{"id":"https://openalex.org/W4415240513","doi":"https://doi.org/10.1109/iccv51701.2025.00634","title":"UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling","display_name":"UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415240513","doi":"https://doi.org/10.1109/iccv51701.2025.00634"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00634","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.14604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100321113","display_name":"P. R. Li","orcid":"https://orcid.org/0000-0002-1603-3646"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiming Li","raw_affiliation_strings":["Peking University, Shenzhen Graduate School,State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen Graduate School,State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441382","display_name":"Ziyi Wang","orcid":"https://orcid.org/0000-0002-9007-1210"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Wang","raw_affiliation_strings":["Peking University, Shenzhen Graduate School,State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen Graduate School,State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102399202","display_name":"Yulin Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulin Yuan","raw_affiliation_strings":["The Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410370","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0003-3629-2626"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Peking University, Shenzhen Graduate School,State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen Graduate School,State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078150685","display_name":"Xiangming Meng","orcid":"https://orcid.org/0000-0003-3379-1868"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangming Meng","raw_affiliation_strings":["The Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Zhejiang University-University of Illinois Urbana-Champaign Institute, Zhejiang University","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085245110","display_name":"Junsong Yuan","orcid":"https://orcid.org/0000-0002-7324-7034"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junsong Yuan","raw_affiliation_strings":["State University of New York at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705472","display_name":"Mengyuan Liu","orcid":"https://orcid.org/0000-0002-6332-8316"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyuan Liu","raw_affiliation_strings":["Peking University, Shenzhen Graduate School,State Key Laboratory of General Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen Graduate School,State Key Laboratory of General Artificial Intelligence","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22599129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6738","last_page":"6747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.7534999847412109},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6389999985694885},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5418999791145325},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5317999720573425},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43630000948905945},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.42340001463890076},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4077000021934509},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3962000012397766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617999911308289},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.7534999847412109},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6389999985694885},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5418999791145325},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.36980000138282776},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C174440990","wikidata":"https://www.wikidata.org/wiki/Q681349","display_name":"Point-to-point","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.25619998574256897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00634","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:2508.14604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.14604","pdf_url":"https://arxiv.org/pdf/2508.14604","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.14604","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.14604","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:2508.14604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.14604","pdf_url":"https://arxiv.org/pdf/2508.14604","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4220163454","display_name":null,"funder_award_id":"2024A1515012089","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G660169824","display_name":null,"funder_award_id":"62473007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415240513.pdf","grobid_xml":"https://content.openalex.org/works/W4415240513.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Point":[0],"cloud":[1,48,59,91],"videos":[2,49],"capture":[3],"dynamic":[4],"3D":[5],"motion":[6,133],"while":[7],"reducing":[8],"the":[9,43,57,75,84,112,126,149,171,180],"effects":[10],"of":[11,46,115,182],"lighting":[12],"and":[13,23,120,132,142,164,175],"viewpoint":[14],"variations,":[15],"making":[16],"them":[17],"highly":[18],"effective":[19,113],"for":[20],"recognizing":[21],"subtle":[22],"continuous":[24],"human":[25],"actions.":[26],"Although":[27],"Selective":[28],"State":[29,78],"Space":[30,79],"Models":[31],"(SSMs)":[32],"have":[33],"shown":[34],"good":[35],"performance":[36],"in":[37,87],"sequence":[38,64],"modeling":[39,53],"with":[40],"linear":[41],"complexity,":[42],"spatio-temporal":[44,140],"disorder":[45],"point":[47,58,90],"hinders":[50],"their":[51],"unidirectional":[52],"when":[54],"directly":[55],"unfolding":[56],"video":[60],"into":[61,104],"a":[62],"1D":[63],"through":[65,107,160],"temporally":[66,121],"sequential":[67],"scanning.":[68],"To":[69,144],"address":[70],"this":[71],"challenge,":[72],"we":[73,94],"propose":[74],"Unified":[76],"Spatio-Temporal":[77,135],"Model":[80],"(UST-SSM),":[81],"which":[82,100],"extends":[83],"latest":[85],"advancements":[86],"SSMs":[88],"to":[89],"videos.":[92],"Specifically,":[93],"introduce":[95],"Spatial-Temporal":[96],"Selection":[97],"Scanning":[98],"(STSS),":[99],"reorganizes":[101],"unordered":[102],"points":[103,116],"semantic-aware":[105],"sequences":[106],"prompt-guided":[108],"clustering,":[109],"thereby":[110],"enabling":[111],"utilization":[114,163],"that":[117],"are":[118],"spatially":[119],"distant":[122],"yet":[123],"similar":[124],"within":[125,148],"sequence.":[127],"For":[128],"missing":[129],"4D":[130,177],"geometric":[131],"details,":[134],"Structure":[136],"Aggregation":[137],"(STSA)":[138],"aggregates":[139],"features":[141],"compensates.":[143],"improve":[145],"temporal":[146,158],"interaction":[147],"sampled":[150],"sequence,":[151],"Temporal":[152],"Interaction":[153],"Sampling":[154],"(TIS)":[155],"enhances":[156],"fine-grained":[157],"dependencies":[159],"non-anchor":[161],"frame":[162],"expanded":[165],"receptive":[166],"fields.":[167],"Experimental":[168],"results":[169],"on":[170],"MSR-Action3D,":[172],"NTU":[173],"RGB+D,":[174],"Synthia":[176],"datasets":[178],"validate":[179],"effectiveness":[181],"our":[183],"method.":[184],"Our":[185],"code":[186],"is":[187],"available":[188],"at":[189],"https://github.com/wangzy01/UST-SSM.":[190]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-16T00:00:00"}