arXiv Computer Vision November 2, 2026 By Jingtao Deng, Zihao Jin, Yuehe Chen, Feixiang He, Shuiwang Li, Dan Zeng

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

Read the original on arXiv Computer Vision →

Nereus is a new large-scale underwater dataset that supports fine-grained object attribute understanding and grounded counting perception. It contains 88,000 images, 2.68 million question-answer pairs, and annotations for 136,000 marine organism objects spanning 2,690 species and 1,515 genera, along with 65,000 point annotations and 67,000 grounded counting QA pairs. Experiments with 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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

multimodal

Hugging Face Trending Papers

Aug 24

WADE: A Reasoning-Annotated Benchmark for Multi-Instance Floating-Waste Grounding with Compact Vision-Language Models

Floating waste in inland waterways threatens aquatic ecosystems and requires timely monitoring under cluttered, multi-object conditions. Existing aquatic-waste datasets provide limited geographic cove...

llms fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Aug 25

WADE: A Reasoning-Annotated Benchmark for Multi-Instance Floating-Waste Grounding with Compact Vision-Language Models

arXiv:2608.22950v1 Announce Type: new Abstract: Floating waste in inland waterways threatens aquatic ecosystems and requires timely monitoring under cluttered, multi-object conditions. Existing aquat...

By Md. Asaduzzaman Shuvo, Ahsan Farabi, Md. Abdul Ahad Minhaz, Mahedi Hasan, Israt Khandaker, Ibrahim Khalil Shanto, Muhammad Nomani Kabir

llms fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 25

Taxonomy-aware deep learning for hierarchical marine species classification in underwater imagery

arXiv:2606. 25989v1 Announce Type: cross Abstract: Automated classification of marine species from underwater imagery is essential for scalable ocean biodiversity monitoring and conservation policy.

By Dan Zimmerman, Dimitris A. Pados, George Sklivanitis

arXiv AI

Oct 27

MarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding

arXiv:2610.33478v1 Announce Type: cross Abstract: Marine video understanding is crucial for a wide range of real-world applications. However, existing marine video datasets suffer from limitations, i...

By Quang-Trung Truong, Thanh-Nghia Nguyen, Phu-Phong Vo, Jaeyeon Kim, Cheng Chen, Jie Zhang, Binh-Son Hua, Duc Thanh Nguyen, Ivor Tsang, Sai-Kit Yeung

llms nlp benchmarks

arXiv AI

Jul 28

MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning

arXiv:2607. 24064v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality image-text pairs.

By Tuan-An To, Yuk-Kwan Wong, Tuan-Anh Vu, Ziqiang Zheng, Sai-Kit Yeung

llms multimodal benchmarks

arXiv AI

Oct 15

Exploring the Underwater World Segmentation without Extra Training

The paper introduces AquaOV255, a large-scale underwater segmentation dataset with 255 categories and over 20,000 images, and establishes the UOVSBench benchmark by combining it with five other datasets. It also presents Earth2Ocean, a training‑free open‑vocabulary segmentation framework that adapts terrestrial vision‑language models to underwater scenes using a Geometric‑guided Visual Mask Generator and a Category‑visual Semantic Alignment module. Experiments on UOVSBench show that Earth2Ocean significantly improves performance while keeping inference efficient.

By Bingyu Li, Tao Huo, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li

llms rag computer-vision multimodal benchmarks safety

One email a morning, machine-written

Related stories

WADE: A Reasoning-Annotated Benchmark for Multi-Instance Floating-Waste Grounding with Compact Vision-Language Models

WADE: A Reasoning-Annotated Benchmark for Multi-Instance Floating-Waste Grounding with Compact Vision-Language Models

Taxonomy-aware deep learning for hierarchical marine species classification in underwater imagery

MarineLife-16K: An Attribute-Rich Video-Text Dataset for Motion-Aware Marine Video Understanding

MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning

Exploring the Underwater World Segmentation without Extra Training