{"id":"https://openalex.org/W7124455525","doi":"https://doi.org/10.1109/tmm.2026.3654382","title":"Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space","display_name":"Multi-Modal Motion Retrieval by Learning a Fine-Grained Joint Embedding Space","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124455525","doi":"https://doi.org/10.1109/tmm.2026.3654382"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2026.3654382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654382","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/A5020550081","display_name":"Shiyao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyao Yu","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-4161-1598","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zi-An Wang","orcid":"https://orcid.org/0009-0004-6259-1368"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zi-An Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6259-1368","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081909336","display_name":"Kangning Yin","orcid":"https://orcid.org/0000-0001-8652-0151"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangning Yin","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng Tian","orcid":"https://orcid.org/0009-0008-0622-8512"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Tian","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-0622-8512","affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123229907","display_name":"Mingyuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mingyuan Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8212-715X","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119968897","display_name":"Weixin Si","orcid":null},"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"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixin Si","raw_affiliation_strings":["Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3289-9714","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077144356","display_name":"Shihao Zou","orcid":"https://orcid.org/0000-0002-9042-6069"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Zou","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9042-6069","affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"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":0.06072827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3694","last_page":"3708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6304000020027161,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6304000020027161,"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":0.13930000364780426,"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":0.10970000177621841,"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":0.7064999938011169},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5683000087738037},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5570999979972839},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.39469999074935913},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3792000114917755},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3709999918937683},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.36649999022483826},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.36640000343322754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8564000129699707},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7064999938011169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237999796867371},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4260999858379364},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3709999918937683},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.31189998984336853},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2026.3654382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654382","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"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/212451","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/212451","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3321136001","display_name":null,"funder_award_id":"2023A1515030268","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G5254710405","display_name":null,"funder_award_id":"62372441","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"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Motion":[0],"retrieval":[1,31,59,90,136,157,166,190],"is":[2,100],"crucial":[3],"for":[4,29,57,84,114,155,164,191],"motion":[5,16,30,89,135,189,193],"acquisition,":[6],"offering":[7],"superior":[8,141],"precision,":[9],"realism,":[10],"controllability,":[11],"and":[12,44,48,75,95,158],"editability":[13],"compared":[14],"to":[15,23,91],"generation.":[17],"Existing":[18],"approaches":[19],"leverage":[20],"contrastive":[21,105],"learning":[22,106],"construct":[24],"a":[25,41,67,77,103,159],"unified":[26],"embedding":[27,80],"space":[28,99],"from":[32],"text":[33],"or":[34],"visual":[35],"modality.":[36],"However,":[37],"these":[38,63],"methods":[39,145],"lack":[40],"more":[42],"intuitive":[43],"user-friendly":[45],"interaction":[46],"mode":[47],"often":[49],"overlook":[50],"the":[51,85,168,185],"sequential":[52],"representation":[53],"of":[54,187],"most":[55],"modalities":[56,113],"improved":[58],"performance.":[60],"To":[61,117],"address":[62],"limitations,":[64],"we":[65,121],"propose":[66],"framework":[68,178],"that":[69,175],"aligns":[70],"four":[71],"modalities\u2014text,":[72],"audio,":[73],"video,":[74],"motion\u2014within":[76],"fine-grained":[78,98],"joint":[79],"space,":[81],"incorporating":[82],"audio":[83,130],"first":[86],"time":[87],"in":[88,153,162],"enhance":[92],"user":[93],"immersion":[94],"convenience.":[96],"This":[97],"achieved":[101],"through":[102],"sequence-level":[104],"approach,":[107],"which":[108],"captures":[109],"critical":[110],"details":[111],"across":[112,146],"better":[115],"alignment.":[116],"evaluate":[118],"our":[119,172,176],"framework,":[120],"augment":[122],"existing":[123],"text-motion":[124],"datasets":[125],"with":[126],"synthetic":[127],"but":[128],"diverse":[129],"recordings,":[131],"creating":[132],"two":[133],"multi-modal":[134,188],"datasets.":[137],"Experimental":[138],"results":[139,173],"demonstrate":[140],"performance":[142],"over":[143],"state-of-the-art":[144],"multiple":[147],"sub-tasks,":[148],"including":[149],"an":[150],"10.16%":[151],"improvement":[152,161],"R@10":[154],"text-to-motion":[156],"25.43%":[160],"R@1":[163],"video-to-motion":[165],"on":[167],"HumanML3D":[169],"dataset.":[170],"Furthermore,":[171],"show":[174],"4-modal":[177],"significantly":[179],"outperforms":[180],"its":[181],"3-modal":[182],"counterpart,":[183],"underscoring":[184],"potential":[186],"advancing":[192],"acquisition.":[194]},"counts_by_year":[],"updated_date":"2026-05-23T06:10:36.450269","created_date":"2026-01-17T00:00:00"}
