{"id":"https://openalex.org/W7123486680","doi":"https://doi.org/10.1109/mmsp64401.2025.11324104","title":"Prototype Embedding Optimization for Human-Object Interaction Detection in Livestreaming : PeO-HOI","display_name":"Prototype Embedding Optimization for Human-Object Interaction Detection in Livestreaming : PeO-HOI","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123486680","doi":"https://doi.org/10.1109/mmsp64401.2025.11324104"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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/A5122975460","display_name":"Menghui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Menghui Zhang","raw_affiliation_strings":["University of Technology,School of Information Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Technology,School of Information Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I78675632","https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122983900","display_name":"Jing 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"]},{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology,School of Information Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology,School of Information Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I78675632","https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109602582","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0002-5935-3877"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Chen","raw_affiliation_strings":["University of Technology,School of Information Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Technology,School of Information Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I78675632","https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122973642","display_name":"Li Zhuo","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"]},{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhuo","raw_affiliation_strings":["Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology,School of Information Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology,School of Information Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I78675632","https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5122975460"],"corresponding_institution_ids":["https://openalex.org/I78675632","https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66305441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.44020000100135803,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.44020000100135803,"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":0.2700999975204468,"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":0.094200000166893,"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/embedding","display_name":"Embedding","score":0.8476999998092651},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7290999889373779},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5903000235557556},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.571399986743927},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4487999975681305},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.42329999804496765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40220001339912415}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8476999998092651},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7290999889373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6424999833106995},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5903000235557556},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5591999888420105},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.42329999804496765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.37059998512268066},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.301800012588501},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":19,"referenced_works":["https://openalex.org/W2146055337","https://openalex.org/W2250539671","https://openalex.org/W2362855512","https://openalex.org/W2603203130","https://openalex.org/W2888096830","https://openalex.org/W3035735638","https://openalex.org/W3096057444","https://openalex.org/W3108878460","https://openalex.org/W3164894587","https://openalex.org/W3174164794","https://openalex.org/W3186621246","https://openalex.org/W4226451586","https://openalex.org/W4304945116","https://openalex.org/W4313057876","https://openalex.org/W4319300871","https://openalex.org/W4367187150","https://openalex.org/W4378675697","https://openalex.org/W4379619455","https://openalex.org/W4390875025"],"related_works":[],"abstract_inverted_index":{"Livestreaming":[0],"frequently":[1],"features":[2,83],"interactions":[3,34,51],"between":[4],"streamers":[5],"and":[6,13,79,130,138,141],"objects,":[7],"which":[8],"is":[9,92],"critical":[10],"for":[11,25,65],"understanding":[12],"regulating":[14],"online":[15],"content.":[16],"While":[17],"human-object":[18,66,85],"interaction":[19,67],"(HOI)":[20],"detection":[21,68,78,110,125,156],"has":[22],"advanced":[23],"significantly":[24],"general":[26],"video":[27],"tasks,":[28],"its":[29],"application":[30],"to":[31,81,94],"recognizing":[32],"streamer-object":[33],"in":[35,158],"livestreaming":[36,75,159],"often":[37],"exhibits":[38],"object":[39,77,96],"bias:":[40],"an":[41],"excessive":[42],"focuses":[43],"on":[44,132,143],"the":[45,48,53,74,102,108,115,122,133],"objects":[46],"at":[47],"expense":[49],"of":[50,84,127],"with":[52],"streamer.":[54],"To":[55],"address":[56],"this":[57],"challenge,":[58],"we":[59],"propose":[60],"a":[61],"prototype":[62,89],"embedding":[63,90],"optimization":[64,91],"(PeO-HOI).":[69],"Our":[70],"approach":[71],"first":[72],"preprocesses":[73],"using":[76],"tracking":[80],"extract":[82],"(HO)":[86],"pairs.":[87],"Subsequently,":[88],"applied":[93],"mitigate":[95],"bias":[97],"effects.":[98],"Finally,":[99],"after":[100],"modeling":[101],"spatio-temporal":[103],"context":[104],"among":[105],"HO":[106],"pairs,":[107],"HOI":[109,155],"results":[111,119,149],"are":[112],"generated":[113],"by":[114],"prediction":[116],"head.":[117],"Experimental":[118],"demonstrate":[120],"that":[121,151],"PeO-HOI":[123,152],"achieves":[124],"accuracies":[126],"37.19%@full,":[128],"51.42%@non-rare,":[129],"26.20%@rare":[131],"publicly":[134],"available":[135],"VidHOI":[136],"dataset,":[137],"45.13%@full,":[139],"62.78%@non-rare,":[140],"30.37%@rare":[142],"our":[144],"self-built":[145],"BJUT-HOI":[146],"dataset.":[147],"These":[148],"confirm":[150],"effectively":[153],"enhances":[154],"performance":[157],"scenarios.":[160]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}