{"id":"https://openalex.org/W4416960160","doi":"https://doi.org/10.1109/wacv61042.2026.00313","title":"PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications","display_name":"PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416960160","doi":"https://doi.org/10.1109/wacv61042.2026.00313"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/2512.01383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027384671","display_name":"Yunze Liu","orcid":"https://orcid.org/0009-0002-3148-8822"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunze Liu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032942801","display_name":"Zifan Wang","orcid":"https://orcid.org/0000-0003-3394-8060"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zifan Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111341363","display_name":"Peiran Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peiran Wu","raw_affiliation_strings":["University of Bristol"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051951717","display_name":"Jiayang Ao","orcid":"https://orcid.org/0000-0001-6416-1215"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiayang Ao","raw_affiliation_strings":["The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.01595436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3203","last_page":"3212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3312000036239624,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3312000036239624,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.1889999955892563,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10709","display_name":"Social Robot Interaction and HRI","score":0.05829999968409538,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6815000176429749},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5677000284194946},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5094000101089478},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4318000078201294},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.39640000462532043},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3831999897956848},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.3695000112056732},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.35740000009536743},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939000129699707},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6815000176429749},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5196999907493591},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42100000381469727},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.01383","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01383","pdf_url":"https://arxiv.org/pdf/2512.01383","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2512.01383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.01383","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.01383","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01383","pdf_url":"https://arxiv.org/pdf/2512.01383","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416960160.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"dynamic":[1],"4D":[2,43,69,161,166],"environments\u20143D":[3],"space":[4],"evolving":[5],"over":[6],"time\u2014is":[7],"critical":[8],"for":[9,72],"robotic":[10,158],"and":[11,36,51,58,75,96,165,176,180],"interactive":[12],"systems.":[13],"These":[14],"applications":[15],"demand":[16],"systems":[17],"that":[18,129],"can":[19],"process":[20],"streaming":[21],"point":[22],"cloud":[23],"video":[24],"in":[25],"real-time,":[26],"often":[27,55],"under":[28],"resource":[29],"constraints,":[30],"while":[31],"also":[32],"benefiting":[33],"from":[34],"past":[35],"present":[37],"observations":[38],"when":[39],"available.":[40],"However,":[41],"current":[42],"backbone":[44,70],"networks":[45],"rely":[46],"heavily":[47],"on":[48,141,173],"spatiotemporal":[49],"convolutions":[50],"Transformers,":[52],"which":[53,88],"are":[54],"computationally":[56],"intensive":[57],"poorly":[59],"suited":[60],"to":[61,106],"real-time":[62],"applications.":[63],"We":[64,150],"propose":[65],"PointNet4D,":[66],"a":[67,82,123],"lightweight":[68],"optimized":[71],"both":[73],"online":[74,109],"offline":[76],"settings.":[77],"At":[78],"its":[79],"core":[80],"is":[81],"Hybrid":[83],"Mamba-Transformer":[84],"temporal":[85,118],"fusion":[86],"block,":[87],"integrates":[89],"the":[90,97,174],"efficient":[91],"state-space":[92],"modeling":[93,99],"of":[94,101],"Mamba":[95],"bidirectional":[98],"power":[100],"Transformers.":[102],"This":[103],"enables":[104],"PointNet4D":[105],"handle":[107],"variable-length":[108],"sequences":[110],"efficiently":[111],"across":[112,133,138,147],"different":[113],"deployment":[114],"scenarios.":[115],"To":[116],"enhance":[117],"understanding,":[119],"we":[120],"introduce":[121],"4DMAP,":[122],"frame-wise":[124],"masked":[125],"auto-regressive":[126],"pretraining":[127],"strategy":[128],"captures":[130],"motion":[131],"cues":[132],"frames.":[134],"Our":[135],"extensive":[136],"evaluations":[137],"9":[139],"tasks":[140],"7":[142],"datasets,":[143],"demonstrating":[144],"consistent":[145],"improvements":[146],"diverse":[148],"domains.":[149],"further":[151],"demonstrate":[152],"PointNet4D\u2019s":[153],"utility":[154],"by":[155],"building":[156],"two":[157],"application":[159],"systems:":[160],"Diffusion":[162],"Policy":[163],"(DP4)":[164],"Imitation":[167],"Learning":[168],"(4DIL),":[169],"achieving":[170],"substantial":[171],"gains":[172],"RoboTwin":[175],"HandoverSim":[177],"benchmarks.":[178],"Code":[179],"checkpoints":[181],"available:":[182],"https://github.com/yunzeliu/MAP":[183]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-03T00:00:00"}
