{"id":"https://openalex.org/W4402775285","doi":"https://doi.org/10.1109/cvpr52733.2024.00158","title":"Tri-Modal Motion Retrieval by Learning a Joint Embedding Space","display_name":"Tri-Modal Motion Retrieval by Learning a Joint Embedding Space","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402775285","doi":"https://doi.org/10.1109/cvpr52733.2024.00158"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.00158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077144356","display_name":"Shihao Zou","orcid":"https://orcid.org/0000-0002-9042-6069"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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 Institute of Advanced Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111140232","display_name":"Yuxuan Ge","orcid":"https://orcid.org/0009-0000-7277-5436"},"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":"Yuxuan Ge","raw_affiliation_strings":["ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101846140","display_name":"Tian Zheng","orcid":"https://orcid.org/0000-0003-0379-7986"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1552,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9415387,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1596","last_page":"1605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9983000159263611,"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":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6891149878501892},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6718188524246216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6715846061706543},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5664994120597839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508082389831543},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.507481038570404},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4859548807144165},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4584924280643463},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10482284426689148},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.101594477891922}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6891149878501892},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6718188524246216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6715846061706543},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5664994120597839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508082389831543},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.507481038570404},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4859548807144165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4584924280643463},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10482284426689148},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.101594477891922},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.00158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.00158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416","https://openalex.org/W1996130883"],"abstract_inverted_index":{"Information":[0],"retrieval":[1,160],"is":[2],"an":[3,53,66,77,107],"ever-evolving":[4],"and":[5,42,63,79,117,132,138,147,166],"crucial":[6],"re-search":[7],"domain.":[8],"The":[9],"substantial":[10],"demand":[11],"for":[12,100],"high-quality":[13],"human":[14,27],"motion":[15,28,43,139],"data":[16],"especially":[17],"in":[18,26,156,174],"online":[19],"acquirement":[20],"has":[21,48],"led":[22],"to":[23,128],"a":[24,59,97,123],"surge":[25],"research":[29],"works.":[30],"Prior":[31],"works":[32],"have":[33],"mainly":[34],"concentrated":[35],"on":[36,144],"dual-modality":[37],"learning,":[38],"such":[39],"as":[40,76,106],"text":[41,116],"tasks,":[44,161],"but":[45],"three-modality":[46,101],"learning":[47,102],"been":[49],"rarely":[50],"explored.":[51],"Intuitively,":[52],"extra":[54,71],"introduced":[55],"modality":[56,72],"can":[57,73,171],"enrich":[58],"model's":[60],"application":[61],"scenario,":[62],"more":[64],"importantly,":[65],"adequate":[67],"choice":[68],"of":[69],"the":[70,81,84,113,145],"also":[74],"act":[75],"intermediary":[78],"enhance":[80],"alignment":[82,131],"between":[83,115],"other":[85],"two":[86],"disparate":[87],"modalities.":[88,140],"In":[89],"this":[90],"work,":[91],"we":[92],"introduce":[93],"LAVIMO":[94,152],"(LAnguage-VIdeo-MOtion":[95],"alignment),":[96],"novel":[98],"framework":[99],"integrating":[103],"human-centric":[104],"videos":[105],"additional":[108],"modality,":[109],"thereby":[110],"ef-fectively":[111],"bridging":[112],"gap":[114],"motion.":[118],"More-over,":[119],"our":[120,142],"approach":[121],"leverages":[122],"specially":[124],"designed":[125],"attention":[126],"mechanism":[127],"foster":[129],"enhanced":[130],"synergistic":[133],"effects":[134],"among":[135],"text,":[136],"video,":[137],"Empirically,":[141],"results":[143],"HumanML3D":[146],"KIT-ML":[148],"datasets":[149],"show":[150],"that":[151],"achieves":[153],"state-of-the-art":[154],"performance":[155],"various":[157],"motion-related":[158],"cross-modal":[159],"in-cluding":[162],"text-to-motion,":[163],"motion-to-text,":[164],"video-to-motion":[165],"motion-to-video.":[167],"Our":[168],"project":[169],"webpage":[170],"be":[172],"found":[173],"https://lavimo2023.github.io/LAVIMO/.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}