{"id":"https://openalex.org/W4405022411","doi":"https://doi.org/10.1109/tcsvt.2024.3510735","title":"Multi-Modal Understanding and Generation for Object Tracking","display_name":"Multi-Modal Understanding and Generation for Object Tracking","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4405022411","doi":"https://doi.org/10.1109/tcsvt.2024.3510735"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3510735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3510735","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","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":"https://openalex.org/A5002250162","display_name":"Hong Zhu","orcid":"https://orcid.org/0000-0002-2841-7129"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhu","raw_affiliation_strings":["College of Electronic Engineering, National University of Defense Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2841-7129","affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, National University of Defense Technology, Hefei, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451855","display_name":"Pingping Zhang","orcid":"https://orcid.org/0000-0003-1206-1444"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingping Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1206-1444","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115444850","display_name":"Lei Xue","orcid":"https://orcid.org/0009-0002-7355-9668"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xue","raw_affiliation_strings":["College of Electronic Engineering, National University of Defense Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-7355-9668","affiliations":[{"raw_affiliation_string":"College of Electronic Engineering, National University of Defense Technology, Hefei, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102718971","display_name":"Guanglin Yuan","orcid":"https://orcid.org/0009-0008-7591-943X"},"institutions":[{"id":"https://openalex.org/I4210115169","display_name":"Second Artillery General Hospital of Chinese People's Liberation Army","ror":"https://ror.org/0264qnp36","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210115169"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglin Yuan","raw_affiliation_strings":["Army Artillery and Air Defense Academy of PLA, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-7591-943X","affiliations":[{"raw_affiliation_string":"Army Artillery and Air Defense Academy of PLA, Hefei, China","institution_ids":["https://openalex.org/I4210115169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2815,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53526741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"35","issue":"5","first_page":"4384","last_page":"4396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9226999878883362,"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":0.9226999878883362,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9103999733924866,"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/computer-science","display_name":"Computer science","score":0.6085224747657776},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5805197358131409},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5641613006591797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5309861302375793},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44981271028518677},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4320472478866577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6085224747657776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5805197358131409},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5641613006591797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5309861302375793},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44981271028518677},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4320472478866577},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3510735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3510735","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5478071163","display_name":null,"funder_award_id":"PFXY220114001","funder_id":"https://openalex.org/F4320313655","funder_display_name":"Foundation for Research, Science and Technology"},{"id":"https://openalex.org/G5886194139","display_name":null,"funder_award_id":"2308085MF211","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320313655","display_name":"Foundation for Research, Science and Technology","ror":null},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2489434015","https://openalex.org/W2616247523","https://openalex.org/W2747053578","https://openalex.org/W2769941643","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2962766617","https://openalex.org/W2963109634","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3010072143","https://openalex.org/W3012573144","https://openalex.org/W3106542916","https://openalex.org/W3107787446","https://openalex.org/W3159619744","https://openalex.org/W3167536469","https://openalex.org/W3173871266","https://openalex.org/W3181069167","https://openalex.org/W3214586131","https://openalex.org/W4214759957","https://openalex.org/W4285259499","https://openalex.org/W4289535600","https://openalex.org/W4292828074","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4312956471","https://openalex.org/W4322576880","https://openalex.org/W4375869376","https://openalex.org/W4385569741","https://openalex.org/W4386065544","https://openalex.org/W4386075643","https://openalex.org/W4390871890","https://openalex.org/W4390889789","https://openalex.org/W4392908016","https://openalex.org/W4393148669","https://openalex.org/W6756015008","https://openalex.org/W6759579507","https://openalex.org/W6786822275","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6792387559","https://openalex.org/W6795704626","https://openalex.org/W6798805250","https://openalex.org/W6802517928","https://openalex.org/W6811013733"],"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":{"Vision-Language":[0],"Tracking":[1],"(VLT)":[2],"aims":[3],"to":[4,103,177,188,211,232],"predict":[5],"the":[6,19,27,32,37,44,51,56,60,65,71,94,105,132,136,144,148,169,174,179,185,195,199,208,213,228,233],"target":[7,38,154,180,203],"state":[8],"in":[9,55,64,80,198,207],"video":[10],"sequences":[11],"using":[12],"two":[13,112],"types":[14],"of":[15,26,74,107,135,215],"heterogeneous":[16],"information:":[17],"1)":[18],"static":[20],"text":[21,57,128,145],"description":[22,58],"detailing":[23],"main":[24],"characteristics":[25],"tracked":[28],"object,":[29],"and":[30,39,59,76,97,119,141,160,166,205,227],"2)":[31],"dynamic":[33,127],"image":[34],"patches":[35],"containing":[36],"its":[40,236],"surroundings.":[41],"However,":[42],"as":[43,147],"tracking":[45],"proceeds,":[46],"inconsistencies":[47],"may":[48],"arise":[49],"between":[50],"linguistic":[52,161,209],"information":[53],"embedded":[54],"visual":[61,159,200],"representations":[62,162],"stored":[63],"search":[66],"images.":[67],"In":[68],"such":[69],"cases,":[70],"direct":[72],"fusion":[73],"vision":[75],"language":[77],"could":[78],"result":[79],"conflicts.":[81],"To":[82,182],"tackle":[83],"this":[84],"issue,":[85],"we":[86,110,193],"propose":[87],"MugTracker,":[88],"which":[89],"integrates":[90],"image-to-text":[91],"generation":[92,121],"into":[93],"VLT":[95],"framework":[96],"attempts":[98],"a":[99,126,190],"generative":[100],"updating":[101],"way":[102],"mitigate":[104],"effects":[106],"inconsistencies.":[108],"Specifically,":[109],"design":[111],"branch":[113,171],"tasks:":[114],"multi-modal":[115,120],"understanding":[116],"for":[117,122,151,202],"reasoning":[118,170],"updating.":[123],"We":[124],"develop":[125],"generator":[129],"based":[130],"on":[131,173,224],"hybrid":[133],"architecture":[134],"pre-trained":[137],"foundation":[138,186],"model":[139,187],"BLIP":[140,175],"adaptively":[142],"update":[143],"reference":[146],"context":[149],"varies":[150],"more":[152],"accurate":[153],"modeling.":[155],"The":[156],"semantically":[157],"consistent":[158],"are":[163],"then":[164],"aligned":[165],"associated":[167],"by":[168],"built":[172],"dual-encoder":[176],"infer":[178],"state.":[181],"better":[183],"transfer":[184],"build":[189],"strong":[191],"tracker,":[192],"introduce":[194],"proposed":[196],"TE-Adapter":[197],"components":[201,210],"enhancement":[204],"Text-Adapter":[206],"strengthen":[212],"learning":[214],"discriminative":[216],"semantics.":[217],"Our":[218],"MugTracker":[219],"has":[220],"been":[221],"extensively":[222],"evaluated":[223],"three":[225],"datasets,":[226],"superior":[229],"performance":[230],"compared":[231],"state-of-the-arts":[234],"demonstrates":[235],"effectiveness.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}