{"id":"https://openalex.org/W7128541221","doi":"https://doi.org/10.1109/tip.2026.3661407","title":"Monocular Multi-Object 3D Visual Language Tracking","display_name":"Monocular Multi-Object 3D Visual Language Tracking","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128541221","doi":"https://doi.org/10.1109/tip.2026.3661407","pmid":"https://pubmed.ncbi.nlm.nih.gov/41666070"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3661407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3661407","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"https://orcid.org/0009-0007-1414-6181"},"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":["School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0007-1414-6181","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125522412","display_name":"Rong Wang","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":"Rong Wang","raw_affiliation_strings":["School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0007-7901-5158","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125573250","display_name":"Haixiang Hu","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":"Haixiang Hu","raw_affiliation_strings":["School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0007-0069-9041","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125477531","display_name":"Shijie Sun","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":"Shijie Sun","raw_affiliation_strings":["School of Data Science and Artificial Intelligence, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-4043-8448","affiliations":[{"raw_affiliation_string":"School of Data Science and Artificial Intelligence, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124163607","display_name":"Xiangyu Song","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":"Xiangyu Song","raw_affiliation_strings":["School of Data Science and Artificial Intelligence, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-5550-6354","affiliations":[{"raw_affiliation_string":"School of Data Science and Artificial Intelligence, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, 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":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-0384-3743","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124180015","display_name":"Keyu Guo","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":"Keyu Guo","raw_affiliation_strings":["School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0005-0699-3992","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102665049","display_name":"Yongle Huang","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":"Yongle Huang","raw_affiliation_strings":["School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0007-6462-6087","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hua Cui","orcid":"https://orcid.org/0000-0002-7928-897X"},"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":"Hua Cui","raw_affiliation_strings":["School of Data Science and Artificial Intelligence, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-7928-897X","affiliations":[{"raw_affiliation_string":"School of Data Science and Artificial Intelligence, Chang&#x2019;an University, Xi&#x2019;an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125586291","display_name":"Naveed Akhtar","orcid":null},"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":["School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3406-673X","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.13720469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"2050","last_page":"2065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8535000085830688,"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":0.8535000085830688,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.01720000058412552,"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/T12031","display_name":"Speech and dialogue systems","score":0.01679999940097332,"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/monocular","display_name":"Monocular","score":0.6973000168800354},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5270000100135803},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49320000410079956},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47510001063346863},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4526999890804291},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.42660000920295715},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198000192642212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7440000176429749},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6973000168800354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6563000082969666},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4526999890804291},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.42660000920295715},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27079999446868896}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3661407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3661407","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41666070","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41666070","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6459726691246033,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G193029910","display_name":null,"funder_award_id":"2023YFB4301800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4686645268","display_name":null,"funder_award_id":"Program No. 