{"id":"https://openalex.org/W7221125147","doi":"https://doi.org/10.64898/2026.10.07.757484","title":"JEPA-SORT: World-Model Embeddings Improve Deep-Sea Multi-Object Tracking on Visually Homogeneous Fauna","display_name":"JEPA-SORT: World-Model Embeddings Improve Deep-Sea Multi-Object Tracking on Visually Homogeneous Fauna","publication_year":2026,"publication_date":"2026-10-09","ids":{"openalex":"https://openalex.org/W7221125147","doi":"https://doi.org/10.64898/2026.10.07.757484"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.07.757484","doi":"https://doi.org/10.64898/2026.10.07.757484","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757484","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/09/2026.10.07.757484.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/09/2026.10.07.757484.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056308301","display_name":"Amory Tillinghast-Raby","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405265517","display_name":"OceanX","ror":"https://ror.org/051v6mv50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405265517"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amory Tillinghast-Raby","raw_affiliation_strings":["OceanX, Department of Data and Artificial Intelligence, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OceanX, Department of Data and Artificial Intelligence, New York, NY, USA","institution_ids":["https://openalex.org/I4405265517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158046829","display_name":"Matt Kravetz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405265517","display_name":"OceanX","ror":"https://ror.org/051v6mv50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405265517"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Kravetz","raw_affiliation_strings":["OceanX, Department of Data and Artificial Intelligence, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OceanX, Department of Data and Artificial Intelligence, New York, NY, USA","institution_ids":["https://openalex.org/I4405265517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158198478","display_name":"Jeriyla Kamau-Weng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405265517","display_name":"OceanX","ror":"https://ror.org/051v6mv50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405265517"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeriyla Kamau-Weng","raw_affiliation_strings":["OceanX, Department of Science, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OceanX, Department of Science, New York, NY, USA","institution_ids":["https://openalex.org/I4405265517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135779569","display_name":"Alexis Weinnig","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405265517","display_name":"OceanX","ror":"https://ror.org/051v6mv50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405265517"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexis Weinnig","raw_affiliation_strings":["OceanX, Department of Data and Artificial Intelligence, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OceanX, Department of Data and Artificial Intelligence, New York, NY, USA","institution_ids":["https://openalex.org/I4405265517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158204247","display_name":"Yara Rodrigues","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yara Rodrigues","raw_affiliation_strings":["Instituto do Mar, Mindelo, S\u00e3o Vicente, Cabo Verde"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto do Mar, Mindelo, S\u00e3o Vicente, Cabo Verde","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106113126","display_name":"Filippo Varini","orcid":"https://orcid.org/0009-0009-5908-787X","observed_orcids":["https://orcid.org/0009-0009-5908-787X"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Filippo Varini","raw_affiliation_strings":["Imperial College London, South Kensington Campus, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, South Kensington Campus, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135530640","display_name":"Vincent Pieribone","orcid":"https://orcid.org/0000-0002-5836-5454","observed_orcids":["https://orcid.org/0000-0002-5836-5454"]},"institutions":[{"id":"https://openalex.org/I4405265517","display_name":"OceanX","ror":"https://ror.org/051v6mv50","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4405265517"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Pieribone","raw_affiliation_strings":["OceanX, Department of Data and Artificial Intelligence, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OceanX, Department of Data and Artificial Intelligence, New York, NY, USA","institution_ids":["https://openalex.org/I4405265517"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056308301"],"corresponding_institution_ids":["https://openalex.org/I4405265517"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9810000061988831,"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":0.9810000061988831,"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":0.003599999938160181,"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/T12697","display_name":"Water Quality Monitoring Technologies","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/2312","display_name":"Water Science and Technology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-object-tracking","display_name":"multi-target tracking","score":0.8410000205039978},{"id":"https://openalex.org/keywords/jepa","display_name":"JEPA","score":0.6980000138282776},{"id":"https://openalex.org/keywords/identity-stability","display_name":"identity