{
  "abstract": "Protecting deep-sea sessile communities as Marine Protected Areas (MPAs) requires accurate estimates of their spatial distribution and abundance. Existing computer-vision detection methods require careful calibration to avoid counting errors; multi-object tracking (MOT) theoretically offers a more robust alternative. In practice, however, poor lighting and turbidity limit the efficacy of purely kinematic MOT algorithms in deep-sea environments. At the same time, the intra-species visual homogeneity typical of deep-sea scenes means traditional per-frame appearance features are often too weak to maintain stable identities in deep-association MOT algorithms. In this paper we introduce JEPA-SORT, an MOT algorithm that injects V-JEPA 2.1 embeddings into detection-to-track association, to show that video world-model embeddings - which capture not only physical appearance but spatiotemporal trajectory across viewpoints - can help maintain stable identities on visually homogeneous specimens. We provide a benchmark of twelve ROV transects surveying deep-sea sessile communities and evaluate JEPA-SORT against standard MOT algorithms across a range of simulated optical environments. We also propose the Biodensity Utility Metric (BDU), which measures tracker performance in the context of downstream ecological modeling. JEPA-SORT outperforms all benchmarked trackers on IDF1, MOTA, and BDU and is competitive on specimen-count accuracy. Ablations indicate its advantage stems primarily from the discriminative power of world-model embeddings on visually homogeneous footage.",
  "abstract_shown": true,
  "affiliations": [
    "OceanX"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "A. Tillinghast-Raby"
    },
    {
      "name": "M. Kravetz"
    },
    {
      "name": "J. Kamau-Weng"
    },
    {
      "name": "A. Weinnig"
    },
    {
      "name": "Y. Rodrigues"
    },
    {
      "name": "F. Varini"
    },
    {
      "name": "V. Pieribone"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/arnzs6bnvn8b3.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.07.757484",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.07.757484v1.full",
  "id": "arnzs6bnvn8b3",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.07.757484v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "ecology"
    ],
    [
      "openalex",
      "1707|Video Surveillance and Tracking Methods"
    ]
  ],
  "openalex": "W7221125147",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.07.757484v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-07",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/arnzs6bnvn8b3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:50Z",
      "native_id": "10.64898/2026.10.07.757484",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.07.757484v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:ecology",
      "subfield": "ecology"
    }
  ],
  "title": "JEPA-SORT: World-Model Embeddings Improve Deep-Sea Multi-Object Tracking on Visually Homogeneous Fauna",
  "title_text": "JEPA-SORT: World-Model Embeddings Improve Deep-Sea Multi-Object Tracking on Visually Homogeneous Fauna",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:50Z",
  "url": "https://research.draconitic.com/paper/arnzs6bnvn8b3",
  "venue": "bioRxiv",
  "versions": []
}