{"id":"https://openalex.org/W4415124347","doi":"https://doi.org/10.1109/tpami.2025.3615714","title":"UniSOT: A Unified Framework for Multi-Modality Single Object Tracking","display_name":"UniSOT: A Unified Framework for Multi-Modality Single Object Tracking","publication_year":2025,"publication_date":"2025-10-13","ids":{"openalex":"https://openalex.org/W4415124347","doi":"https://doi.org/10.1109/tpami.2025.3615714","pmid":"https://pubmed.ncbi.nlm.nih.gov/41082418"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3615714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3615714","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.01427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060224928","display_name":"Yinchao Ma","orcid":"https://orcid.org/0009-0003-0506-5217"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinchao Ma","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-0506-5217","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100514151","display_name":"Yuyang Tang","orcid":"https://orcid.org/0000-0001-5292-2873"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Tang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5292-2873","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054606798","display_name":"Wenfei Yang","orcid":"https://orcid.org/0000-0003-3599-7659"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Yang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3599-7659","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1856-9564","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Zhou","orcid":"https://orcid.org/0009-0002-7695-5834"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210130009","display_name":"Shenzhen Institute of Building Research (China)","ror":"https://ror.org/039vzrf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210130009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["Sangfor Research Institute, Shenzhen, China","School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-7695-5834","affiliations":[{"raw_affiliation_string":"Sangfor Research Institute, Shenzhen, China","institution_ids":["https://openalex.org/I4210130009"]},{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103150943","display_name":"Feng Wu","orcid":"https://orcid.org/0000-0001-7266-5579"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wu","raw_affiliation_strings":["School of Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7266-5579","affiliations":[{"raw_affiliation_string":"School of Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14307422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"2","first_page":"1554","last_page":"1572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.8510000109672546,"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"}},"topics":[{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.8510000109672546,"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"}},{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.8271999955177307,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.7583000063896179,"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/modalities","display_name":"Modalities","score":0.9060999751091003},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.7233999967575073},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.6128000020980835},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5673999786376953},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5198000073432922},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5116000175476074},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.49570000171661377}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.9060999751091003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516999840736389},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.7233999967575073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7067000269889832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6780999898910522},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.6128000020980835},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5673999786376953},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.3199000060558319},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C150189527","wikidata":"https://www.wikidata.org/wiki/Q356674","display_name":"Reference model","level":2,"score":0.27309998869895935}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2025.3615714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3615714","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41082418","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41082418","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 pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:2511.01427","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01427","pdf_url":"https://arxiv.org/pdf/2511.01427","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.01427","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01427","pdf_url":"https://arxiv.org/pdf/2511.01427","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":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/G1691810814","display_name":null,"funder_award_id":"62306294","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308808780","display_name":null,"funder_award_id":"62021001","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415124347.pdf","grobid_xml":"https://content.openalex.org/works/W4415124347.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Single":[0],"object":[1,7],"tracking":[2,48,100,143,146],"aims":[3],"to":[4,46,68,82],"localize":[5],"target":[6],"with":[8,60,101,132],"specific":[9,22],"reference":[10,31,64,104,126,171],"modalities":[11,24,32,40,59,105,109,127,131,172],"(bounding":[12],"box,":[13],"natural":[14],"language":[15],"or":[16,28,56,62],"both)":[17],"in":[18,43,112],"a":[19,77,117],"sequence":[20],"of":[21,89,124],"video":[23,39,58,108,130,185],"(RGB,":[25],"RGB+Depth,":[26],"RGB+Thermal":[27],"RGB+Event.).":[29],"Different":[30],"enable":[33],"various":[34,84],"human-machine":[35],"interactions,":[36],"and":[37,72,128,144,173],"different":[38,122],"are":[41,52],"demanded":[42],"complex":[44],"scenarios":[45],"enhance":[47],"robustness.":[49],"Existing":[50],"trackers":[51],"designed":[53],"for":[54,121],"single":[55,61],"several":[57,63],"modalities,":[65],"which":[66],"leads":[67],"separate":[69],"model":[70],"designs":[71],"limits":[73],"practical":[74],"applications.":[75],"Practically,":[76],"unified":[78,118],"tracker":[79,96],"is":[80,93],"needed":[81],"handle":[83],"requirements.":[85],"To":[86],"the":[87],"best":[88],"our":[90],"knowledge,":[91],"there":[92],"still":[94],"no":[95],"that":[97,149],"can":[98],"perform":[99],"these":[102,107],"above":[103],"across":[106,168,181],"simultaneously.":[110],"Thus,":[111],"this":[113],"paper,":[114],"we":[115],"present":[116],"tracker,":[119],"UniSOT,":[120],"combinations":[123],"three":[125,170,183],"four":[129],"uniform":[133],"parameters.":[134],"Extensive":[135],"experimental":[136],"results":[137],"on":[138,166],"18":[139],"visual":[140],"tracking,":[141],"vision-language":[142],"RGB+X":[145,184],"benchmarks":[147],"demonstrate":[148],"UniSOT":[150,158],"shows":[151],"superior":[152],"performance":[153],"against":[154],"modality-specific":[155],"counterparts.":[156],"Notably,":[157],"outperforms":[159,174],"previous":[160],"counterparts":[161],"by":[162,176],"over":[163,177],"3.0%":[164],"AUC":[165],"TNL2K":[167],"all":[169,182],"Un-Track":[175],"2.0%":[178],"main":[179],"metric":[180],"modalities.":[186]},"counts_by_year":[],"updated_date":"2026-01-11T23:08:45.486102","created_date":"2025-10-14T00:00:00"}