{"id":"https://openalex.org/W4414990128","doi":"https://doi.org/10.1109/iccv51701.2025.02672","title":"GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding","display_name":"GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414990128","doi":"https://doi.org/10.1109/iccv51701.2025.02672"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02672","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/2506.21188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041044253","display_name":"Zijun Lin","orcid":"https://orcid.org/0009-0009-4502-4157"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zijun Lin","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085200012","display_name":"Shuting He","orcid":"https://orcid.org/0000-0002-1582-5684"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuting He","raw_affiliation_strings":["Shanghai University of Finance and Economics,MoE Key Laboratory of Interdisciplinary Research of Computation and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics,MoE Key Laboratory of Interdisciplinary Research of Computation and Economics","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073326796","display_name":"Cheston Tan","orcid":"https://orcid.org/0000-0003-1248-4906"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheston Tan","raw_affiliation_strings":["Centre for Frontier AI Research, A*STAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Frontier AI Research, A*STAR","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024709593","display_name":"Bihan Wen","orcid":"https://orcid.org/0000-0002-6874-6453"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bihan Wen","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"28774","last_page":"28784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/margin","display_name":"Margin (machine learning)","score":0.6207000017166138},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5756999850273132},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5602999925613403},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5453000068664551},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5415999889373779},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5163000226020813},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4675000011920929},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4560000002384186},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45509999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195000290870667},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6207000017166138},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5756999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5742999911308289},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2533000111579895},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02672","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:2506.21188","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21188","pdf_url":"https://arxiv.org/pdf/2506.21188","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.2506.21188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.21188","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.21188","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21188","pdf_url":"https://arxiv.org/pdf/2506.21188","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/G7344333925","display_name":null,"funder_award_id":"25ZR1402138","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sequential":[0],"grounding":[1,27,69],"in":[2,50,106,153,221],"3D":[3,25,127,160],"point":[4,128],"clouds":[5],"(SG3D)":[6],"refers":[7],"to":[8,62,71,82,88,108,182,188,213],"locating":[9],"sequences":[10],"of":[11,91,142,193],"objects":[12],"by":[13,146],"following":[14],"text":[15,31],"instructions":[16,32,49],"for":[17,95,123],"a":[18,37,120,147,159,190],"daily":[19],"activity":[20],"with":[21,33],"detailed":[22],"steps.":[23],"Current":[24],"visual":[26],"(3DVG)":[28],"methods":[29,70,102,145],"treat":[30],"multiple":[34],"steps":[35,81],"as":[36,56,202],"whole,":[38],"without":[39],"extracting":[40],"useful":[41],"temporal":[42,124,199,210],"information":[43,78,177,195],"from":[44,79],"each":[45],"step.":[46],"However,":[47],"the":[48,73,89,109,139,154,183,222],"SG3D":[51,110,155,223],"often":[52],"contain":[53],"pronouns":[54],"such":[55],"\"it\",":[57],"\"here\"":[58],"and":[59,75,151,174,196,217],"\"the":[60],"same\"":[61],"make":[63],"language":[64,162],"expressions":[65],"concise.":[66],"This":[67],"requires":[68],"understand":[72],"context":[74],"retrieve":[76],"relevant":[77],"previous":[80],"correctly":[83],"locate":[84],"object":[85],"sequences.":[86],"Due":[87],"lack":[90],"an":[92],"effective":[93],"module":[94,122],"collecting":[96],"related":[97],"historical":[98,194],"information,":[99],"state-of-the-art":[100,219],"3DVG":[101,143,215],"face":[103],"significant":[104],"challenges":[105],"adapting":[107],"task.":[111],"To":[112],"fill":[113],"this":[114],"gap,":[115],"we":[116,133,169],"propose":[117],"GroundFlow":[118,137,187],"--":[119],"plug-in":[121],"reasoning":[125,211],"on":[126,165,179],"cloud":[129],"sequential":[130],"grounding.":[131],"Firstly,":[132],"demonstrate":[134],"that":[135],"integrating":[136],"improves":[138],"task":[140],"accuracy":[141],"baseline":[144],"large":[148,161],"margin":[149],"(+7.5\\%":[150],"+10.2\\%)":[152],"benchmark,":[156],"even":[157],"outperforming":[158],"model":[163],"pre-trained":[164],"various":[166],"datasets.":[167,227],"Furthermore,":[168],"selectively":[170],"extract":[171],"both":[172],"short-term":[173],"long-term":[175],"step":[176,203],"based":[178],"its":[180,198],"relevance":[181],"current":[184],"instruction,":[185],"enabling":[186],"take":[189],"comprehensive":[191],"view":[192],"maintain":[197],"understanding":[200],"advantage":[201],"counts":[204],"increase.":[205],"Overall,":[206],"our":[207],"work":[208],"introduces":[209],"capabilities":[212],"existing":[214],"models":[216],"achieves":[218],"performance":[220],"benchmark":[224],"across":[225],"five":[226]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-09T00:00:00"}