{"id":"https://openalex.org/W4404573408","doi":"https://doi.org/10.48550/arxiv.2411.11922","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","display_name":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","publication_year":2024,"publication_date":"2024-11-18","ids":{"openalex":"https://openalex.org/W4404573408","doi":"https://doi.org/10.48550/arxiv.2411.11922"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.11922","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.11922","pdf_url":"https://arxiv.org/pdf/2411.11922","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.11922","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047672937","display_name":"Cheng-Yen Yang","orcid":"https://orcid.org/0009-0004-2631-6756","observed_orcids":["https://orcid.org/0009-0004-2631-6756"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Cheng-Yen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101699930","display_name":"Hsiang-Wei Huang","orcid":"https://orcid.org/0000-0003-0373-9487","observed_orcids":["https://orcid.org/0000-0003-0373-9487"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Hsiang-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103021774","display_name":"Wenhao Chai","orcid":"https://orcid.org/0000-0003-2611-0008","observed_orcids":["https://orcid.org/0000-0003-2611-0008"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chai, Wenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618974","display_name":"Zhongyu Jiang","orcid":"https://orcid.org/0000-0003-4462-6497","observed_orcids":["https://orcid.org/0000-0003-4462-6497"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Zhongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101702810","display_name":"Jenq\u2013Neng Hwang","orcid":"https://orcid.org/0000-0002-8877-2421","observed_orcids":["https://orcid.org/0000-0002-8877-2421"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Jenq-Neng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"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":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0010000000474974513,"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":0.0007999999797903001,"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":0.9459999799728394},{"id":"https://openalex.org/keywords/mask-refinement","display_name":"mask refinement","score":0.3610000014305115},{"id":"https://openalex.org/keywords/crowded-scenes","display_name":"crowded scenes","score":0.6420000195503235},{"id":"https://openalex.org/keywords/self-occlusion","display_name":"self-occlusion","score":0.9190000295639038},{"id":"https://openalex.org/keywords/error-propagation","display_name":"error propagation","score":0.6880000233650208},{"id":"https://openalex.org/keywords/real-time-tracking","display_name":"real-time tracking","score":0.7429999709129333}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6760818958282471},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6378588080406189},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.614388108253479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5955901741981506},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5698024034500122},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5475260019302368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5199771523475647},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3906973898410797},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26332956552505493},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08018708229064941},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic 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},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.11922","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.11922","pdf_url":"https://arxiv.org/pdf/2411.11922","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":"doi:10.48550/arxiv.2411.11922","doi":"https://doi.org/10.48550/arxiv.2411.11922","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.11922","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":"pmh:oai:arXiv.org:2411.11922","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.11922","pdf_url":"https://arxiv.org/pdf/2411.11922","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7123905231","https://openalex.org/W7155065802","https://openalex.org/W7160253894","https://openalex.org/W7162114871","https://openalex.org/W6948201892","https://openalex.org/W7122474438","https://openalex.org/W4412024265","https://openalex.org/W4408953854","https://openalex.org/W7076962296","https://openalex.org/W4409262191"],"abstract_inverted_index":{"The":[0],"Segment":[1],"Anything":[2],"Model":[3],"2":[4,73],"(SAM":[5],"2)":[6],"has":[7],"demonstrated":[8],"strong":[9,118],"performance":[10,120],"in":[11,18,37,62,114,138,175,185],"object":[12,20,78,95],"segmentation":[13],"tasks":[14],"but":[15],"faces":[16],"challenges":[17],"visual":[19,77],"tracking,":[21],"particularly":[22],"when":[23],"managing":[24],"crowded":[25],"scenes":[26],"with":[27,85,146],"fast-moving":[28],"or":[29,110],"self-occluding":[30],"objects.":[31],"Furthermore,":[32],"the":[33,38,44,51,55,86,106],"fixed-window":[34],"memory":[35,89],"approach":[36],"original":[39],"model":[40],"does":[41],"not":[42],"consider":[43],"quality":[45],"of":[46,71],"memories":[47],"selected":[48],"to":[49,59,128,166],"condition":[50],"image":[52],"features":[53],"for":[54,76,108,182],"next":[56],"frame,":[57],"leading":[58],"error":[60],"propagation":[61],"videos.":[63],"This":[64],"paper":[65],"introduces":[66],"SAMURAI,":[67],"an":[68],"enhanced":[69],"adaptation":[70],"SAM":[72],"specifically":[74],"designed":[75],"tracking.":[79],"By":[80],"incorporating":[81],"temporal":[82],"motion":[83,96],"cues":[84],"proposed":[87],"motion-aware":[88],"selection":[90],"mechanism,":[91],"SAMURAI":[92,112,134],"effectively":[93],"predicts":[94],"and":[97,116,141,153,179],"refines":[98],"mask":[99],"selection,":[100],"achieving":[101],"robust,":[102],"accurate":[103],"tracking":[104,177],"without":[105,130],"need":[107],"retraining":[109],"fine-tuning.":[111,131],"operates":[113],"real-time":[115],"demonstrates":[117],"zero-shot":[119],"across":[121],"diverse":[122],"benchmark":[123],"datasets,":[124],"showcasing":[125],"its":[126,173,180],"ability":[127],"generalize":[129],"In":[132],"evaluations,":[133],"achieves":[135,162],"significant":[136],"improvements":[137],"success":[139],"rate":[140],"precision":[142],"over":[143],"existing":[144],"trackers,":[145],"a":[147,154],"7.1%":[148],"AUC":[149],"gain":[150,157],"on":[151,158,170],"LaSOT$_{\\text{ext}}$":[152],"3.5%":[155],"AO":[156],"GOT-10k.":[159],"Moreover,":[160],"it":[161],"competitive":[163],"results":[164],"compared":[165],"fully":[167],"supervised":[168],"methods":[169],"LaSOT,":[171],"underscoring":[172],"robustness":[174],"complex":[176],"scenarios":[178],"potential":[181],"real-world":[183],"applications":[184],"dynamic":[186],"environments.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-11-21T00:00:00"}