{"id":"https://openalex.org/W4400531282","doi":"https://doi.org/10.1145/3626772.3657804","title":"Hierarchical Semantics Alignment for 3D Human Motion Retrieval","display_name":"Hierarchical Semantics Alignment for 3D Human Motion Retrieval","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400531282","doi":"https://doi.org/10.1145/3626772.3657804"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657804","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/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":0.857,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73683185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1083","last_page":"1092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","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/T12290","display_name":"Human Motion and Animation","score":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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":0.7783447504043579},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6543612480163574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5889500975608826},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5180187821388245},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3907557427883148},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38843587040901184},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3701273202896118},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15119895339012146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783447504043579},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6543612480163574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889500975608826},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5180187821388245},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3907557427883148},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38843587040901184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3701273202896118},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15119895339012146}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657804","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1035181375","display_name":null,"funder_award_id":"62206137, 62206200","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G4359249504","display_name":null,"funder_award_id":"2022MS06025","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1967554269","https://openalex.org/W2110119381","https://openalex.org/W2474702929","https://openalex.org/W2956018683","https://openalex.org/W3125772723","https://openalex.org/W3168433561","https://openalex.org/W4288079574","https://openalex.org/W4291926315","https://openalex.org/W4304014690","https://openalex.org/W4312635677","https://openalex.org/W4317796373","https://openalex.org/W4321780110","https://openalex.org/W4366851068","https://openalex.org/W4367060669","https://openalex.org/W4384641262","https://openalex.org/W4386076086","https://openalex.org/W4386076288","https://openalex.org/W4386076485","https://openalex.org/W4386083126","https://openalex.org/W4387963302","https://openalex.org/W4387969585","https://openalex.org/W4390871790","https://openalex.org/W4390872434","https://openalex.org/W4390874197"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W4386051551","https://openalex.org/W2779427294","https://openalex.org/W2725946685","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W2953174548","https://openalex.org/W1528460682"],"abstract_inverted_index":{"Text":[0],"to":[1,15,31,137,193],"3D":[2],"human":[3,118],"Motion":[4],"Retrieval":[5],"(TMR)":[6],"is":[7,30],"a":[8,52,62,109,132,172,186,219],"challenging":[9],"task":[10],"in":[11,42,93],"information":[12],"retrieval,":[13],"aiming":[14],"query":[16],"relevant":[17],"motion":[18,59,82,96,119,149,217,235],"sequences":[19,60,97,150],"with":[20,98],"the":[21,33,71,81,104,126,143,146,157,164,194,203,249,252],"natural":[22],"language":[23],"description.":[24],"The":[25,182],"conventional":[26],"approach":[27],"for":[28,39,69,116],"TMR":[29],"represent":[32],"data":[34],"instances":[35],"as":[36],"point":[37],"embeddings":[38],"alignment.":[40],"However,":[41],"real-world":[43],"scenarios,":[44],"multiple":[45],"motions":[46,177],"often":[47],"co-occur":[48],"and":[49,58,86,131,148,178,196,200,216,229,234,246,269],"superimpose":[50],"on":[51,239,267,271],"single":[53,63],"avatar.":[54],"Simply":[55],"aggregating":[56],"text":[57,147,215,233],"into":[61,151,218],"global":[64,122],"embedding":[65],"may":[66],"be":[67],"inadequate":[68],"capturing":[70,156],"intricate":[72],"semantics":[73,158],"of":[74,80,159,166,205,221,251,265],"superimposing":[75,160,176],"motions.":[76,161],"In":[77],"addition,":[78],"most":[79],"variations":[83],"occur":[84],"locally":[85],"subtly,":[87],"which":[88],"further":[89],"presents":[90],"considerable":[91],"challenges":[92],"precisely":[94],"aligning":[95],"their":[99,179],"corresponding":[100,180],"text.":[101,181],"To":[102],"address":[103],"aforementioned":[105],"challenges,":[106],"we":[107,124,209],"propose":[108,125],"novel":[110],"Hierarchical":[111],"Semantics":[112],"Alignment":[113,129,135],"(HSA)":[114],"framework":[115],"text-to-3D":[117],"retrieval.":[120],"Beyond":[121],"alignment,":[123,169],"Probabilistic-based":[127],"Distribution":[128],"(PDA)":[130],"Descriptors-based":[133],"Fine-grained":[134],"(DFA)":[136],"achieve":[138],"precise":[139,173],"semantic":[140],"matching.":[141],"Specifically,":[142],"PDA":[144,170],"encodes":[145],"multidimensional":[152],"probabilistic":[153,167],"distributions,":[154],"effectively":[155],"By":[162],"optimizing":[163],"problem":[165],"distribution":[168],"achieves":[171],"match":[174],"between":[175,231],"DFA":[183],"first":[184],"adopts":[185],"fine-grained":[187,232],"feature":[188],"gating":[189],"by":[190],"selectively":[191],"filtering":[192],"significant":[195],"representative":[197],"local":[198,212,223,227],"representations":[199,213],"meanwhile":[201],"excluding":[202],"interferences":[204],"meaningless":[206],"features.":[207,236],"Then":[208],"adaptively":[210],"assign":[211],"from":[214],"set":[220],"cross-modal":[222],"aggregated":[224],"descriptors,":[225],"enabling":[226],"comparison":[228],"interaction":[230],"Extensive":[237],"experiments":[238],"two":[240],"widely":[241],"used":[242],"benchmark":[243],"datasets,":[244],"HumanML3D":[245,268],"KIT-ML,":[247],"demonstrate":[248],"effectiveness":[250],"proposed":[253],"method.":[254],"It":[255],"significantly":[256],"outperforms":[257],"existing":[258],"state-of-the-art":[259],"retrieval":[260],"methods,":[261],"achieving":[262],"Rsum":[263],"improvements":[264],"24.74%":[266],"23.08%":[270],"KIT-ML.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}