{"id":"https://openalex.org/W4403780889","doi":"https://doi.org/10.1145/3664647.3681444","title":"Multi-Instance Multi-Label Learning for Text-motion Retrieval","display_name":"Multi-Instance Multi-Label Learning for Text-motion Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780889","doi":"https://doi.org/10.1145/3664647.3681444"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681444","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100397772","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0003-2690-7180"},"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":"Yang Yang","raw_affiliation_strings":["Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0003-2690-7180","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049533256","display_name":"Liyuan Cao","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":"Liyuan Cao","raw_affiliation_strings":["Inner Mongolia University, Hothot, China"],"raw_orcid":"https://orcid.org/0009-0002-4625-4850","affiliations":[{"raw_affiliation_string":"Inner Mongolia University, Hothot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","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":1.0712,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78854277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5829","last_page":"5837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.991599977016449,"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/computer-science","display_name":"Computer science","score":0.7649399638175964},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6196005344390869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5500947833061218},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36099618673324585},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3216368556022644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649399638175964},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6196005344390869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5500947833061218},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36099618673324585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3216368556022644}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681444","pdf_url":null,"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":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2027266161","https://openalex.org/W2114315281","https://openalex.org/W2474702929","https://openalex.org/W2560674852","https://openalex.org/W2964089981","https://openalex.org/W2971856312","https://openalex.org/W3125772723","https://openalex.org/W4288079574","https://openalex.org/W4312635677","https://openalex.org/W4317796373","https://openalex.org/W4319068931","https://openalex.org/W4375958382","https://openalex.org/W4378501009","https://openalex.org/W4382657787","https://openalex.org/W4385681340","https://openalex.org/W4385825380","https://openalex.org/W4386501573","https://openalex.org/W4387963302","https://openalex.org/W4387969585","https://openalex.org/W4387969774","https://openalex.org/W4388186306","https://openalex.org/W4388189161","https://openalex.org/W4390523479","https://openalex.org/W4400531282","https://openalex.org/W6601037301"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Text-motion":[0],"retrieval":[1],"(TMR)":[2],"is":[3,47,94,105],"a":[4,15,84,97,118,252,260],"significant":[5,66,246],"cross-modal":[6],"task":[7],"that":[8],"retrieves":[9],"motion":[10,32,36,75,92,135,150,228],"sequences":[11,37,136,151],"semantically":[12],"similar":[13],"to":[14,26,49,166,210,223],"given":[16],"query":[17,148],"text.":[18],"Existing":[19],"TMR":[20,82],"methods":[21,233],"primarily":[22],"utilize":[23,162],"single":[24,53],"embeddings":[25],"represent":[27],"and":[28,31,59,71,74,102,128,134,149,158,172,189,202,205,219,227,240,259],"align":[29,225],"text":[30,73,104,133,226],"sequences.":[33,76],"However,":[34],"real-world":[35],"typically":[38],"contain":[39],"multiple":[40,185],"atomic":[41,62,100,192],"motions":[42,63,101,201],"with":[43,251],"complex":[44],"semantics,":[45],"which":[46,125],"hard":[48],"precisely":[50,180],"capture":[51],"by":[52],"embeddings.":[54],"Additionally,":[55],"the":[56,91,103,106,113,130,141,147,182,196,207,249],"common":[57],"co-occurring":[58,191],"coupling":[60],"of":[61,99,108,132],"further":[64],"post":[65],"challenges":[67],"in":[68,255],"effective":[69],"modeling":[70],"aligning":[72],"In":[77],"this":[78],"paper,":[79],"we":[80,116,161,194,215],"regard":[81],"as":[83,96],"Multi-Instance":[85],"Multi-Label":[86],"(MIML)":[87],"learning":[88],"problem,":[89,115],"where":[90],"sequence":[93],"viewed":[95],"bag":[98,107],"corresponding":[109],"phrases.":[110],"To":[111,187],"address":[112],"MIML":[114],"propose":[117],"novel":[119],"Multi-Granularity":[120],"Semantics":[121],"Interaction":[122],"(MGSI)":[123],"approach,":[124],"effectively":[126],"captures":[127],"aligns":[129],"semantics":[131,170,174,183,221],"across":[137],"various":[138],"levels.":[139],"Specifically,":[140],"MGSI":[142],"approach":[143],"initially":[144],"decomposes":[145],"both":[146],"into":[152],"three":[153],"hierarchical":[154],"levels:":[155],"token,":[156,217],"instance,":[157,218],"bag.":[159],"Then,":[160],"graph":[163],"neural":[164],"networks":[165],"explicitly":[167],"model":[168,190],"their":[169,212],"correlation":[171],"perform":[173],"interaction":[175,222],"at":[176,184],"these":[177],"respective":[178],"levels,":[179],"capturing":[181],"granularities.":[186],"identify":[188],"motions,":[193],"measure":[195],"frame-wise":[197],"semantic":[198],"consistency":[199],"between":[200],"then":[203],"fuse":[204],"interact":[206],"accordant":[208],"ones":[209],"refine":[211],"representations.":[213],"Finally,":[214],"exploit":[216],"bag-wise":[220],"comprehensively":[224],"sequence.":[229],"We":[230],"evaluated":[231],"our":[232],"on":[234,257,263],"two":[235],"widely-used":[236],"benchmark":[237],"datasets,":[238],"HumanML3D":[239,258],"KIT-ML.":[241,264],"The":[242],"proposed":[243],"method":[244],"achieves":[245],"improvements,":[247],"outperforming":[248],"state-of-the-art":[250],"23.09%":[253],"increase":[254,262],"Rsum":[256],"21.84%":[261]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}