{"id":"https://openalex.org/W7123365217","doi":"https://doi.org/10.1109/tmm.2025.3632629","title":"HMS <sup>2</sup> Net: Heterogeneous Multimodal State Space Network via CLIP for Dynamic Scene Classification in Livestreaming","display_name":"HMS <sup>2</sup> Net: Heterogeneous Multimodal State Space Network via CLIP for Dynamic Scene Classification in Livestreaming","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123365217","doi":"https://doi.org/10.1109/tmm.2025.3632629"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3632629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632629","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5101517522","display_name":"Jiafeng Li","orcid":"https://orcid.org/0000-0001-6976-7275"},"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":true,"raw_author_name":"Wensheng Li","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122885764","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122865996","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhuo","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111172356","display_name":"Qi Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101517522"],"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":0.16668024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"772","last_page":"785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8802000284194946,"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":0.8802000284194946,"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/T11439","display_name":"Video Analysis and Summarization","score":0.018200000748038292,"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":0.013100000098347664,"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/feature-vector","display_name":"Feature vector","score":0.4699000120162964},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4674000144004822},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.4551999866962433},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4372999966144562},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.38119998574256897},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3447999954223633},{"id":"https://openalex.org/keywords/dynamic-network-analysis","display_name":"Dynamic network analysis","score":0.3443000018596649},{"id":"https://openalex.org/keywords/dynamic-data","display_name":"Dynamic data","score":0.30790001153945923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8751999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5627999901771545},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.4551999866962433},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.38119998574256897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35659998655319214},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3447999954223633},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C197298091","wikidata":"https://www.wikidata.org/wiki/Q5318963","display_name":"Dynamic data","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.25850000977516174},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3632629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632629","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2996130371","https://openalex.org/W3034572008","https://openalex.org/W3088752609","https://openalex.org/W3126721948","https://openalex.org/W4214612132","https://openalex.org/W4283792038","https://openalex.org/W4296437530","https://openalex.org/W4311432122","https://openalex.org/W4312560592","https://openalex.org/W4312769131","https://openalex.org/W4312815172","https://openalex.org/W4362683584","https://openalex.org/W4384159628","https://openalex.org/W4385695854","https://openalex.org/W4386071707","https://openalex.org/W4386083135","https://openalex.org/W4390190670","https://openalex.org/W4390872366","https://openalex.org/W4390874610","https://openalex.org/W4392353733","https://openalex.org/W4394586021","https://openalex.org/W4399568547","https://openalex.org/W4400647053","https://openalex.org/W4401506443","https://openalex.org/W4402727669","https://openalex.org/W4403842425"],"related_works":[],"abstract_inverted_index":{"Livestreaming":[0],"platforms":[1],"attract":[2],"countless":[3],"daily":[4],"active":[5],"users,":[6],"making":[7],"online":[8],"content":[9,17,29,53],"regulation":[10],"imperative.":[11],"The":[12],"complex":[13],"and":[14,77,123,180,195,201],"diverse":[15],"multimodal":[16,59,97,135,159],"elements":[18,83],"in":[19,70,84,99,112,207],"dynamic":[20,41,67,81,143,148,204],"livestreaming":[21,71],"scene":[22,42,68,82,205],"pose":[23],"a":[24,57,88,118,147],"great":[25],"challenge":[26],"to":[27,32,95,127],"video":[28,52,163],"understanding.":[30,54],"Thanks":[31],"the":[33,48,80,108,156,173,181,199],"success":[34],"of":[35,47,51,142,158,167,191,203],"contrastive":[36],"language-image":[37],"pre-training":[38],"(CLIP)":[39],"for":[40,66,154],"classification,":[43],"which":[44],"is":[45],"one":[46],"basic":[49],"tasks":[50],"We":[55],"propose":[56],"heterogeneous":[58,89,113],"state":[60,149],"space":[61,150],"network":[62],"(HMS<sup":[63],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[64,186],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>Net)":[65],"classification":[69,206],"via":[72],"CLIP.":[73],"(1)":[74],"To":[75,105],"fully":[76],"efficiently":[78],"mine":[79],"livestreaming,":[85],"we":[86,116,145],"design":[87],"teacher-student":[90],"Transformer":[91],"(HT-SFormer)":[92],"with":[93,107],"CLIP":[94],"extract":[96],"features":[98],"an":[100],"energy-efficient":[101],"unified":[102],"pipeline;":[103],"(2)":[104],"cope":[106],"possible":[109],"information":[110,131],"conflicts":[111],"feature":[114,121,136],"fusion,":[115],"introduce":[117],"cross-modal":[119],"adaptive":[120],"filter":[122],"fusion":[124],"(CMAF)":[125],"module":[126],"generate":[128],"more":[129],"complete":[130],"complementarity":[132],"by":[133],"adjusting":[134],"composition;":[137],"(3)":[138],"For":[139],"temporal":[140],"context-awareness":[141],"scene,":[144],"establish":[146],"memory":[151],"(DSSM)":[152],"structure":[153],"capturing":[155],"correlation":[157],"data":[160],"between":[161],"neighboring":[162],"frames.":[164],"A":[165],"series":[166],"comparative":[168],"experiments":[169],"are":[170],"conducted":[171],"on":[172],"publicly":[174],"available":[175],"datasets":[176],"DAVIS,":[177],"Mini-kinetics,":[178],"HMDB51,":[179],"self-built":[182],"BJUT-LCD.":[183],"Our":[184],"HMS<sup":[185],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>Net":[187],"produce":[188],"competitive":[189],"results":[190],"71.09%,":[192],"95.40%,":[193],"53.64%,":[194],"82.36%,":[196],"respectively,":[197],"demonstrating":[198],"effectiveness":[200],"superiority":[202],"livestreaming.":[208]},"counts_by_year":[],"updated_date":"2026-01-14T00:46:21.520733","created_date":"2026-01-14T00:00:00"}