stability","score":0.5479999780654907},{"id":"https://openalex.org/keywords/marine-protected-areas","display_name":"marine protected areas","score":0.6029999852180481},{"id":"https://openalex.org/keywords/benthic-community-distribution","display_name":"benthic community distribution","score":0.5950000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6607999801635742},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6534000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6504999995231628},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5404999852180481},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.353300005197525},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C142259097","wikidata":"https://www.wikidata.org/wiki/Q5891314","display_name":"Homogeneity (statistics)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C145424490","wikidata":"https://www.wikidata.org/wiki/Q618465","display_name":"Remotely operated underwater vehicle","level":4,"score":0.27399998903274536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C22041718","wikidata":"https://www.wikidata.org/wiki/Q638949","display_name":"Geolocation","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.07.757484","doi":"https://doi.org/10.64898/2026.10.07.757484","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757484","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/09/2026.10.07.757484.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.07.757484","doi":"https://doi.org/10.64898/2026.10.07.757484","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.07.757484","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/09/2026.10.07.757484.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"score":1.0,"display_name":"Life below water","id":"https://metadata.un.org/sdg/14"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221125147.pdf","grobid_xml":"https://content.openalex.org/works/W7221125147.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1147987924","https://openalex.org/W2252355370","https://openalex.org/W3089737863","https://openalex.org/W4292553302","https://openalex.org/W4378471167","https://openalex.org/W4386076204","https://openalex.org/W4386590375","https://openalex.org/W4415245655","https://openalex.org/W4417190253","https://openalex.org/W4417414882","https://openalex.org/W6910554155","https://openalex.org/W7118792386","https://openalex.org/W7137837393","https://openalex.org/W7210292488"],"related_works":["https://openalex.org/W4417414882","https://openalex.org/W7168162496","https://openalex.org/W7106158426","https://openalex.org/W4395074320","https://openalex.org/W3204241363","https://openalex.org/W4394853694","https://openalex.org/W4401567442","https://openalex.org/W2896442146","https://openalex.org/W7117675891","https://openalex.org/W2954733329"],"abstract_inverted_index":{"ABSTRACT":[0],"Protecting":[1],"deep-sea":[2,55,67,140],"sessile":[3,141],"communities":[4,142],"as":[5],"Marine":[6],"Protected":[7],"Areas":[8],"(MPAs)":[9],"requires":[10],"accurate":[11],"estimates":[12],"of":[13,49,66,135,153,172,202],"their":[14],"spatial":[15],"distribution":[16],"and":[17,44,143,184,186],"abundance.":[18],"Existing":[19],"computer-vision":[20],"detection":[21],"methods":[22],"require":[23],"careful":[24],"calibration":[25],"to":[26,78,103],"avoid":[27],"counting":[28],"errors;":[29],"multi-object":[30],"tracking":[31],"(MOT)":[32],"theoretically":[33],"offers":[34],"a":[35,133,151],"more":[36],"robust":[37],"alternative.":[38],"In":[39,86],"practice,":[40],"however,":[41],"poor":[42],"lighting":[43],"turbidity":[45],"limit":[46],"the":[47,58,61,160,170,199],"efficacy":[48],"purely":[50],"kinematic":[51],"MOT":[52,84,93,148],"algorithms":[53,149],"in":[54,82,169],"environments.":[56,156],"At":[57],"same":[59],"time,":[60],"intra-species":[62],"visual":[63],"homogeneity":[64],"typical":[65],"scenes":[68],"means":[69],"traditional":[70],"per-frame":[71],"appearance":[72,115],"features":[73],"are":[74],"often":[75],"too":[76],"weak":[77],"maintain":[79,124],"stable":[80,125],"identities":[81,126],"deep-association":[83],"algorithms.":[85],"this":[87],"paper":[88],"we":[89],"introduce":[90],"JEPA-SORT,":[91],"an":[92],"algorithm":[94],"that":[95,105],"injects":[96],"V-JEPA":[97],"2.1":[98],"embeddings":[99,108,204],"into":[100],"detection-to-track":[101],"association,":[102],"show":[104],"video":[106],"world-model":[107,203],"-":[109,121],"which":[110,165],"capture":[111],"not":[112],"only":[113],"physical":[114],"but":[116],"spatiotemporal":[117],"trajectory":[118],"across":[119,150],"viewpoints":[120],"can":[122],"help":[123],"on":[127,181,189,205],"visually":[128,206],"homogeneous":[129,207],"specimens.":[130],"We":[131,157],"provide":[132],"benchmark":[134],"twelve":[136],"ROV":[137],"transects":[138],"surveying":[139],"evaluate":[144],"JEPA-SORT":[145,176],"against":[146],"standard":[147],"range":[152],"simulated":[154],"optical":[155],"also":[158],"propose":[159],"Biodensity":[161],"Utility":[162],"Metric":[163],"(BDU),":[164],"measures":[166],"tracker":[167],"performance":[168],"context":[171],"downstream":[173],"ecological":[174],"modeling.":[175],"outperforms":[177],"all":[178],"benchmarked":[179],"trackers":[180],"IDF1,":[182],"MOTA,":[183],"BDU":[185],"is":[187],"competitive":[188],"specimen-count":[190],"accuracy.":[191],"Ablations":[192],"indicate":[193],"its":[194],"advantage":[195],"stems":[196],"primarily":[197],"from":[198],"discriminative":[200],"power":[201],"footage.":[208]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-10T00:00:00"}