{"id":"https://openalex.org/W4416272529","doi":"https://doi.org/10.1109/3dv69130.2026.00166","title":"Dense Motion Captioning","display_name":"Dense Motion Captioning","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W4416272529","doi":"https://doi.org/10.1109/3dv69130.2026.00166"},"language":"en","primary_location":{"id":"doi:10.1109/3dv69130.2026.00166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","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/2511.05369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102863671","display_name":"Shijing Xu","orcid":"https://orcid.org/0009-0000-4510-2615"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Shiyao Xu","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120404913","display_name":"Benedetta Liberatori","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Benedetta Liberatori","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024292507","display_name":"G\u00fcl Varol","orcid":"https://orcid.org/0000-0002-8438-6152"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00fcl Varol","raw_affiliation_strings":["Univ Gustave Eiffel, CNRS,LIGM, Ecole des Ponts, IP Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ Gustave Eiffel, CNRS,LIGM, Ecole des Ponts, IP Paris","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210154111"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046536801","display_name":"Paolo Rota","orcid":"https://orcid.org/0000-0003-0663-5659"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Rota","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.00833556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1750","last_page":"1759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6887000203132629,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6887000203132629,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19920000433921814,"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":0.05290000140666962,"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/motion","display_name":"Motion (physics)","score":0.8072999715805054},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6729999780654907},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6164000034332275},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.5464000105857849},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.44269999861717224},{"id":"https://openalex.org/keywords/structure-from-motion","display_name":"Structure from motion","score":0.4041999876499176},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/human-motion","display_name":"Human motion","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.8072999715805054},{"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/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6729999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6644999980926514},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.5464000105857849},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5383999943733215},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.4041999876499176},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.35899999737739563},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C20864712","wikidata":"https://www.wikidata.org/wiki/Q667800","display_name":"Biological motion","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/3dv69130.2026.00166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.05369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.05369","pdf_url":"https://arxiv.org/pdf/2511.05369","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":"pmh:oai:iris.unitn.it:11572/490190","is_oa":false,"landing_page_url":"https://hdl.handle.net/11572/490190","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2511.05369","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.05369","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:2511.05369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.05369","pdf_url":"https://arxiv.org/pdf/2511.05369","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,48,166],"3D":[3,40,167],"human":[4,41],"motion":[5,19,42,81,98,133,168],"and":[6,36,53,170],"language":[7,128],"integration":[8],"have":[9],"primarily":[10],"focused":[11],"on":[12,151,156],"text-to-motion":[13],"generation,":[14],"leaving":[15],"the":[16,68,73],"task":[17,30],"of":[18,56,102],"understanding":[20,169],"relatively":[21],"unexplored.":[22],"We":[23,118],"introduce":[24],"Dense":[25],"Motion":[26,70],"Captioning,":[27],"a":[28,89,122,126,131,160],"novel":[29],"that":[31,124,145],"aims":[32],"to":[33,110,136],"temporally":[34,139],"localize":[35],"caption":[37],"actions":[38,104],"within":[39],"sequences.":[43],"Current":[44],"datasets":[45],"fall":[46],"short":[47,57],"providing":[49],"detailed":[50],"temporal":[51,85,116],"annotations":[52],"predominantly":[54],"consist":[55],"sequences":[58,82],"featuring":[59,77],"few":[60],"actions.":[61],"To":[62],"overcome":[63],"these":[64],"limitations,":[65],"we":[66],"present":[67,120],"Complex":[69],"Dataset":[71],"(CompMo),":[72],"first":[74],"large-scale":[75],"dataset":[76],"richly":[78],"annotated,":[79],"complex":[80],"with":[83,114,130],"precise":[84],"boundaries.":[86],"Built":[87],"through":[88],"carefully":[90],"designed":[91],"data":[92],"generation":[93],"pipeline,":[94],"CompMo":[95,152],"includes":[96],"60,000":[97],"sequences,":[99],"each":[100],"composed":[101],"multiple":[103],"ranging":[105],"from":[106],"at":[107],"least":[108],"two":[109],"ten,":[111],"accurately":[112],"annotated":[113],"their":[115],"extents.":[117],"further":[119],"DEMO,":[121],"model":[123,129],"integrates":[125],"large":[127],"simple":[132],"adapter,":[134],"trained":[135],"generate":[137],"dense,":[138],"grounded":[140],"captions.":[141],"Our":[142],"experiments":[143],"show":[144],"DEMO":[146],"substantially":[147],"outperforms":[148],"existing":[149],"methods":[150],"as":[153,155],"well":[154],"adapted":[157],"benchmarks,":[158],"establishing":[159],"robust":[161],"baseline":[162],"for":[163],"future":[164],"research":[165],"captioning.":[171]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-11T00:00:00"}