{"id":"https://openalex.org/W4393159404","doi":"https://doi.org/10.1609/aaai.v38i5.28205","title":"Unifying Visual and Vision-Language Tracking via Contrastive Learning","display_name":"Unifying Visual and Vision-Language Tracking via Contrastive Learning","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393159404","doi":"https://doi.org/10.1609/aaai.v38i5.28205"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i5.28205","doi":"https://doi.org/10.1609/aaai.v38i5.28205","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28205","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28205/28406","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28205/28406","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","observed_orcids":["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"]},{"id":"https://openalex.org/I4405283751","display_name":"Deep Space Exploration Laboratory","ror":"https://ror.org/026z4ds93","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405283751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinchao Ma","raw_affiliation_strings":["Deep Space Exploration Laboratory/School of Information Science and Technology, University of Science and Technology\nof China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Space Exploration Laboratory/School of Information Science and Technology, University of Science and Technology\nof China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4405283751"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100514151","display_name":"Yuyang Tang","orcid":"https://orcid.org/0000-0001-5292-2873","observed_orcids":["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"]},{"id":"https://openalex.org/I4405283751","display_name":"Deep Space Exploration Laboratory","ror":"https://ror.org/026z4ds93","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405283751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Tang","raw_affiliation_strings":["Deep Space Exploration Laboratory/School of Information Science and Technology, University of Science and Technology\nof China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Space Exploration Laboratory/School of Information Science and Technology, University of Science and Technology\nof China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4405283751"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054606798","display_name":"Wenfei Yang","orcid":"https://orcid.org/0000-0003-3599-7659","observed_orcids":["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"]},{"id":"https://openalex.org/I4405283751","display_name":"Deep Space Exploration Laboratory","ror":"https://ror.org/026z4ds93","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405283751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Yang","raw_affiliation_strings":["Deep Space Exploration Laboratory/School of Information Science and Technology, University of Science and Technology\nof China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Space Exploration Laboratory/School of Information Science and Technology, University of Science and Technology\nof China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4405283751"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648981","display_name":"Tianzhu Zhang","orcid":"https://orcid.org/0000-0003-1856-9564","observed_orcids":["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"]},{"id":"https://openalex.org/I4405283751","display_name":"Deep Space Exploration Laboratory","ror":"https://ror.org/026z4ds93","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405283751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhu Zhang","raw_affiliation_strings":["Deep Space Exploration Laboratory/School of Information Science and Technology, University of Science and Technology\nof China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deep Space Exploration Laboratory/School of Information Science and Technology, University of Science and Technology\nof China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I4405283751"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685013","display_name":"Jinpeng Zhang","orcid":"https://orcid.org/0000-0001-6499-0128","observed_orcids":["https://orcid.org/0000-0001-6499-0128","https://orcid.org/0000-0003-1426-099X"]},"institutions":[{"id":"https://openalex.org/I15089104","display_name":"China Aerospace Science and Industry Corporation (China)","ror":"https://ror.org/0523vvf33","country_code":"CN","type":"company","lineage":["https://openalex.org/I15089104"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinpeng Zhang","raw_affiliation_strings":["Intelligent Science Technology Academy of CASIC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Science Technology Academy of CASIC","institution_ids":["https://openalex.org/I15089104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006395407","display_name":"Mengxue Kang","orcid":"https://orcid.org/0000-0002-3847-1997","observed_orcids":["https://orcid.org/0000-0002-3847-1997"]},"institutions":[{"id":"https://openalex.org/I15089104","display_name":"China Aerospace Science and Industry Corporation (China)","ror":"https://ror.org/0523vvf33","country_code":"CN","type":"company","lineage":["https://openalex.org/I15089104"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxue Kang","raw_affiliation_strings":["Intelligent Science Technology Academy of CASIC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Science Technology Academy of CASIC","institution_ids":["https://openalex.org/I15089104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.7064,"has_fulltext":true,"cited_by_count":81,"citation_normalized_percentile":{"value":0.98883426,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"38","issue":"5","first_page":"4107","last_page":"4116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9926999807357788,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9926999807357788,"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":0.0017999999690800905,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0013000000035390258,"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/single-object-tracking","display_name":"single object