],"multiple":[123],"fine-grained":[124],"partitions.":[125],"Conversely,":[126],"latter":[128],"aspires":[130],"encapsulate":[132],"through":[135],"entities.":[139],"It":[140],"commences":[141],"by":[142,174,238],"capturing":[143],"amalgamating":[145],"sub-interaction":[147],"extract":[150],"comprehensive":[151],"features,":[153],"subsequently":[154],"refining":[155],"them":[156],"using":[157],"interaction":[159,215],"cues":[160],"embedded":[161],"within":[162,187],"long-term":[164],"global":[165],"context.":[166],"Furthermore,":[167],"contribute":[169],"research":[172],"community":[173],"constructing":[175],"new":[177],"dataset,":[179],"dubbed":[180],"dataset.":[183],"encompassed":[186],"dataset":[189],"pertain":[190],"operational":[193],"behaviors":[194],"manufacturing,":[197],"imbuing":[198],"it":[199],"with":[200],"substantial":[201],"application":[202],"potential":[203],"serving":[205],"valuable":[208],"addition":[209],"existing":[212,235],"repertoire":[213],"action":[216],"datasets.":[218],"Experimental":[219],"evaluations":[220],"conducted":[221],"on":[222],"widely-used":[227],"AVA":[228],"datasets":[229],"demonstrate":[230],"our":[232],"outperforms":[234],"state-of-the-art":[236],"techniques":[237],"margins":[239],"6.16":[241],"mAP":[242],"1.9":[244],"mAP,":[245],"respectively,":[246],"thus":[247],"substantiating":[248],"its":[249],"effectiveness.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}