{"id":"https://openalex.org/W7130528968","doi":"https://doi.org/10.1109/ictc66702.2025.11388400","title":"Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization","display_name":"Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130528968","doi":"https://doi.org/10.1109/ictc66702.2025.11388400"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104342254","display_name":"Sukhyun Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sukhyun Jeong","raw_affiliation_strings":["Kwangwoon University,Division of Robotics,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Division of Robotics,Seoul,Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049911677","display_name":"Hong-Gi Shin","orcid":null},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Gi Shin","raw_affiliation_strings":["Kwangwoon University,Division of Robotics,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Division of Robotics,Seoul,Korea","institution_ids":["https://openalex.org/I161024014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101817296","display_name":"Yonghoon Choi","orcid":"https://orcid.org/0000-0002-5218-4513"},"institutions":[{"id":"https://openalex.org/I161024014","display_name":"Kwangwoon University","ror":"https://ror.org/02e9zc863","country_code":"KR","type":"education","lineage":["https://openalex.org/I161024014"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong-Hoon Choi","raw_affiliation_strings":["Kwangwoon University,Division of Robotics,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwangwoon University,Division of Robotics,Seoul,Korea","institution_ids":["https://openalex.org/I161024014"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161024014"],"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":"568","last_page":"573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9304999709129333,"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":0.9304999709129333,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.02459999918937683,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.01140000019222498,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7935000061988831},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5320000052452087},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5235999822616577},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48489999771118164},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.4819999933242798},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4034999907016754},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7935000061988831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.667900025844574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5764999985694885},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4819999933242798},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4034999907016754},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32429999113082886},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31200000643730164},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.263700008392334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322064","display_name":"Korea Institute for Advancement of Technology","ror":"https://ror.org/015w1qa96"},{"id":"https://openalex.org/F4320324625","display_name":"Korea Agency for Infrastructure Technology Advancement","ror":"https://ror.org/00rxf7n07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2971856312","https://openalex.org/W4288079574","https://openalex.org/W4312635677","https://openalex.org/W4312920950","https://openalex.org/W4312974539","https://openalex.org/W4386076288","https://openalex.org/W4400839976","https://openalex.org/W4402754111","https://openalex.org/W4402754184","https://openalex.org/W4403878062","https://openalex.org/W4404002639","https://openalex.org/W4415800789"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,108],"text-to-motion":[3],"has":[4],"advanced":[5],"both":[6],"3D":[7],"human":[8],"motion":[9,13,16,37,57,78,130],"generation":[10,17],"and":[11,69,103],"text-based":[12],"control.":[14],"Controllable":[15],"(CoMo),":[18],"which":[19],"enables":[20],"intuitive":[21],"control,":[22],"typically":[23],"relies":[24],"on":[25,85],"pose":[26,31,51,72,122],"code":[27],"representations;":[28],"however,":[29],"discrete":[30],"codes":[32,73,123],"alone":[33],"cannot":[34],"capture":[35],"fine-grained":[36],"details,":[38],"limiting":[39],"expressiveness.":[40],"To":[41],"address":[42],"this":[43],"limitation,":[44],"we":[45],"propose":[46],"a":[47,105],"method":[48],"that":[49,90],"augments":[50],"code\u2013based":[52],"latent":[53],"representations":[54],"with":[55],"continuous":[56],"features":[58],"using":[59],"residual":[60],"vector":[61],"quantization":[62],"(RVQ).":[63],"This":[64],"approach":[65],"preserves":[66],"the":[67,86,94,126],"interpretability":[68],"manipulability":[70],"of":[71,117],"while":[74],"effectively":[75],"capturing":[76],"subtle":[77],"characteristics":[79],"such":[80],"as":[81],"high-frequency":[82],"details.":[83],"Experiments":[84],"HumanML3D":[87],"dataset":[88],"show":[89],"our":[91],"model":[92],"reduces":[93],"Fr\u00e9chet":[95],"Inception":[96],"Distance":[97],"(FID)":[98],"from":[99,111],"0.041":[100],"to":[101,113],"0.015":[102],"yields":[104],"slight":[106],"improvement":[107],"Top-1":[109],"R-Precision":[110],"0.508":[112],"0.510.":[114],"Qualitative":[115],"analysis":[116],"pairwise":[118],"direction":[119],"similarity":[120],"between":[121],"further":[124],"demonstrates":[125],"model\u2019s":[127],"controllability":[128],"for":[129],"editing.":[131]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}