2024CY2-GJHX-59","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G6594572011","display_name":null,"funder_award_id":"Grant No. 2024YFF0908100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7295744243","display_name":null,"funder_award_id":"Grant No. 2023YFB4301800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320334010","display_name":"Key Research and Development Program of Ningxia","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1995903777","https://openalex.org/W2150066425","https://openalex.org/W2158592639","https://openalex.org/W2222512263","https://openalex.org/W2530887700","https://openalex.org/W2603203130","https://openalex.org/W2794744029","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2913466142","https://openalex.org/W2962766617","https://openalex.org/W2962777203","https://openalex.org/W2962803115","https://openalex.org/W2998434318","https://openalex.org/W3008380142","https://openalex.org/W3035172746","https://openalex.org/W3035564946","https://openalex.org/W3035574168","https://openalex.org/W3084173793","https://openalex.org/W3094000868","https://openalex.org/W3096609285","https://openalex.org/W3130990491","https://openalex.org/W3131716792","https://openalex.org/W3132607695","https://openalex.org/W3167095230","https://openalex.org/W3173871266","https://openalex.org/W3181069167","https://openalex.org/W3187295906","https://openalex.org/W4213019189","https://openalex.org/W4214736485","https://openalex.org/W4286904999","https://openalex.org/W4313072323","https://openalex.org/W4383755718","https://openalex.org/W4385245566","https://openalex.org/W4386076180","https://openalex.org/W4386076331","https://openalex.org/W4386076547","https://openalex.org/W4390872615","https://openalex.org/W4390872833","https://openalex.org/W4390872843","https://openalex.org/W4390873008","https://openalex.org/W4391768407","https://openalex.org/W4393159404","https://openalex.org/W4399993978","https://openalex.org/W4401024032","https://openalex.org/W4401024575","https://openalex.org/W4402704555","https://openalex.org/W4402726924","https://openalex.org/W4402753636","https://openalex.org/W4402916748","https://openalex.org/W4407382240","https://openalex.org/W4409128969","https://openalex.org/W4413145064","https://openalex.org/W4413146307","https://openalex.org/W4413147026","https://openalex.org/W4413157181","https://openalex.org/W4415798002","https://openalex.org/W4415798615","https://openalex.org/W4415800553"],"related_works":[],"abstract_inverted_index":{"Visual":[0,113],"Language":[1,114,141],"Tracking":[2,115],"(VLT)":[3],"enables":[4],"machines":[5],"to":[6,22,91,94],"perform":[7],"tracking":[8,25,29,36,48,97],"in":[9,45,69],"real":[10],"world":[11],"through":[12],"human-like":[13],"language":[14,63,67,190],"descriptions.":[15,64,169],"However,":[16],"existing":[17,70,205,237],"VLT":[18,71,93],"methods":[19,238],"are":[20,247],"limited":[21],"2D":[23,154],"spatial":[24],"or":[26],"single-object":[27],"3D":[28,35,46,96,112,156,227],"and":[30,80,127,144,155,192,196,221,245],"do":[31],"not":[32],"support":[33],"multi-object":[34,47,95,228],"within":[37],"monocular":[38,99,226],"video.":[39,100],"This":[40,181],"limitation":[41],"arises":[42],"because":[43],"advancements":[44],"have":[49],"predominantly":[50],"relied":[51],"on":[52,239],"sensor-based":[53],"data":[54],"(e.g.,":[55],"point":[56],"clouds,":[57],"depth":[58],"sensors)":[59],"that":[60,106,213,233],"lacks":[61],"corresponding":[62],"Moreover,":[65],"natural":[66],"descriptions":[68],"literature":[72],"often":[73],"suffer":[74],"from":[75],"redundancy,":[76],"impeding":[77],"the":[78,88,137,173,240],"efficient":[79],"precise":[81],"localization":[82],"of":[83,139],"multiple":[84],"objects.":[85],"We":[86,101,170],"present":[87],"first":[89,174],"technique":[90],"extend":[92],"using":[98],"introduce":[102],"a":[103,109,119,129,184,188,199,209,215],"comprehensive":[104],"framework":[105],"includes":[107],"(i)":[108],"Monocular":[110],"Multi-object":[111],"(MoMo-3DVLT)":[116],"task,":[117,126],"(ii)":[118],"large-scale":[120],"dataset,":[121,134],"MoMo-3DRoVLT,":[122],"tailored":[123],"for":[124,179,194,202,224],"this":[125],"(iii)":[128],"custom":[130],"neural":[131,175],"model.":[132],"Our":[133,243],"generated":[135],"with":[136,152,159,219],"aid":[138],"Large":[140],"Models":[142],"(LLMs)":[143],"manual":[145],"verification,":[146],"contains":[147],"8,216":[148],"video":[149],"sequences":[150],"annotated":[151],"both":[153],"bounding":[157],"boxes,":[158],"each":[160],"sequence":[161],"accompanied":[162],"by":[163],"three":[164],"freely":[165],"generated,":[166],"human-level":[167],"textual":[168],"propose":[171],"MoMo-3DVLTracker,":[172],"model":[176,182],"specifically":[177],"designed":[178],"MoMo-3DVLT.":[180,203],"integrates":[183,214],"multimodal":[185],"feature":[186],"extractor,":[187],"visual":[189],"encoder-decoder,":[191],"modules":[193],"detection":[195],"tracking,":[197],"setting":[198],"strong":[200],"baseline":[201],"Beyond":[204],"paradigms,":[206],"it":[207],"introduces":[208],"task-specific":[210],"structural":[211],"coupling":[212],"differentiable":[216],"linked-memory":[217],"mechanism":[218],"depth-guided":[220],"language-conditioned":[222],"reasoning":[223],"robust":[225],"tracking.":[229],"Experimental":[230],"results":[231],"demonstrate":[232],"our":[234],"approach":[235],"outperforms":[236],"MoMo-3DRoVLT":[241],"dataset.":[242],"dataset":[244],"code":[246],"available":[248],"at":[249],"https://github.com/hongkai-wei/MoMo-3DVLT.":[250]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-11T00:00:00"}
