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.
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...
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...
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.
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...
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.
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.
The paper presents a method that leverages sparse expert point annotations from historical benthic surveys to improve dense segmentation of marine imagery. By using these points as visual prompts for the SAM2 foundation model and introducing a mechanism to filter out unreliable points, the authors generate high‑quality pseudo‑ground‑truth masks that train more accurate fine‑grained semantic segmentation models. The approach is validated on public benthic datasets and a new benchmark featuring real‑world sparse annotations, aiming to enable scalable ecological analysis.
Vessel perception from space is crucial for a wide range of maritime applications, from traffic monitoring to environmental protection. However, most existing datasets predominantly focus on general o...
arXiv:2608.21281v1 Announce Type: new Abstract: Recent advances in field technology have led to a massive influx of in-the-wild video data for ecological science. The primary bottleneck in leveraging...
arXiv:2606. 00080v1 Announce Type: cross Abstract: Marine plankton underpin aquatic food webs and play a key role in global CO2 sequestration, making reliable species identification critical for understanding ocean health and climate feedbacks.
arXiv:2609.37003v1 Announce Type: new Abstract: Vessel perception from space is crucial for a wide range of maritime applications, from traffic monitoring to environmental protection. However, most e...
Det‑LIME is a detector‑aware, multi‑instance adaptation of LIME designed to explain black‑box object detectors used in marine mammal research. It generates instance‑specific, box‑aligned explanations by weighting detections, applying a proximity kernel, and using IoU‑based matching to track instances across perturbations. Evaluated on aerial drone imagery of harbor seals and a seabird case study, Det‑LIME outperformed vanilla LIME, Stabilized LIME, Deterministic LIME, and gradient‑based methods in Attribution Ratio and Max Saliency Hit Rate, offering higher‑resolution, instance‑aware explanations that aid debugging, data augmentation, and modeling improvements.