{"id":"https://openalex.org/W6947921150","doi":"https://doi.org/10.48550/arxiv.2505.18111","title":"Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking","display_name":"Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking","publication_year":2025,"publication_date":"2025-05-23","ids":{"openalex":"https://openalex.org/W6947921150","doi":"https://doi.org/10.48550/arxiv.2505.18111"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2505.18111","doi":"https://doi.org/10.48550/arxiv.2505.18111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.18111","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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2505.18111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang, Cheng-Yen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Cheng-Yen","raw_affiliation_strings":["University of Washington , Seattle WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington , Seattle WA , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huang, Hsiang-Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Hsiang-Wei","raw_affiliation_strings":["University of Washington , Seattle WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington , Seattle WA , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155842022","display_name":"Pyongkun Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Pyong-Kun","raw_affiliation_strings":["Electronics and Telecommunications Research Institute , Daejeon , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute , Daejeon , South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kuo, Chien-Kai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuo, Chien-Kai","raw_affiliation_strings":["University of Washington , Seattle WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington , Seattle WA , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chang, Jui-Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang, Jui-Wei","raw_affiliation_strings":["University of Washington , Seattle WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington , Seattle WA , USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kim, Kwang-Ju","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Kwang-Ju","raw_affiliation_strings":["Electronics and Telecommunications Research Institute , Daejeon , South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute , Daejeon , South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huang, Chung-I","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107525","display_name":"National Center for High-Performance Computing","ror":"https://ror.org/01jpzd518","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210107525","https://openalex.org/I4210128167","https://openalex.org/I4210166867"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huang, Chung-I","raw_affiliation_strings":["National Center for High-performance Computing , Hsinchu , Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for High-performance Computing , Hsinchu , Taiwan","institution_ids":["https://openalex.org/I4210107525"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hwang, Jenq-Neng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hwang, Jenq-Neng","raw_affiliation_strings":["University of Washington , Seattle WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington , Seattle WA , USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9907000064849854,"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":0.9907000064849854,"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":0.004600000102072954,"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":0.0019000000320374966,"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/segment-anything-model-2","display_name":"Segment Anything Model 2","score":0.9679999947547913},{"id":"https://openalex.org/keywords/visual-tracking","display_name":"visual object tracking","score":0.953000009059906}],"concepts":[{"id":"https://openalex.org/C144251240","wikidata":"https://www.wikidata.org/wiki/Q7068229","display_name":"Nucleofection","level":4,"score":0.44510000944137573},{"id":"https://openalex.org/C2992336715","wikidata":"https://www.wikidata.org/wiki/Q63431143","display_name":"Gestational period","level":4,"score":0.3601999878883362},{"id":"https://openalex.org/C2778283623","wikidata":"https://www.wikidata.org/wiki/Q18032200","display_name":"TSG101","level":5,"score":0.3395000100135803},{"id":"https://openalex.org/C18743360","wikidata":"https://www.wikidata.org/wiki/Q1208096","display_name":"Diafiltration","level":4,"score":0.3345000147819519},{"id":"https://openalex.org/C2777054765","wikidata":"https://www.wikidata.org/wiki/Q6402731","display_name":"Dysgeusia","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C145741570","wikidata":"https://www.wikidata.org/wiki/Q7251534","display_name":"Proteogenomics","level":5,"score":0.30630001425743103},{"id":"https://openalex.org/C133074676","wikidata":"https://www.wikidata.org/wiki/Q428729","display_name":"Fusible alloy","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C180938184","wikidata":"https://www.wikidata.org/wiki/Q2142270","display_name":"Liquation","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C2777935831","wikidata":"https://www.wikidata.org/wiki/Q3144949","display_name":"Hemopericardium","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C2777968768","wikidata":"https://www.wikidata.org/wiki/Q1280161","display_name":"Emperipolesis","level":4,"score":0.29260000586509705},{"id":"https://openalex.org/C2777742743","wikidata":"https://www.wikidata.org/wiki/Q19904005","display_name":"Durvalumab","level":5,"score":0.2924000024795532},{"id":"https://openalex.org/C2777158700","wikidata":"https://www.wikidata.org/wiki/Q1419356","display_name":"Hyporeflexia","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C2776781215","wikidata":"https://www.wikidata.org/wiki/Q83253","display_name":"Triacetin","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2781032047","wikidata":"https://www.wikidata.org/wiki/Q938793","display_name":"Articular cartilage damage","level":5,"score":0.2827000021934509},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C135979968","wikidata":"https://www.wikidata.org/wiki/Q609809","display_name":"Protein isoform","level":5,"score":0.2775000035762787},{"id":"https://openalex.org/C104545631","wikidata":"https://www.wikidata.org/wiki/Q464858","display_name":"Demotion","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C2776356786","wikidata":"https://www.wikidata.org/wiki/Q1048573","display_name":"Tubulopathy","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C2778843634","wikidata":"https://www.wikidata.org/wiki/Q2013780","display_name":"Ocrelizumab","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C2909186138","wikidata":"https://www.wikidata.org/wiki/Q1500373","display_name":"Hyperlactatemia","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2775917601","wikidata":"https://www.wikidata.org/wiki/Q1424050","display_name":"Sclerodactyly","level":4,"score":0.2565000057220459},{"id":"https://openalex.org/C2779645999","wikidata":"https://www.wikidata.org/wiki/Q1858477","display_name":"Frugality","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2505.18111","doi":"https://doi.org/10.48550/arxiv.2505.18111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.18111","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2505.18111","doi":"https://doi.org/10.48550/arxiv.2505.18111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.18111","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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"effective":[3],"approach":[4],"for":[5],"adapting":[6],"the":[7,14,23,58,66,76,90,97,101],"Segment":[8],"Anything":[9],"Model":[10],"2":[11],"(SAM2)":[12],"to":[13,34,80],"Visual":[15],"Object":[16,62],"Tracking":[17,63],"(VOT)":[18],"task.":[19],"Our":[20],"method":[21],"leverages":[22],"powerful":[24],"pre-trained":[25],"capabilities":[26],"of":[27,55,68,86,92,100],"SAM2":[28,43],"and":[29,82],"incorporates":[30],"several":[31],"key":[32],"techniques":[33],"enhance":[35],"its":[36],"performance":[37],"in":[38,89],"VOT":[39,93],"applications.":[40],"By":[41],"combining":[42],"with":[44,96],"our":[45,69,74,87],"proposed":[46],"optimizations,":[47],"we":[48],"achieved":[49],"a":[50,83],"first":[51],"place":[52],"AUC":[53],"score":[54],"89.4":[56],"on":[57],"2024":[59],"ICPR":[60],"Multi-modal":[61],"challenge,":[64],"demonstrating":[65],"effectiveness":[67],"approach.":[70],"This":[71],"paper":[72],"details":[73],"methodology,":[75],"specific":[77],"enhancements":[78],"made":[79],"SAM2,":[81],"comprehensive":[84],"analysis":[85],"results":[88],"context":[91],"solutions":[94],"along":[95],"multi-modality":[98],"aspect":[99],"dataset.":[102]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}
