{"id":"https://openalex.org/W7130595664","doi":"https://doi.org/10.1109/tip.2026.3663857","title":"Temporal Visual Semantics-Induced Human Motion Understanding With Large Language Models","display_name":"Temporal Visual Semantics-Induced Human Motion Understanding With Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7130595664","doi":"https://doi.org/10.1109/tip.2026.3663857","pmid":"https://pubmed.ncbi.nlm.nih.gov/41712391"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3663857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3663857","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5036659144","display_name":"Zheng Xing","orcid":"https://orcid.org/0000-0002-9710-082X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Xing","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9710-082X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047407285","display_name":"Weibing Zhao","orcid":"https://orcid.org/0000-0002-2819-990X"},"institutions":[{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibing Zhao","raw_affiliation_strings":["Guangdong Laboratory of Machine Perception and Intelligent Computing, Faculty of Engineering, Shenzhen MSU-BIT University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2819-990X","affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Machine Perception and Intelligent Computing, Faculty of Engineering, Shenzhen MSU-BIT University, Shenzhen, China","institution_ids":["https://openalex.org/I4388482657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20554365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"2182","last_page":"2197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.6769999861717224,"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":0.6769999861717224,"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/T12290","display_name":"Human Motion and Animation","score":0.12839999794960022,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07460000365972519,"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/subspace-topology","display_name":"Subspace topology","score":0.7458000183105469},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6590999960899353},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5730000138282776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5566999912261963},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49459999799728394},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.47279998660087585},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45680001378059387},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4372999966144562}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.758400022983551},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7458000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035999894142151},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6590999960899353},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5730000138282776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C106135958","wikidata":"https://www.wikidata.org/wiki/Q7291993","display_name":"Random subspace method","level":3,"score":0.3968999981880188},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.376800000667572},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.25279998779296875},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25200000405311584}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098430","descriptor_name":"Clustering Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D009068","descriptor_name":"Movement","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3663857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3663857","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41712391","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41712391","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4625350534915924,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G502802024","display_name":null,"funder_award_id":"JCYJ20241202130548062","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"}],"funders":[{"id":"https://openalex.org/F4320336736","display_name":"Chengdu Science and Technology Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W225975350","https://openalex.org/W1538422756","https://openalex.org/W1890623278","https://openalex.org/W1978383016","https://openalex.org/W1993962865","https://openalex.org/W1997201895","https://openalex.org/W2032481801","https://openalex.org/W2035813998","https://openalex.org/W2088748973","https://openalex.org/W2107962625","https://openalex.org/W2116324873","https://openalex.org/W2121947440","https://openalex.org/W2124658620","https://openalex.org/W2146634731","https://openalex.org/W2161491846","https://openalex.org/W2162238004","https://openalex.org/W2164278908","https://openalex.org/W2222512263","https://openalex.org/W2257742059","https://openalex.org/W2343142751","https://openalex.org/W2491875666","https://openalex.org/W2533503513","https://openalex.org/W2788291594","https://openalex.org/W2889731794","https://openalex.org/W2896169497","https://openalex.org/W2897582990","https://openalex.org/W2964062686","https://openalex.org/W3130064502","https://openalex.org/W3187676397","https://openalex.org/W3200590151","https://openalex.org/W4210353804","https://openalex.org/W4224313990","https://openalex.org/W4312574212","https://openalex.org/W4321780073","https://openalex.org/W4327524127","https://openalex.org/W4361859495","https://openalex.org/W4384161741","https://openalex.org/W4386076140","https://openalex.org/W4387969320","https://openalex.org/W4391116744","https://openalex.org/W4392085048","https://openalex.org/W4393078951","https://openalex.org/W4393148541","https://openalex.org/W4396886519","https://openalex.org/W4401806301","https://openalex.org/W4401878734","https://openalex.org/W4402715874","https://openalex.org/W4402955558","https://openalex.org/W4403758986","https://openalex.org/W4404094511","https://openalex.org/W4406138276","https://openalex.org/W4408017262","https://openalex.org/W4408051337","https://openalex.org/W4409129241","https://openalex.org/W4409886833","https://openalex.org/W4410341905","https://openalex.org/W4411549762","https://openalex.org/W4411991872","https://openalex.org/W4412444881","https://openalex.org/W4413145251","https://openalex.org/W4413145624","https://openalex.org/W4413145659","https://openalex.org/W4413146887","https://openalex.org/W4413147450","https://openalex.org/W4415073292","https://openalex.org/W4415178438","https://openalex.org/W4415798917","https://openalex.org/W7124759612"],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"human":[1,37,87,206],"motion":[2,38,62,88,110,207],"segmentation":[3,154,190],"(HMS)":[4],"can":[5],"be":[6],"effectively":[7],"achieved":[8],"using":[9,90],"subspace":[10,52,76,97,130,134,147,159,185],"clustering":[11,53,77,131],"techniques.":[12],"However,":[13],"traditional":[14],"methods":[15],"overlook":[16],"the":[17,28,41,75,108,113,167,189,196],"role":[18],"of":[19,30,44,169],"temporal":[20,31,118,138,151,163,174],"semantic":[21],"exploration":[22],"in":[23,83],"HMS.":[24],"This":[25],"paper":[26],"explores":[27],"use":[29],"vision":[32],"semantics":[33],"(TVS)":[34],"derived":[35],"from":[36,64,86],"sequences,":[39],"leveraging":[40],"image-to-text":[42],"capabilities":[43],"a":[45,128,137,162,179],"large":[46],"language":[47],"model":[48],"(LLM)":[49],"to":[50,59,144],"enhance":[51],"performance.":[54],"The":[55,79],"core":[56],"idea":[57],"is":[58,155],"extract":[60],"textual":[61],"information":[63,73,95,120],"consecutive":[65,105],"frames":[66,106],"via":[67],"LLM":[68,91,114],"and":[69,92,115],"incorporate":[70],"this":[71,94],"learned":[72],"into":[74,96],"framework.":[78],"primary":[80],"challenge":[81],"lies":[82],"learning":[84],"TVS":[85],"sequences":[89],"incorporating":[93,133],"clustering.":[98],"To":[99],"address":[100],"this,":[101],"we":[102],"determine":[103],"whether":[104],"depict":[107],"same":[109],"by":[111],"querying":[112],"subsequently":[116],"learn":[117],"neighboring":[119],"based":[121,157,187],"on":[122,158,188,203],"its":[123,150,173],"response.":[124],"We":[125,176],"then":[126],"develop":[127],"TVS-integrated":[129],"approach,":[132],"embedding":[135,160,186],"with":[136,149,161,172],"regularizer":[139],"that":[140,165,182,195],"induces":[141,166],"each":[142,170],"frame":[143,171],"share":[145],"similar":[146],"embeddings":[148],"neighbors.":[152,175],"Additionally,":[153],"performed":[156],"constraint":[164],"grouping":[168],"also":[177],"introduce":[178],"feedback-enabled":[180],"framework":[181],"continuously":[183],"optimizes":[184],"output.":[191],"Experimental":[192],"results":[193],"demonstrate":[194],"proposed":[197],"method":[198],"outperforms":[199],"existing":[200],"state-of-the-art":[201],"approaches":[202],"four":[204],"benchmark":[205],"datasets.":[208]},"counts_by_year":[],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2026-02-20T00:00:00"}