{"id":"https://openalex.org/W4415965606","doi":"https://doi.org/10.1109/iccv51701.2025.00666","title":"4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads","display_name":"4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415965606","doi":"https://doi.org/10.1109/iccv51701.2025.00666"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.00666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00666","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.17664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100343973","display_name":"Ling Liu","orcid":"https://orcid.org/0000-0001-8297-9088"},"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":"Ling Liu","raw_affiliation_strings":["IIIS, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102080180","display_name":"Tian Jun","orcid":null},"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":"Jun Tian","raw_affiliation_strings":["IIIS, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100421687","display_name":"Yi Li","orcid":"https://orcid.org/0000-0003-0152-6605"},"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":"Li Yi","raw_affiliation_strings":["IIIS, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7089","last_page":"7098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.26930001378059387,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.26930001378059387,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.09910000115633011,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.09600000083446503,"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/segmentation","display_name":"Segmentation","score":0.6793000102043152},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6574000120162964},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5842000246047974},{"id":"https://openalex.org/keywords/crowds","display_name":"Crowds","score":0.5238999724388123},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47690001130104065},{"id":"https://openalex.org/keywords/workspace","display_name":"Workspace","score":0.38749998807907104},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3747999966144562},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.37049999833106995},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.34619998931884766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330000042915344},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5842000246047974},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5370000004768372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47690001130104065},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.38749998807907104},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.34619998931884766},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2776741261","wikidata":"https://www.wikidata.org/wiki/Q3027665","display_name":"Live streaming","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C45617602","wikidata":"https://www.wikidata.org/wiki/Q465266","display_name":"Crowd simulation","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25200000405311584},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00666","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:2510.17664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17664","pdf_url":"https://arxiv.org/pdf/2510.17664","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.2510.17664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.17664","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:2510.17664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17664","pdf_url":"https://arxiv.org/pdf/2510.17664","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415965606.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"4D":[0,67],"panoptic":[1],"segmentation":[2,68],"in":[3,21,164,169],"a":[4,29,41,46,94],"streaming":[5,52,82],"setting":[6],"is":[7,33,56],"critical":[8],"for":[9,123,134],"highly":[10],"dynamic":[11,137,167],"environments,":[12],"such":[13],"as":[14],"evacuating":[15],"dense":[16],"crowds":[17],"and":[18,58,66,97,107,113,132,136,148,152],"autonomous":[19],"driving":[20],"complex":[22,170],"scenarios,":[23],"where":[24],"real-time,":[25],"fine-grained":[26],"perception":[27,83],"within":[28],"constrained":[30],"time":[31],"budget":[32],"essential.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"introduce":[39],"4DSegStreamer,":[40],"novel":[42],"framework":[43,55],"that":[44],"employs":[45],"Dual-Thread":[47],"System":[48],"to":[49,70,80,110],"efficiently":[50],"process":[51],"frames.":[53],"The":[54,90,101,117],"general":[57],"can":[59],"be":[60],"seamlessly":[61],"integrated":[62],"into":[63],"existing":[64,81],"3D":[65],"methods":[69],"enable":[71],"real-time":[72],"capability.":[73],"It":[74],"also":[75],"demonstrates":[76],"superior":[77],"robustness":[78],"compared":[79],"approaches,":[84],"particularly":[85,163],"under":[86],"high":[87],"FPS":[88],"conditions.":[89],"system":[91],"consists":[92],"of":[93,160],"predictive":[95,102],"thread":[96,103,119],"an":[98],"inference":[99,118],"thread.":[100],"leverages":[104],"historical":[105],"motion":[106],"geometric":[108],"information":[109],"extract":[111],"features":[112],"forecast":[114],"future":[115],"dynamics.":[116],"ensures":[120],"timely":[121],"prediction":[122],"incoming":[124],"frames":[125],"by":[126],"aligning":[127],"with":[128],"the":[129,144,149,158],"latest":[130],"memory":[131],"compensating":[133],"ego-motion":[135],"object":[138],"movements.":[139],"We":[140],"evaluate":[141],"4DSegStreamer":[142],"on":[143],"indoor":[145],"HOI4D":[146],"dataset":[147],"outdoor":[150],"SemanticKITTI":[151],"nuScenes":[153],"datasets.":[154],"Comprehensive":[155],"experiments":[156],"demonstrate":[157],"effectiveness":[159],"our":[161],"approach,":[162],"accurately":[165],"predicting":[166],"objects":[168],"scenes.":[171]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-22T00:00:00"}