{"id":"https://openalex.org/W4413147026","doi":"https://doi.org/10.1109/cvpr52734.2025.01296","title":"Mono3DVLT: Monocular-Video-Based 3D Visual Language Tracking","display_name":"Mono3DVLT: Monocular-Video-Based 3D Visual Language Tracking","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147026","doi":"https://doi.org/10.1109/cvpr52734.2025.01296"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hongkai Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Wei","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397650","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-6511-3079"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070400","display_name":"Shijie Sun","orcid":"https://orcid.org/0000-0003-4043-8448"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Sun","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022848316","display_name":"Mingtao Feng","orcid":"https://orcid.org/0000-0003-0384-3743"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingtao Feng","raw_affiliation_strings":["Xidian University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068123569","display_name":"Xiangyu Song","orcid":"https://orcid.org/0000-0001-8560-1638"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Song","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393404","display_name":"Qi Lei","orcid":"https://orcid.org/0009-0005-7340-1643"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Lei","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003415404","display_name":"Hongli Hu","orcid":"https://orcid.org/0000-0003-1287-1244"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongli Hu","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324880","display_name":"Rong Wang","orcid":"https://orcid.org/0000-0002-0465-9561"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Wang","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008672520","display_name":"Huansheng Song","orcid":"https://orcid.org/0000-0002-8590-0061"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huansheng Song","raw_affiliation_strings":["Chang&#x2019;an University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang&#x2019;an University,China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103837157","display_name":"Naveed Akhtar","orcid":"https://orcid.org/0009-0005-6999-9865"},"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":"Naveed Akhtar","raw_affiliation_strings":["The University of Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne,Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089986388","display_name":"Ajmal Mian","orcid":"https://orcid.org/0000-0002-5206-3842"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ajmal Saeed Mian","raw_affiliation_strings":["University of Western Australia,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Western Australia,Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13886","last_page":"13896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9904999732971191,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9904999732971191,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.982699990272522,"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/monocular","display_name":"Monocular","score":0.7624872922897339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.76014244556427},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6388238072395325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6253538727760315},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4289373457431793},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.42428573966026306},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.1800718605518341},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07295998930931091}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7624872922897339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76014244556427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6388238072395325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6253538727760315},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4289373457431793},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.42428573966026306},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.1800718605518341},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07295998930931091},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W4315836309"],"abstract_inverted_index":{"Visual-Language":[0],"Tracking":[1,120],"(VLT)":[2],"is":[3,30,143,181],"emerging":[4],"as":[5],"a":[6,110,124,134,147,202,208],"promising":[7],"paradigm":[8],"to":[9,23,33,41,88,101],"bridge":[10],"the":[11,20,39,47,74,82,95,115,128,139,182,187,191,212,227],"human-machine":[12],"performance":[13],"gap.":[14],"For":[15],"single":[16,166],"objects,":[17],"VLT":[18,86,100],"broadens":[19],"problem":[21],"scope":[22],"text-driven":[24],"video":[25,162],"comprehension.":[26],"Yet,":[27],"this":[28],"direction":[29],"still":[31],"confined":[32],"2D":[34,170],"spatial":[35],"extents,":[36],"currently":[37],"lacking":[38],"ability":[40],"deal":[42],"with":[43],"3D":[44,55,89,102,117,172],"tracking":[45,56,103,199,203],"in":[46,54,81,236],"confines":[48],"of":[49,70,76,193],"monocular":[50,106],"video.":[51,107],"Unfortunately,":[52],"advances":[53],"mainly":[57],"rely":[58],"on":[59,105,214,226],"expensive":[60],"sensor":[61],"inputs,":[62],"e.g.,":[63],"point":[64],"clouds,":[65],"depth":[66],"measurements,":[67],"radar.":[68],"Absence":[69],"language":[71,158],"counterpart":[72],"for":[73,127,138,160,186,211],"outputs":[75],"these":[77],"mildly":[78],"democratized":[79],"sensors":[80],"literature":[83],"also":[84],"hinders":[85],"expansion":[87],"tracking.":[90],"Addressing":[91],"that,":[92],"we":[93],"make":[94],"first":[96,183],"attempt":[97],"towards":[98],"extending":[99],"based":[104],"We":[108],"present":[109],"comprehensive":[111],"framework,":[112],"introducing":[113],"(i)":[114],"Monocular-Video-based":[116],"Visual":[118],"Language":[119],"(Mono3DVLT)":[121],"task,":[122,129],"(ii)":[123],"large-scale":[125],"dataset":[126,142,231],"called":[130],"Mono3DVLT-V2X,":[131],"and":[132,171,201,232],"(iii)":[133],"customized":[135],"neural":[136,177],"model":[137,206],"task.":[140,189],"Our":[141,176,230],"carefully":[144],"curated,":[145],"leveraging":[146],"Large":[148],"Langauge":[149],"Model":[150],"(LLM)":[151],"followed":[152],"by":[153],"human":[154],"verification,":[155],"composing":[156],"natural":[157],"descriptions":[159],"79,158":[161],"sequences":[163],"aiming":[164],"at":[165],"object":[167],"tracking,":[168],"providing":[169],"bounding":[173],"box":[174],"annotations.":[175],"model,":[178],"termed":[179],"Mono3DVLT-MT,":[180],"targeted":[184],"approach":[185],"Mono3DVLT":[188],"Comprising":[190],"pipeline":[192],"multi-modal":[194],"feature":[195],"extractor,":[196],"visual-language":[197],"encoder,":[198],"decoder":[200],"head,":[204],"our":[205,220],"sets":[207],"strong":[209],"baseline":[210],"task":[213],"Mono3DVLT-V2X.":[215],"Experimental":[216],"results":[217],"show":[218],"that":[219],"method":[221],"significantly":[222],"outperforms":[223],"existing":[224],"techniques":[225],"Mono3DVLT-V2X":[228],"dataset.":[229],"code":[233],"are":[234],"available":[235],"https://github.com/hongkai-wei/Mono3DVLT.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
