{"id":"https://openalex.org/W4416078141","doi":"https://doi.org/10.1109/jbhi.2025.3631045","title":"MoChat: Joints-Grouped Spatio-Temporal Grounding Multimodal Large Language Model for Multi-Turn Motion Comprehension and Description","display_name":"MoChat: Joints-Grouped Spatio-Temporal Grounding Multimodal Large Language Model for Multi-Turn Motion Comprehension and Description","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416078141","doi":"https://doi.org/10.1109/jbhi.2025.3631045","pmid":"https://pubmed.ncbi.nlm.nih.gov/41212709"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2025.3631045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3631045","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"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 Journal of Biomedical and Health Informatics","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":null,"display_name":"Jiawei Mo","orcid":"https://orcid.org/0009-0006-3925-4560"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Mo","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0006-3925-4560","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yixuan Chen","orcid":"https://orcid.org/0009-0004-9924-3252"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0004-9924-3252","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091755668","display_name":"Rifen Lin","orcid":"https://orcid.org/0009-0002-6005-3131"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rifen Lin","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0002-6005-3131","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021923","display_name":"Yaodong Ni","orcid":"https://orcid.org/0000-0003-0607-7757"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkang Ni","raw_affiliation_strings":["School of Software, Xinjiang University, Urumqi, China","School of Software, Xinjiang University, Urumqi, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, PR China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100575589","display_name":"Feng Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liang","raw_affiliation_strings":["School of Medical Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8542-9871","affiliations":[{"raw_affiliation_string":"School of Medical Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033885404","display_name":"Min Zeng","orcid":"https://orcid.org/0000-0002-1726-0955"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-1726-0955","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007941489","display_name":"Xiping Hu","orcid":"https://orcid.org/0000-0002-4952-699X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiping Hu","raw_affiliation_strings":["School of Medical Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4952-699X","affiliations":[{"raw_affiliation_string":"School of Medical Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100719013","display_name":"Min Li","orcid":"https://orcid.org/0000-0002-0188-1394"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Li","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0188-1394","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.30256327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":"3","first_page":"1972","last_page":"1985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.652400016784668,"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":0.652400016784668,"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":0.15489999949932098,"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/T11431","display_name":"Action Observation and Synchronization","score":0.07980000227689743,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6783000230789185},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6105999946594238},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5986999869346619},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5759000182151794},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5638999938964844},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5577999949455261},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5311999917030334},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5102999806404114},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4587000012397766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431000113487244},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6783000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5986999869346619},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4593000113964081},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4587000012397766},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35440000891685486},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3418000042438507},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C523889960","wikidata":"https://www.wikidata.org/wiki/Q160695","display_name":"Torso","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2500999867916107}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","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":"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":"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}],"locations_count":2,"locations":[{"id":"doi:10.1109/jbhi.2025.3631045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3631045","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"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 Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:41212709","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41212709","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 journal of biomedical and health informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1967554269","https://openalex.org/W2101105183","https://openalex.org/W2474702929","https://openalex.org/W2948058585","https://openalex.org/W2963076818","https://openalex.org/W2990763144","https://openalex.org/W3203634062","https://openalex.org/W4200634815","https://openalex.org/W4312245820","https://openalex.org/W4312635677","https://openalex.org/W4312675926","https://openalex.org/W4312841534","https://openalex.org/W4312936899","https://openalex.org/W4385245566","https://openalex.org/W4390873156","https://openalex.org/W4402727046","https://openalex.org/W4402727272","https://openalex.org/W4402727764","https://openalex.org/W4402753712","https://openalex.org/W4402753874","https://openalex.org/W4402754220","https://openalex.org/W4410153550","https://openalex.org/W4411232405","https://openalex.org/W4412353044","https://openalex.org/W4415795395","https://openalex.org/W7108068597","https://openalex.org/W7133196460","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"continuous":[1],"advancements":[2],"in":[3,33,93,188],"deep":[4],"learning":[5],"for":[6,48,148,164,174],"understanding":[7,190],"human":[8,79,98,204],"motion,":[9],"existing":[10],"models":[11],"often":[12],"struggle":[13],"to":[14,97,119,131,152],"accurately":[15],"identify":[16],"action":[17],"timing":[18],"and":[19,40,58,81,101,135,158],"specific":[20],"body":[21],"parts,":[22],"typically":[23],"supporting":[24],"only":[25],"single-round":[26],"interaction.":[27],"This":[28],"limitation":[29],"is":[30,46,128],"particularly":[31],"pronounced":[32],"home":[34],"exercise":[35,50],"monitoring,":[36],"neurological":[37,56],"disorder":[38],"assessment,":[39],"rehabilitation,":[41],"where":[42],"precise":[43,140],"motion":[44,80,189],"analysis":[45],"crucial":[47],"ensuring":[49],"efficacy,":[51],"detecting":[52],"early":[53],"signs":[54],"of":[55,75,78,199,203],"conditions,":[57],"guiding":[59],"personalized":[60],"recovery":[61],"programs.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,88,144],"propose":[67],"MoChat,":[68],"a":[69,105,146,160],"multimodal":[70],"large":[71,115],"language":[72,116],"model":[73,117,197],"capable":[74,198],"spatio-temporal":[76,201],"grounding":[77,150,166,202],"multi-turn":[82,161],"dialogue":[83],"understanding.":[84],"To":[85],"achieve":[86],"this,":[87],"first":[89,196],"group":[90],"spatial":[91,165],"features":[92],"skeleton":[94],"frames":[95],"according":[96],"anatomical":[99],"structures":[100],"process":[102],"them":[103],"through":[104],"Joints-Grouped":[106],"Skeleton":[107],"Encoder.":[108],"The":[109],"encoder's":[110],"outputs":[111],"are":[112,172],"fused":[113],"with":[114],"embeddings":[118,134],"generate":[120],"spatio-aware":[121],"representations.":[122],"A":[123],"cross-attention-based":[124],"Regression":[125],"Head":[126],"module":[127],"then":[129],"designed":[130],"align":[132],"hidden-layer":[133],"skeletal":[136],"sequence":[137],"embeddings,":[138],"enabling":[139],"temporal":[141,149],"grounding.":[142],"Furthermore,":[143],"develop":[145],"pipeline":[147],"task":[151,170],"extract":[153],"timestamps":[154],"from":[155],"skeleton-text":[156],"pairs":[157],"construct":[159],"instruction":[162],"dialogues":[163],"task.":[167],"Finally,":[168],"various":[169],"instructions":[171],"generated":[173],"jointly":[175],"training.":[176],"Experimental":[177],"results":[178],"demonstrate":[179],"that":[180],"MoChat":[181],"achieves":[182],"state-of-the-art":[183],"performance":[184],"across":[185],"multiple":[186],"metrics":[187],"tasks,":[191],"making":[192],"it":[193],"as":[194],"the":[195],"fine-grained":[200],"motion.":[205]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-10T00:00:00"}