tracking","score":0.8659999966621399},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.8090000152587891},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.8050000071525574}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5688586235046387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5585370063781738},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4794820249080658},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4424504041671753},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.41073527932167053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41030973196029663},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34227222204208374},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33846116065979004},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.33668431639671326},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08816176652908325}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v38i5.28205","doi":"https://doi.org/10.1609/aaai.v38i5.28205","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28205","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28205/28406","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2401.11228","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.11228","pdf_url":"https://arxiv.org/pdf/2401.11228","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"pmh:oai:ojs.aaai.org:article/28205","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/28205","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2401.11228","doi":"https://doi.org/10.48550/arxiv.2401.11228","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.11228","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i5.28205","doi":"https://doi.org/10.1609/aaai.v38i5.28205","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v38i5.28205","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/28205/28406","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"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/G3828173677","display_name":null,"funder_award_id":"62121002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4287865964","display_name":"\u5168\u5929\u5019\u884c\u4eba\u91cd\u8bc6\u522b\u6280\u672f\u7814\u7a76","funder_award_id":"62071122","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5295720946","display_name":null,"funder_award_id":"2018166","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393159404.pdf","grobid_xml":"https://content.openalex.org/works/W4393159404.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1861492603","https://openalex.org/W2470394683","https://openalex.org/W2489434015","https://openalex.org/W2518876086","https://openalex.org/W2605173812","https://openalex.org/W2626778328","https://openalex.org/W2747053578","https://openalex.org/W2794744029","https://openalex.org/W2891033863","https://openalex.org/W2896457183","https://openalex.org/W2898200825","https://openalex.org/W2901751835","https://openalex.org/W2936520980","https://openalex.org/W2963109634","https://openalex.org/W2963534981","https://openalex.org/W2984121207","https://openalex.org/W2998434318","https://openalex.org/W3013266062","https://openalex.org/W3035511673","https://openalex.org/W3090155371","https://openalex.org/W3106542916","https://openalex.org/W3108519869","https://openalex.org/W3110435696","https://openalex.org/W3142630836","https://openalex.org/W3144314306","https://openalex.org/W3150017950","https://openalex.org/W3156978626","https://openalex.org/W3167536469","https://openalex.org/W3173364567","https://openalex.org/W3173871266","https://openalex.org/W3174004334","https://openalex.org/W3174225630","https://openalex.org/W3181069167","https://openalex.org/W3204076343","https://openalex.org/W4226002507","https://openalex.org/W4286251267","https://openalex.org/W4287248588","https://openalex.org/W4292102100","https://openalex.org/W4292828074","https://openalex.org/W4309181071","https://openalex.org/W4312323989","https://openalex.org/W4312532041","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4313145013","https://openalex.org/W4376851307","https://openalex.org/W4386075643","https://openalex.org/W7133228328"],"related_works":["https://openalex.org/W4387969322","https://openalex.org/W7140657560","https://openalex.org/W7125641080","https://openalex.org/W4415708227","https://openalex.org/W4399344486","https://openalex.org/W4408930345","https://openalex.org/W4409378793","https://openalex.org/W4416380338","https://openalex.org/W4417130732","https://openalex.org/W4415124347"],"abstract_inverted_index":{"Single":[0],"object":[1,8],"tracking":[2,172,176],"aims":[3],"to":[4,14,35,109,136],"locate":[5],"the":[6,15,23,36,57,80,111,133,147],"target":[7,134,148],"in":[9,149,156],"a":[10,63,92,105,117,122,150],"video":[11,143],"sequence":[12],"according":[13],"state":[16],"specified":[17],"by":[18],"different":[19,39,157],"modal":[20],"references,":[21],"including":[22],"initial":[24],"bounding":[25],"box":[26,124],"(BBOX),":[27],"natural":[28],"language":[29,100,114],"(NL),":[30],"or":[31,48],"both":[32],"(NL+BBOX).":[33],"Due":[34],"gap":[37],"between":[38],"modalities,":[40],"most":[41],"existing":[42],"trackers":[43],"are":[44],"designed":[45],"for":[46,96],"single":[47],"partial":[49],"of":[50,132],"these":[51],"reference":[52,74,135,158],"settings":[53,75],"and":[54,99,103,113,145,178,184],"overspecialize":[55],"on":[56,169],"specific":[58],"modality.":[59],"Differently,":[60],"we":[61,90],"present":[62],"unified":[64,118],"tracker":[65],"called":[66],"UVLTrack,":[67],"which":[68,128],"can":[69],"simultaneously":[70],"handle":[71],"all":[72],"three":[73,174,179],"(BBOX,":[76],"NL,":[77],"NL+BBOX)":[78],"with":[79],"same":[81],"parameters.":[82],"The":[83],"proposed":[84],"UVLTrack":[85,165],"enjoys":[86],"several":[87],"merits.":[88],"First,":[89],"design":[91],"modality-unified":[93],"feature":[94,101],"extractor":[95],"joint":[97],"visual":[98,112,171,180],"learning":[102],"propose":[104],"multi-modal":[106],"contrastive":[107,151],"loss":[108],"align":[110],"features":[115,140],"into":[116],"semantic":[119],"space.":[120],"Second,":[121],"modality-adaptive":[123],"head":[125],"is":[126],"proposed,":[127],"makes":[129],"full":[130],"use":[131],"mine":[137],"ever-changing":[138],"scenario":[139],"dynamically":[141],"from":[142],"contexts":[144],"distinguish":[146],"way,":[152],"enabling":[153],"robust":[154],"performance":[155,168],"settings.":[159],"Extensive":[160],"experimental":[161],"results":[162],"demonstrate":[163],"that":[164],"achieves":[166],"promising":[167],"seven":[170],"datasets,":[173,177],"vision-language":[175],"grounding":[181],"datasets.":[182],"Codes":[183],"models":[185],"will":[186],"be":[187],"open-sourced":[188],"at":[189],"https://github.com/OpenSpaceAI/UVLTrack.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":11}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2024-03-26T00:00:00"}