{"id":"https://openalex.org/W4403791746","doi":"https://doi.org/10.1145/3664647.3681625","title":"Modal-Enhanced Semantic Modeling for Fine-Grained 3D Human Motion Retrieval","display_name":"Modal-Enhanced Semantic Modeling for Fine-Grained 3D Human Motion Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791746","doi":"https://doi.org/10.1145/3664647.3681625"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681625?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681625?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103325224","display_name":"Haoyu Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Shi","raw_affiliation_strings":["Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0009-0003-7845-781X","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000417495","display_name":"Huaiwen Zhang","orcid":"https://orcid.org/0000-0002-3183-9218"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiwen Zhang","raw_affiliation_strings":["Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-3183-9218","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.6427,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70232139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"10114","last_page":"10123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":1.0,"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":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.792411208152771},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.592665433883667},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.5231579542160034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43947482109069824},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.43806836009025574},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1321718692779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792411208152771},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.592665433883667},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.5231579542160034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43947482109069824},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.43806836009025574},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1321718692779541},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681625?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3681625","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3681625","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664647.3681625?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1383338027","display_name":null,"funder_award_id":"62206137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1406082945","display_name":null,"funder_award_id":"62206200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1498893086","display_name":null,"funder_award_id":"62036012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2280626339","display_name":null,"funder_award_id":"62276257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2454296646","display_name":null,"funder_award_id":"62106262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4856500953","display_name":null,"funder_award_id":"22JCQNJC00940","funder_id":"https://openalex.org/F4320323993","funder_display_name":"Natural Science Foundation of Tianjin City"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403791746.pdf","grobid_xml":"https://content.openalex.org/works/W4403791746.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2474702929","https://openalex.org/W2560674852","https://openalex.org/W2951019013","https://openalex.org/W2962964995","https://openalex.org/W2996249958","https://openalex.org/W3035225512","https://openalex.org/W3092336341","https://openalex.org/W3125772723","https://openalex.org/W3215052027","https://openalex.org/W4288079574","https://openalex.org/W4291926315","https://openalex.org/W4312635677","https://openalex.org/W4317796373","https://openalex.org/W4321780110","https://openalex.org/W4375958382","https://openalex.org/W4384641262","https://openalex.org/W4384661029","https://openalex.org/W4385934203","https://openalex.org/W4386071700","https://openalex.org/W4386072365","https://openalex.org/W4386075842","https://openalex.org/W4386076086","https://openalex.org/W4386076359","https://openalex.org/W4386076485","https://openalex.org/W4386076600","https://openalex.org/W4386083126","https://openalex.org/W4387963302","https://openalex.org/W4387969371","https://openalex.org/W4390872412","https://openalex.org/W4390872434","https://openalex.org/W4390872529","https://openalex.org/W4390874542","https://openalex.org/W4400531282"],"related_works":["https://openalex.org/W2035558540","https://openalex.org/W2529580585","https://openalex.org/W2804584315","https://openalex.org/W2004712313","https://openalex.org/W2167757589","https://openalex.org/W2332110715","https://openalex.org/W2988011613","https://openalex.org/W2806036343","https://openalex.org/W2079653927","https://openalex.org/W142482926"],"abstract_inverted_index":{"Text":[0],"to":[1,9,27,37,118,144,150,161,176,203],"Motion":[2],"Retrieval":[3],"(TMR)":[4],"is":[5],"an":[6],"emerging":[7],"task":[8],"retrieve":[10],"relevant":[11,169],"motion":[12,40,64,85,141,192,206],"sequences":[13,86],"with":[14,87],"the":[15,46,53,63,130,147,164,174,177,234],"nature":[16],"language":[17],"description.":[18],"The":[19,189],"dominant":[20],"approach":[21,241],"learns":[22],"a":[23,95,113,139,157,183,195],"joint":[24],"embedding":[25],"space":[26],"measure":[28],"global-level":[29],"similarities.":[30],"However,":[31],"simple":[32],"global":[33],"embeddings":[34,207],"are":[35],"insufficient":[36],"represent":[38,151],"complicated":[39],"and":[41,52,68,200,218,231,255],"textual":[42,115,132],"details,":[43],"such":[44],"as":[45],"movement":[47],"of":[48,62,122,197,236,251],"specific":[49,123],"body":[50,57,124,170],"parts":[51],"coordination":[54],"among":[55,74,168],"these":[56,75,91],"parts.":[58,171],"In":[59],"addition,":[60],"most":[61],"variations":[65],"occur":[66],"subtly":[67],"locally,":[69],"resulting":[70],"in":[71,82],"semantic":[72,213],"vagueness":[73],"motions,":[76,179],"which":[77,127],"further":[78,181],"presents":[79],"considerable":[80],"challenges":[81],"precisely":[83],"aligning":[84],"texts.":[88,220],"To":[89,172],"address":[90],"challenges,":[92],"we":[93,111,180],"propose":[94,182],"novel":[96],"Modal-Enhanced":[97],"Semantic":[98],"Modeling":[99],"(MESM)":[100],"method,":[101],"focusing":[102],"on":[103,224,253,257],"fine-grained":[104,131],"alignment":[105,214],"through":[106],"enhanced":[107],"modal":[108],"semantics.":[109],"Specifically,":[110],"develop":[112],"prompt-enhanced":[114],"module":[116,142,155,187],"(PTM)":[117],"generate":[119],"detailed":[120],"descriptions":[121],"part":[125],"movements,":[126],"comprehensively":[128],"captures":[129],"semantics":[133,185],"for":[134],"precise":[135,212],"matching.":[136],"We":[137],"employ":[138],"skeleton-enhanced":[140],"(SMM)":[143],"effectively":[145],"enhance":[146],"model's":[148],"capability":[149],"intricate":[152,165],"motions.":[153],"This":[154],"leverages":[156],"graph":[158],"convolutional":[159],"network":[160],"meticulously":[162],"model":[163],"spatial":[166],"dependencies":[167],"improve":[173],"sensitivity":[175],"subtle":[178,216],"text-driven":[184],"interaction":[186],"(TSIM).":[188],"TSIM":[190],"assigns":[191],"features":[193],"into":[194],"set":[196],"aggregated":[198],"descriptors":[199],"employs":[201],"cross-attention":[202],"aggregate":[204],"discriminative":[205],"guided":[208],"by":[209],"text,":[210],"enabling":[211],"between":[215],"motions":[217],"corresponding":[219],"Extensive":[221],"experiments":[222],"conducted":[223],"two":[225],"widely":[226],"used":[227],"benchmark":[228],"datasets,":[229],"HumanML3D":[230,254],"KIT-ML,":[232],"demonstrate":[233],"effectiveness":[235],"our":[237],"proposed":[238],"method.":[239],"Our":[240],"outperforms":[242],"existing":[243],"state-of-the-art":[244],"retrieval":[245],"methods,":[246],"achieving":[247],"significant":[248],"Rsum":[249],"improvements":[250],"24.28%":[252],"25.80%":[256],"KIT-ML.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}