{"id":"https://openalex.org/W7162211121","doi":"https://doi.org/10.1145/3817607","title":"KdM-Net: Knowledge-Driven Memory Network for Long-Tailed Human-Object Interaction in Livestreaming","display_name":"KdM-Net: Knowledge-Driven Memory Network for Long-Tailed Human-Object Interaction in Livestreaming","publication_year":2026,"publication_date":"2026-05-23","ids":{"openalex":"https://openalex.org/W7162211121","doi":"https://doi.org/10.1145/3817607"},"language":"en","primary_location":{"id":"doi:10.1145/3817607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817607","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3817607","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122975460","display_name":"Menghui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghui Zhang","raw_affiliation_strings":["School of Integrated Circuits, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0032-0745","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015642321","display_name":"J C Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Integrated Circuits, Beijing University of Technology, Beijing, China and Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1290-0738","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing University of Technology, Beijing, China and Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136854942","display_name":"Lin Chen","orcid":"https://orcid.org/0009-0006-5234-7606"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["School of Integrated Circuits, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5234-7606","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136832602","display_name":"Li Zhuo","orcid":"https://orcid.org/0000-0002-9937-2669"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhuo","raw_affiliation_strings":["School of Integrated Circuits, Beijing University of Technology, Beijing, China and Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9937-2669","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Beijing University of Technology, Beijing, China and Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64696845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7998999953269958,"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":0.7998999953269958,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03530000150203705,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.01360000018030405,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/classifier","display_name":"Classifier (UML)","score":0.508400022983551},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.47760000824928284},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47279998660087585},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.39660000801086426},{"id":"https://openalex.org/keywords/cyberspace","display_name":"Cyberspace","score":0.3578000068664551},{"id":"https://openalex.org/keywords/covert","display_name":"Covert","score":0.3264999985694885},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.31450000405311584},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8794999718666077},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47269999980926514},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C2781241145","wikidata":"https://www.wikidata.org/wiki/Q204606","display_name":"Cyberspace","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C2779338814","wikidata":"https://www.wikidata.org/wiki/Q5179285","display_name":"Covert","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2780378701","wikidata":"https://www.wikidata.org/wiki/Q7451195","display_name":"Sentence processing","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3817607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817607","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3817607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817607","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6816412638","display_name":null,"funder_award_id":"62471013, 61971016","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2146055337","https://openalex.org/W2250539671","https://openalex.org/W2603203130","https://openalex.org/W2745461083","https://openalex.org/W2888096830","https://openalex.org/W3035598501","https://openalex.org/W3035735638","https://openalex.org/W3096057444","https://openalex.org/W3096609285","https://openalex.org/W3106121867","https://openalex.org/W3164894587","https://openalex.org/W3168279596","https://openalex.org/W3174164794","https://openalex.org/W3186621246","https://openalex.org/W4226451586","https://openalex.org/W4312574495","https://openalex.org/W4312960102","https://openalex.org/W4313057876","https://openalex.org/W4319300871","https://openalex.org/W4321512621","https://openalex.org/W4367187150","https://openalex.org/W4378675697","https://openalex.org/W4379619455","https://openalex.org/W4379986307","https://openalex.org/W4386071869","https://openalex.org/W4390872886","https://openalex.org/W4390875025","https://openalex.org/W4392172801","https://openalex.org/W4396612938","https://openalex.org/W4400075398","https://openalex.org/W4401847474","https://openalex.org/W4404724811","https://openalex.org/W4410698459","https://openalex.org/W6893711219","https://openalex.org/W7123486680"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,5,16,73,97,101,134,158,218,229,236],"continuous":[2],"advancement":[3],"of":[4,18,76,100,162,212,239],"livestreaming":[6,42,249],"industry,":[7],"streamers":[8],"as":[9,23],"content":[10],"producers":[11],"pose":[12],"significant":[13],"challenges":[14],"to":[15,138,150,177,184],"timeliness":[17],"regulatory":[19],"response":[20],"mechanisms,":[21],"emerging":[22],"a":[24,36,86,125,145,171],"critical":[25],"weak":[26],"link":[27],"in":[28,39,80,94,248],"cyberspace":[29],"governance.":[30],"Human-object":[31],"interaction":[32,185],"(HOI)":[33],"detection":[34,201,210,244],"plays":[35],"pivotal":[37],"role":[38],"understanding":[40],"multimodal":[41,81,159],"videos.":[43],"In":[44],"mainstream":[45],"healthy":[46],"online":[47],"ecosystems,":[48],"normal":[49],"HOI":[50,64,93,122,168,200,209,243],"categories":[51,164,186],"dominate,":[52],"while":[53],"rare":[54,163],"ones":[55],"are":[56,111,131],"extremely":[57],"scarce,":[58],"i.e.,":[59],"long-tail":[60],"distribution":[61,191],"that":[62,165,206],"hinders":[63],"models":[65,78],"from":[66],"effectively":[67],"detecting":[68],"streamer":[69],"violations.":[70],"Driven":[71],"by":[72],"transformative":[74],"potential":[75],"foundation":[77],"(FMs)":[79],"video":[82],"understanding,":[83],"we":[84,143],"propose":[85],"knowledge-driven":[87,172],"memory":[88,173],"network":[89],"(KdM-Net)":[90],"for":[91,157,242],"long-tailed":[92,167,190],"livestreaming,":[95],"leveraging":[96],"extensive":[98],"capabilities":[99],"contrastive":[102],"language-image":[103],"pretraining":[104],"(CLIP)":[105],"model.":[106],"First,":[107],"human-object":[108],"(HO)":[109],"pairs":[110],"generated":[112],"and":[113,153,182,198,215,223,226,245],"modeled":[114],"using":[115],"general":[116],"object":[117],"detector/tracker.":[118],"After":[119],"converting":[120],"each":[121],"label":[123],"into":[124],"short":[126],"sentence":[127],"description,":[128],"text":[129,136,154],"embeddings":[130],"extracted":[132],"via":[133],"CLIP":[135],"encoder":[137],"initialize":[139],"classifier":[140],"weights.":[141],"Notably,":[142],"introduce":[144],"visual-textual":[146],"knowledge":[147,160],"transfer":[148],"strategy":[149],"align":[151],"visual":[152],"features,":[155],"complementing":[156],"deficit":[161],"plague":[166],"distributions.":[169],"Finally,":[170],"module":[174],"is":[175],"designed":[176],"dynamically":[178],"assign":[179],"adaptive":[180],"weights":[181],"attention":[183],"based":[187],"on":[188,217,228],"their":[189],"characteristics,":[192],"mitigating":[193],"model":[194],"forgetting":[195],"tail":[196],"data":[197],"enhancing":[199],"performance.":[202],"Experimental":[203],"results":[204],"demonstrate":[205],"KdM-Net":[207,241],"achieves":[208],"accuracies":[211],"37.33@full,":[213],"50.63%@non-rare,":[214],"27.14%@rare":[216],"publicly":[219],"available":[220],"VidHOI":[221],"dataset,":[222],"45.41%@full,":[224],"61.77%@non-rare,":[225],"31.95%@rare":[227],"self-built":[230],"BJUT-HOI":[231],"dataset.":[232],"These":[233],"fundings":[234],"validate":[235],"generalization":[237],"power":[238],"our":[240],"its":[246],"competitiveness":[247],"scenarios.":[250]},"counts_by_year":[],"updated_date":"2026-07-08T06:17:01.165560","created_date":"2026-05-24T00:00:00"}