{"id":"https://openalex.org/W4394713372","doi":"https://doi.org/10.1109/ricai60863.2023.10489325","title":"Multi-Modal Object Tracking with Vision-Language Adaptive Fusion and Alignment","display_name":"Multi-Modal Object Tracking with Vision-Language Adaptive Fusion and Alignment","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4394713372","doi":"https://doi.org/10.1109/ricai60863.2023.10489325"},"language":"en","primary_location":{"id":"doi:10.1109/ricai60863.2023.10489325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ricai60863.2023.10489325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)","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":"Jixiang Zuo","orcid":null},"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":"Jixiang Zuo","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China","College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576187","display_name":"Tao Wu","orcid":"https://orcid.org/0000-0001-5245-3800"},"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":"Tao Wu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China","College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102211751","display_name":"Meiping Shi","orcid":null},"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":"Meiping Shi","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China","College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665614","display_name":"Xueyan Liu","orcid":"https://orcid.org/0000-0001-8918-0148"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyan Liu","raw_affiliation_strings":["China North Artificial Intelligence &#x0026; Innovation Research Institute,Collective Intelligence &#x0026;Collaboration Laboratory,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China North Artificial Intelligence &#x0026; Innovation Research Institute,Collective Intelligence &#x0026;Collaboration Laboratory,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002980949","display_name":"Xijun Zhao","orcid":"https://orcid.org/0000-0003-2090-3648"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xijun Zhao","raw_affiliation_strings":["China North Artificial Intelligence &#x0026; Innovation Research Institute,Collective Intelligence &#x0026;Collaboration Laboratory,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China North Artificial Intelligence &#x0026; Innovation Research Institute,Collective Intelligence &#x0026;Collaboration Laboratory,Beijing,China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1125","last_page":"1133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9778000116348267,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9778000116348267,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9740999937057495,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9244999885559082,"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-vision","display_name":"Computer vision","score":0.7257363200187683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.695196807384491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6434876918792725},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5778641104698181},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5734423398971558},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5349515676498413},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48199525475502014},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.47376492619514465},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4397713243961334},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1296064555644989},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06321662664413452}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7257363200187683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695196807384491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434876918792725},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5778641104698181},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5734423398971558},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5349515676498413},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48199525475502014},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.47376492619514465},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4397713243961334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1296064555644989},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06321662664413452},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/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/ricai60863.2023.10489325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ricai60863.2023.10489325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5975291901","display_name":null,"funder_award_id":"62103431","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W2747053578","https://openalex.org/W2794744029","https://openalex.org/W2890678738","https://openalex.org/W2898200825","https://openalex.org/W2963534981","https://openalex.org/W2966759264","https://openalex.org/W2989604896","https://openalex.org/W3001584168","https://openalex.org/W3010072143","https://openalex.org/W3035453691","https://openalex.org/W3035672751","https://openalex.org/W3106542916","https://openalex.org/W3159619744","https://openalex.org/W3167536469","https://openalex.org/W3181069167","https://openalex.org/W3205239873","https://openalex.org/W3214586131","https://openalex.org/W4214759957","https://openalex.org/W4226077544","https://openalex.org/W4283825622","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4321766229","https://openalex.org/W4385569741","https://openalex.org/W4386075643","https://openalex.org/W6631190155","https://openalex.org/W6791353385","https://openalex.org/W6805147364","https://openalex.org/W6839144149"],"related_works":["https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2353265673","https://openalex.org/W4285271403","https://openalex.org/W2542007731","https://openalex.org/W2031175860","https://openalex.org/W2968379562","https://openalex.org/W3156013036","https://openalex.org/W2152662039"],"abstract_inverted_index":{"The":[0],"current":[1],"CLIP-based":[2],"multi-modal":[3,20,56],"deep":[4],"learning":[5],"has":[6,14],"been":[7],"widely":[8],"used":[9],"for":[10,44],"various":[11],"tasks":[12],"and":[13,25,29,48,52,63,73,77,83,119,134,146,151],"achieved":[15,143],"leading":[16],"results.":[17],"Traditional":[18],"vision-language":[19,121],"tracking":[21],"paradigms":[22],"extract":[23,118],"vision":[24,51,69],"language":[26],"features":[27,122],"separately":[28],"then":[30],"fuse":[31,120],"them,":[32],"which":[33],"is":[34],"difficult":[35],"to":[36,89,161],"train":[37],"end-to-end.":[38],"This":[39],"paper":[40,155],"proposed":[41],"a":[42,68,103],"framework":[43],"synchronous":[45],"feature":[46,105],"extraction":[47],"fusion":[49],"of":[50,86,93,158,165],"language.":[53],"Specifically,":[54],"adaptive":[55],"attention":[57],"operations":[58],"are":[59,126],"performed":[60],"on":[61,128,149],"language-template":[62],"language-search":[64],"region":[65],"respectively.":[66],"Then":[67],"module":[70],"performs":[71],"self-attention":[72],"cross-attention":[74],"between":[75],"template":[76],"search":[78,98],"region,":[79],"integrating":[80],"the":[81,87,91,94,97,108,163],"long":[82],"short-term":[84],"clues":[85],"target":[88,95],"model":[90,101],"position":[92],"in":[96],"region.":[99],"Finally,":[100,153],"learns":[102],"unified":[104],"representation":[106],"through":[107],"modality":[109],"alignment":[110],"module.":[111],"By":[112],"contrastive":[113],"learning,":[114],"this":[115,141,154,166],"method":[116,142],"can":[117],"efficiently.":[123],"Extensive":[124],"experiments":[125,160],"conducted":[127,156],"three":[129],"benchmark":[130],"tests,":[131],"TNL2K,":[132],"OTB99-Lang":[133],"LaSOT.":[135],"Compared":[136],"with":[137],"other":[138],"state-of-the-art":[139,148],"methods,":[140],"promising":[144],"results":[145],"outperformed":[147],"TNL2K":[150],"OTB99-Lang.":[152],"plenty":[157],"ablation":[159],"demonstrate":[162],"effectiveness":[164],"method.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
