{"id":"https://openalex.org/W3033238119","doi":"https://doi.org/10.1145/3372278.3390671","title":"Human Object Interaction Detection via Multi-level Conditioned Network","display_name":"Human Object Interaction Detection via Multi-level Conditioned Network","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033238119","doi":"https://doi.org/10.1145/3372278.3390671","mag":"3033238119"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390671","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-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/A5101441137","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-8241-9320"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Sun","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107247543","display_name":"Xinwen Hu","orcid":"https://orcid.org/0000-0001-9566-5424"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinwen Hu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"https://orcid.org/0000-0003-3092-424X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongwei Ren","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101441137"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.0747,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.7948007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.8155890703201294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6991789937019348},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6439201235771179},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6267575025558472},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.5699150562286377},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5331083536148071},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5247288346290588},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5219542384147644},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.49116250872612},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4849098324775696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48207980394363403},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4646351635456085},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44259509444236755},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4358222484588623},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4259330630302429},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3595389723777771},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07424041628837585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155890703201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6991789937019348},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6439201235771179},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6267575025558472},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.5699150562286377},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5331083536148071},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5247288346290588},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5219542384147644},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.49116250872612},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4849098324775696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48207980394363403},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4646351635456085},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44259509444236755},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4358222484588623},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4259330630302429},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3595389723777771},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07424041628837585},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3372278.3390671","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W874179280","https://openalex.org/W1677182931","https://openalex.org/W2104408738","https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2413641397","https://openalex.org/W2524357132","https://openalex.org/W2617044865","https://openalex.org/W2619098136","https://openalex.org/W2749708282","https://openalex.org/W2760103357","https://openalex.org/W2765137706","https://openalex.org/W2808168184","https://openalex.org/W2808615764","https://openalex.org/W2887585070","https://openalex.org/W2888096830","https://openalex.org/W2889811054","https://openalex.org/W2896948286","https://openalex.org/W2951319586","https://openalex.org/W2951323451","https://openalex.org/W2955882737","https://openalex.org/W2962954773","https://openalex.org/W2963228276","https://openalex.org/W2963814095","https://openalex.org/W2964225075","https://openalex.org/W2981385984","https://openalex.org/W2981578638","https://openalex.org/W2981660636","https://openalex.org/W2981820283","https://openalex.org/W2981895973","https://openalex.org/W2990599624","https://openalex.org/W3099651916","https://openalex.org/W3102566412","https://openalex.org/W3103651098","https://openalex.org/W4249013746"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W2468279273","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W2354198838","https://openalex.org/W1537496349","https://openalex.org/W4387272257"],"abstract_inverted_index":{"As":[0],"one":[1],"of":[2,25,59,108],"the":[3,23,56,105,119,125,150],"essential":[4],"problems":[5],"in":[6],"scene":[7],"understanding,":[8],"human":[9,19,50,94],"object":[10,51,98],"interaction":[11,52],"detection":[12],"(HOID)":[13],"aims":[14],"to":[15,102,123,149],"recognize":[16],"fine-grained":[17],"object-specific":[18],"actions,":[20],"which":[21,45],"demands":[22],"capabilities":[24],"both":[26],"visual":[27,41,74,86],"perception":[28],"and":[29,97,113,138],"reasoning.":[30],"Existing":[31],"methods":[32],"based":[33],"on":[34,132],"convolutional":[35],"neural":[36],"network":[37,67],"(CNN)":[38],"utilize":[39],"diverse":[40],"features":[42,122],"for":[43,48,84],"HOID,":[44],"are":[46],"insufficient":[47],"complex":[49],"understanding.":[53],"To":[54],"enhance":[55],"reasoning":[57],"capablity":[58],"CNN,":[60],"we":[61,77,117],"propose":[62],"a":[63,79],"novel":[64],"multi-level":[65,85],"conditioned":[66],"that":[68,144],"fuses":[69],"extra":[70,91],"spatial-semantic":[71],"knowledge":[72,92],"with":[73],"features.":[75],"Specifically,":[76],"construct":[78],"multi-branch":[80],"CNN":[81,109],"as":[82,100],"backbone":[83],"representation.":[87],"We":[88],"then":[89],"encode":[90],"including":[93],"body":[95],"structure":[96],"context":[99],"condition":[101],"dynamically":[103],"influence":[104],"feature":[106],"extraction":[107],"by":[110],"affine":[111],"transformation":[112],"attention":[114],"mechanism.":[115],"Finally,":[116],"fuse":[118],"modulated":[120],"multimodal":[121],"distinguish":[124],"interactions.":[126],"The":[127,140],"proposed":[128],"method":[129,146],"is":[130,147],"evaluated":[131],"two":[133],"most":[134],"frequently-used":[135],"benchmarks,":[136],"HICO-DET":[137],"V-COCO.":[139],"experiment":[141],"results":[142],"show":[143],"our":[145],"superior":[148],"state-of-the-arts.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}