Metraipolis › archive › dc_d4ff67b267c5

Nereus: A Large-Scale Underwater Dataset for Fine-Grained Attribute Understanding and Grounded Counting Perception — arXiv:2610.41705

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41705
License (as archived)
CC0-1.0
Archived
2026-11-02T08:03:23.120Z
SHA-256 of the archived text
9710fabc09a558f051f3a2cd48ebf5828f5b1049bc335ea64f5e6d0545829657
Stable URL of this page
https://metraipolis.com/documento/dc_d4ff67b267c5

How to cite

Nereus: A Large-Scale Underwater Dataset for Fine-Grained Attribute Understanding and Grounded Counting Perception — arXiv:2610.41705 — arXiv (en), https://arxiv.org/abs/2610.41705 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d4ff67b267c5 (Metraipolis archive dc_d4ff67b267c5, sha256 9710fabc09a558f051f3a2cd48ebf5828f5b1049bc335ea64f5e6d0545829657)
BibTeX
@misc{dcd4ff67b267c5,
  title = {Nereus: A Large-Scale Underwater Dataset for Fine-Grained Attribute Understanding and Grounded Counting Perception — arXiv:2610.41705},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41705},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d4ff67b267c5; sha256 9710fabc09a558f051f3a2cd48ebf5828f5b1049bc335ea64f5e6d0545829657},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41705. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Underwater imagery records rich ecological information and supports applications such as science communication, fishery monitoring, ecological conservation, and oceanographic research. Beyond general scene understanding, these applications require models to recognize fine-grained biological traits and reason over spatially grounded evidence. However, existing underwater datasets often provide coarse category labels, generic captions, or total-count supervision, which limits their use for organism-level analysis and ecological reasoning. We introduce Nereus, a large-scale dataset for Underwater Fine-grained Perception that jointly supports Fine-Grained Object Attribute Understanding and Grounded Counting Perception. Nereus contains 88K images and 2.68M question-answer pairs, including annotations for 136K marine organism objects across 2,690 species and 1,515 genera, as well as 65K point annotations and 67K grounded counting QA pairs. Experiments with representative multimodal models show that Nereus improves downstream adaptation over existing underwater-domain data and provides a foundation for future research on fine-grained marine perception.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41705 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T07:44:00.765Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).