{"id":"https://openalex.org/W4417082390","doi":"https://doi.org/10.1109/iccv51701.2025.01018","title":"MonSTeR: A Unified Model for Motion, Scene, Text Retrieval","display_name":"MonSTeR: A Unified Model for Motion, Scene, Text Retrieval","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417082390","doi":"https://doi.org/10.1109/iccv51701.2025.01018"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01018","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/2510.03200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092489710","display_name":"Luca Collorone","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Collorone","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109271397","display_name":"Matteo Gioia","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Gioia","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080463847","display_name":"Massimiliano Pappa","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimiliano Pappa","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Paolo Leoni","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Leoni","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113204328","display_name":"Giovanni Ficarra","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Ficarra","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006347979","display_name":"Or Litany","orcid":"https://orcid.org/0000-0001-6700-7379"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Or Litany","raw_affiliation_strings":["Technion, NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, NVIDIA","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019615617","display_name":"Indro Spinelli","orcid":"https://orcid.org/0000-0003-1963-3548"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Indro Spinelli","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033120247","display_name":"Fabio Galasso","orcid":"https://orcid.org/0000-0003-1875-7813"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Galasso","raw_affiliation_strings":["Sapienza University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"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":0.34749084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10940","last_page":"10949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8172000050544739,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8172000050544739,"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/T12290","display_name":"Human Motion and Animation","score":0.09220000356435776,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.028300000354647636,"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/context","display_name":"Context (archaeology)","score":0.6043000221252441},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5932000279426575},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.5020999908447266},{"id":"https://openalex.org/keywords/monster","display_name":"Monster","score":0.5012000203132629},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.49709999561309814},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993000149726868},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6043000221252441},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192000269889832},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C2778626061","wikidata":"https://www.wikidata.org/wiki/Q6902671","display_name":"Monster","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4341000020503998},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.375},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.01018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01018","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:2510.03200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.03200","pdf_url":"https://arxiv.org/pdf/2510.03200","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.uniroma1.it:11573/1753073","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1753073","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"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":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2510.03200","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.03200","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.03200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.03200","pdf_url":"https://arxiv.org/pdf/2510.03200","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":[{"id":"https://openalex.org/G4135271260","display_name":null,"funder_award_id":"B53C22003870006","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4497343234","display_name":null,"funder_award_id":"ISF 624/25,ISF 2903/25","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Intention":[0],"drives":[1],"human":[2,120],"movement":[3,9,39],"in":[4],"complex":[5],"environments,":[6],"but":[7,90],"such":[8],"can":[10],"only":[11],"happen":[12],"if":[13],"the":[14,20,35,44,54,61,83,113,129],"surrounding":[15,45],"context":[16,46],"supports":[17],"it.":[18],"Despite":[19],"intuitive":[21],"nature":[22],"of":[23,63,115,131],"this":[24,49],"mechanism,":[25],"existing":[26],"research":[27],"has":[28],"not":[29],"yet":[30],"provided":[31],"tools":[32],"to":[33,81],"evaluate":[34],"alignment":[36,114],"between":[37,86],"skeletal":[38],"(motion),":[40],"intention":[41],"(text),":[42],"and":[43,75,140,144],"(scene).":[47],"In":[48],"work,":[50],"we":[51,111],"introduce":[52],"MonSTeR,":[53],"first":[55],"MOtioN-Scene-TExt":[56],"Retrieval":[57],"model.":[58],"Inspired":[59],"by":[60,72],"modeling":[62],"higher-order":[64],"relations,":[65],"MonSTeR":[66,80,100],"constructs":[67],"a":[68,123],"unified":[69],"latent":[70,133],"space":[71,134],"leveraging":[73],"unimodal":[74,108],"cross-modal":[76],"representations.":[77,109],"This":[78],"allows":[79],"capture":[82],"intricate":[84],"dependencies":[85],"modalities,":[87],"enabling":[88],"flexible":[89],"robust":[91],"retrieval":[92,117],"across":[93],"various":[94],"tasks.":[95],"Our":[96],"results":[97],"show":[98],"that":[99,104],"outperforms":[101],"trimodal":[102],"models":[103,146],"rely":[105],"solely":[106],"on":[107,135],"Furthermore,":[110],"validate":[112],"our":[116],"scores":[118],"with":[119],"preferences":[121],"through":[122],"dedicated":[124],"user":[125],"study.":[126],"We":[127],"demonstrate":[128],"versatility":[130],"MonSTeR's":[132],"zero-shot":[136],"in-Scene":[137],"Object":[138],"Placement":[139],"Motion":[141],"Captioning.":[142],"Code":[143],"pre-trained":[145],"are":[147],"available":[148],"at":[149],"github.com/colloroneluca/MonSTeR.":[150]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
