{"id":"https://openalex.org/W4417100894","doi":"https://doi.org/10.1109/iccv51701.2025.00835","title":"High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation","display_name":"High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417100894","doi":"https://doi.org/10.1109/iccv51701.2025.00835"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.11017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083780769","display_name":"Runyang Feng","orcid":"https://orcid.org/0000-0002-4912-6646"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runyang Feng","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004895698","display_name":"Hyung Jin Chang","orcid":"https://orcid.org/0000-0001-7495-9677"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hyung Jin Chang","raw_affiliation_strings":["School of Computer Science, University of Birmingham"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Birmingham","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017172598","display_name":"Tze Ho Elden Tse","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tze Ho Elden Tse","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101531468","display_name":"Boeun Kim","orcid":"https://orcid.org/0000-0003-3374-4033"},"institutions":[{"id":"https://openalex.org/I89015989","display_name":"Dankook University","ror":"https://ror.org/058pdbn81","country_code":"KR","type":"education","lineage":["https://openalex.org/I89015989"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Boeun Kim","raw_affiliation_strings":["Dankook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dankook University","institution_ids":["https://openalex.org/I89015989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113609049","display_name":"Yi Chang","orcid":"https://orcid.org/0000-0002-1914-1028"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072415508","display_name":"Yixing Gao","orcid":"https://orcid.org/0000-0003-4475-2792"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Gao","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36392783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9641000032424927,"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":0.9641000032424927,"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":0.01769999973475933,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.004100000020116568,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/benchmark","display_name":"Benchmark (surveying)","score":0.6391000151634216},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.4580000042915344},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4271000027656555},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3921999931335449},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.3693000078201294},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3589000105857849},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3549000024795532},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.3296000063419342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.682200014591217},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6391000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.605400025844574},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.00835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.11017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.11017","pdf_url":"https://arxiv.org/pdf/2510.11017","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire/65c0d079-98d6-4cb4-99aa-555dd6c1b0dd","is_oa":true,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/65c0d079-98d6-4cb4-99aa-555dd6c1b0dd","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Feng, R, Chang, H J, Tse, T H E, Kim, B, Chang, Y & Gao, Y 2026, High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation. in 2025 IEEE/CVF International Conference on Computer Vision (ICCV). International Conference on Computer Vision (ICCV), IEEE, pp. 8929-8938, International Conference on Computer Vision 2025, Honolulu, Hawaii, United States, 19/10/25. https://doi.org/10.1109/ICCV51701.2025.00835","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.2510.11017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.11017","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.11017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.11017","pdf_url":"https://arxiv.org/pdf/2510.11017","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1211044700","display_name":null,"funder_award_id":"U2341229","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1866149168","display_name":null,"funder_award_id":"62203184,W2421093","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6592930967","display_name":null,"funder_award_id":"2023YFF0905400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8022846941","display_name":null,"funder_award_id":"20250205079GH","funder_id":"https://openalex.org/F4320322174","funder_display_name":"People's Government of Jilin Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322174","display_name":"People's Government of Jilin Province","ror":"https://ror.org/02fzqav45"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417100894.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modeling":[0],"high-resolution":[1,90,139,170],"spatiotemporal":[2,36,140],"representations,":[3],"including":[4],"both":[5],"global":[6,55,83,136,167],"dynamic":[7,58],"contexts":[8,107],"(e.g.,":[9,18],"holistic":[10],"human":[11,27],"motion":[12,16],"tendencies)":[13],"and":[14,56,60,137,158,160],"local":[15,57,138],"details":[17,186],"high-frequency":[19,185],"changes":[20],"of":[21,42,67,187],"keypoints),":[22],"is":[23],"essential":[24],"for":[25,89,142],"video-based":[26],"pose":[28],"estimation":[29],"(VHPE).":[30],"Current":[31],"state-of-the-art":[32,203],"methods":[33],"typically":[34],"unify":[35],"learning":[37],"within":[38],"a":[39,124,148,175],"single":[40],"type":[41],"modeling":[43,59,105],"structure":[44],"(convolution":[45],"or":[46],"attention-based":[47],"blocks),":[48],"which":[49,152],"inherently":[50],"have":[51,100],"difficulties":[52],"in":[53,104],"balancing":[54],"may":[61],"bias":[62],"the":[63,93,184,199],"network":[64],"to":[65,70,115,133,164,182],"one":[66],"them,":[68],"leading":[69],"suboptimal":[71],"performance.":[72],"Moreover,":[73],"existing":[74],"VHPE":[75,204],"models":[76,96],"suffer":[77],"from":[78,130,169],"quadratic":[79],"complexity":[80],"when":[81],"capturing":[82],"dependencies,":[84],"limiting":[85],"their":[86],"applicability":[87],"especially":[88],"sequences.":[91,171],"Recently,":[92],"state":[94],"space":[95],"(known":[97],"as":[98],"Mamba)":[99],"demonstrated":[101],"significant":[102],"potential":[103],"long-range":[106],"with":[108],"linear":[109],"complexity;":[110],"however,":[111],"they":[112],"are":[113],"restricted":[114],"1D":[116],"sequential":[117],"data.":[118],"In":[119],"this":[120],"paper,":[121],"we":[122,145],"present":[123],"novel":[125],"framework":[126],"that":[127,198],"extends":[128],"Mamba":[129,181],"two":[131],"aspects":[132],"separately":[134],"learn":[135],"representations":[141,168],"VHPE.":[143],"Specifically,":[144],"first":[146],"propose":[147],"Global":[149],"Spatiotemporal":[150],"Mamba,":[151],"performs":[153],"6D":[154],"selective":[155],"space-time":[156,177],"scan":[157,162],"spatial-":[159],"temporal-modulated":[161],"merging":[163],"efficiently":[165],"extract":[166],"We":[172],"further":[173],"introduce":[174],"windowed":[176],"scan-based":[178],"Local":[179],"Refinement":[180],"enhance":[183],"localized":[188],"keypoint":[189],"motions.":[190],"Extensive":[191],"experiments":[192],"on":[193],"four":[194],"benchmark":[195],"datasets":[196],"demonstrate":[197],"proposed":[200],"model":[201],"outperforms":[202],"approaches":[205],"while":[206],"achieving":[207],"better":[208],"computational":[209],"trade-offs.":[210]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-15T00:00:00"}