{"id":"https://openalex.org/W7162630467","doi":"https://doi.org/10.1145/3774905.3794682","title":"Towards Better Evaluation Metrics for Text-to-Motion Generation","display_name":"Towards Better Evaluation Metrics for Text-to-Motion Generation","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162630467","doi":"https://doi.org/10.1145/3774905.3794682"},"language":null,"primary_location":{"id":"doi:10.1145/3774905.3794682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774905.3794682","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774905.3794682","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137244610","display_name":"Wenshuo Chen","orcid":"https://orcid.org/0009-0002-1966-6059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenshuo Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-1966-6059","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137267250","display_name":"Haozhe Jia","orcid":"https://orcid.org/0009-0001-1676-1547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haozhe Jia","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-1676-1547","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136229044","display_name":"Kuimou Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuimou Yu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-3134-4208","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137297824","display_name":"Songning Lai","orcid":"https://orcid.org/0009-0007-3132-9414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songning Lai","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-3132-9414","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137223023","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0002-8600-7099"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Griffith University, Brisbane, Australia and Data61/CSIRO, Canberra, Austria"],"raw_orcid":"https://orcid.org/0000-0002-8600-7099","affiliations":[{"raw_affiliation_string":"Griffith University, Brisbane, Australia and Data61/CSIRO, Canberra, Austria","institution_ids":["https://openalex.org/I11701301","https://openalex.org/I42894916"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137292005","display_name":"Yutao Yue","orcid":"https://orcid.org/0000-0003-4532-0924"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yutao Yue","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and JITRI, Institute of Deep Perception Technology, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0003-4532-0924","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and JITRI, Institute of Deep Perception Technology, Wuxi, China","institution_ids":["https://openalex.org/I90610280","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1301","last_page":"1311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.7141000032424927,"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":0.7141000032424927,"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":0.037700001150369644,"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/T12031","display_name":"Speech and dialogue systems","score":0.03689999878406525,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/metric","display_name":"Metric (unit)","score":0.31619998812675476},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.29159998893737793},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.27160000801086426},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2694999873638153},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2549000084400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5464000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.24130000174045563},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24120000004768372}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774905.3794682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774905.3794682","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774905.3794682","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774905.3794682","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.45408350229263306,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2474702929","https://openalex.org/W2793477525","https://openalex.org/W2982625143","https://openalex.org/W4288079574","https://openalex.org/W4312635677","https://openalex.org/W4312936899","https://openalex.org/W4313145975","https://openalex.org/W4386065848","https://openalex.org/W4390872247","https://openalex.org/W4402727293","https://openalex.org/W4403791248","https://openalex.org/W4403842319"],"related_works":[],"abstract_inverted_index":{"A":[0],"reliable":[1,135],"evaluation":[2,22,70,110],"metric":[3],"is":[4,38],"essential":[5],"for":[6,137],"guiding":[7],"positive":[8],"developments":[9],"within":[10],"a":[11,93],"research":[12],"field.":[13],"In":[14],"the":[15,20],"domain":[16],"of":[17],"text-to-motion":[18],"generation,":[19],"traditional":[21],"metrics":[23,57,123],"such":[24],"as":[25,87],"Fr\u00e9chet":[26],"Inception":[27],"Distance":[28],"(FID)":[29],"and":[30,77,102,117,130,134],"R-Precision":[31,45],"suffer":[32],"from":[33],"inherent":[34],"limitations.":[35],"Specifically,":[36],"FID":[37],"biased":[39],"by":[40],"its":[41],"Gaussian":[42],"assumption,":[43],"while":[44],"lacks":[46],"global":[47,94],"awareness.":[48],"Current":[49],"work":[50],"often":[51],"overemphasizes":[52],"improvements":[53],"on":[54],"these":[55,64],"unreliable":[56],"to":[58],"indicate":[59],"model":[60],"superiority.":[61],"To":[62],"address":[63],"challenges,":[65],"we":[66],"propose":[67],"two":[68],"novel":[69],"metrics:":[71],"Optimal":[72],"Transport":[73],"Matching":[74],"Score":[75],"(OTMS)":[76],"MoCLIP-based":[78],"Maximum":[79,104],"Mean":[80,105],"Discrepancy":[81],"(MMMD).":[82],"OTMS":[83],"formulates":[84],"text-motion":[85],"matching":[86],"an":[88,108],"optimal":[89],"transport":[90],"process,":[91],"enabling":[92],"perspective.":[95],"MMMD":[96],"leverages":[97],"our":[98,121],"enhanced":[99],"MoCLIP":[100],"encoder":[101],"Gaussian-RBF-based":[103],"Discrepancy,":[106],"providing":[107],"unbiased":[109],"without":[111],"restrictive":[112],"distribution":[113],"assumptions.":[114],"Extensive":[115],"experiments":[116],"analysis":[118],"demonstrate":[119],"that":[120],"proposed":[122],"align":[124],"closely":[125],"with":[126],"human":[127],"perceptual":[128],"judgments":[129],"provide":[131],"efficient,":[132],"comprehensive,":[133],"evaluations":[136],"text-driven":[138],"motion":[139],"generation":[140],"tasks.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-29T00:00:00"}