{"id":"https://openalex.org/W4415540783","doi":"https://doi.org/10.1145/3746027.3755662","title":"Sequence-Event Semantic Consistent Learning for Text-to-Motion Retrieval","display_name":"Sequence-Event Semantic Consistent Learning for Text-to-Motion Retrieval","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540783","doi":"https://doi.org/10.1145/3746027.3755662"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755662","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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/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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25571492,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8740","last_page":"8749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9987999796867371,"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":0.9973000288009644,"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/semantics","display_name":"Semantics (computer science)","score":0.7038000226020813},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6851999759674072},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6779000163078308},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6692000031471252},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5533000230789185},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5397999882698059},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5038999915122986},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.40939998626708984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220999836921692},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7038000226020813},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6851999759674072},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6779000163078308},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6692000031471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.633899986743927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5533000230789185},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4059999883174896},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3723999857902527},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34700000286102295},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3434000015258789},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755662","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":23,"referenced_works":["https://openalex.org/W2474702929","https://openalex.org/W2951019013","https://openalex.org/W2962964995","https://openalex.org/W2964089981","https://openalex.org/W3096803658","https://openalex.org/W3118694826","https://openalex.org/W3168433561","https://openalex.org/W3174873881","https://openalex.org/W4294691145","https://openalex.org/W4296437558","https://openalex.org/W4304014690","https://openalex.org/W4317796373","https://openalex.org/W4321780110","https://openalex.org/W4360897523","https://openalex.org/W4375958382","https://openalex.org/W4384661029","https://openalex.org/W4386758381","https://openalex.org/W4390873054","https://openalex.org/W4390874263","https://openalex.org/W4391147898","https://openalex.org/W4392172944","https://openalex.org/W4402753888","https://openalex.org/W4404171857"],"related_works":[],"abstract_inverted_index":{"Text-to-Motion":[0],"Retrieval":[1],"(TMR)":[2],"is":[3,155,172],"a":[4,83,99,122,144],"challenging":[5,225],"task":[6],"to":[7,24,47,60,66,103,126,139,157,174,178,180,202],"retrieve":[8],"relevant":[9],"motion":[10,30,34,94,110,164,232],"sequences":[11,35],"with":[12,41],"the":[13,109,113,117,159,163,185,192],"natural":[14],"language":[15],"description.":[16],"Existing":[17],"TMR":[18],"methods":[19,219],"primarily":[20],"utilize":[21],"single":[22,51],"embeddings":[23],"represent":[25],"and":[26,29,68,130,165,168,197,223,231],"align":[27,158],"text":[28],"sequences.":[31],"However,":[32],"real-world":[33],"typically":[36],"contain":[37],"multiple":[38],"sequential":[39],"actions":[40],"intricate":[42],"semantics,":[43],"which":[44],"are":[45],"hard":[46],"precisely":[48],"capture":[49,61,69,140],"by":[50],"embedding.":[52],"Additionally,":[53],"relying":[54],"solely":[55],"on":[56],"naive":[57],"contrastive":[58,194],"training":[59],"high-level":[62],"semantics":[63,142,161],"may":[64],"struggle":[65],"perceive":[67],"fine-grained":[70,105,149],"action":[71,106,187],"details":[72,107],"necessary":[73],"for":[74,91,148,206],"precise":[75],"text-motion":[76],"alignment.":[77,150],"In":[78],"this":[79],"work,":[80],"we":[81,97,190],"propose":[82,198],"novel":[84],"Sequence-Event":[85],"Semantic":[86],"Consistent":[87],"Learning":[88],"(SECL)":[89],"framework":[90],"3D":[92],"human":[93,228],"retrieval.":[95],"Specifically,":[96],"introduce":[98],"self-supervised":[100],"learning":[101,146],"strategy":[102,201],"incorporate":[104],"into":[108],"representations":[111],"via":[112],"generative":[114],"feedback":[115],"from":[116],"diffusion":[118],"model.":[119],"We":[120],"design":[121],"parameter-free":[123],"sequence-level":[124],"interaction":[125,133,229],"explore":[127],"coarse-grained":[128],"alignment":[129,195],"an":[131,152,169,199],"event-level":[132],"that":[134,213],"utilizes":[135],"several":[136],"learnable":[137],"queries":[138],"event":[141,160,176],"in":[143,220],"shared":[145],"manner":[147],"Furthermore,":[151],"inter-consistency":[153],"loss":[154,171],"introduced":[156],"between":[162],"corresponding":[166],"text,":[167],"intra-diversity":[170],"designed":[173],"encourage":[175],"features":[177],"attend":[179],"different":[181],"contents,":[182],"effectively":[183],"capturing":[184],"rich":[186],"information.":[188],"Finally,":[189],"modify":[191],"traditional":[193],"objective":[196],"importance-sampling":[200],"emphasize":[203],"harder":[204],"negatives":[205],"discriminative":[207],"representation":[208],"learning.":[209],"Extensive":[210],"experiments":[211],"show":[212],"our":[214],"method":[215],"significantly":[216],"outperforms":[217],"existing":[218],"text-to-motion":[221],"retrieval":[222],"other":[224],"tasks,":[226],"e.g.,":[227],"recognition":[230],"temporal":[233],"localization.":[234]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-25T00:00:00"}