California Sea Lion, Brandt's Cormorant

Northern Gannet

Northern Gannet, in Pillar Point Harbor, CA, US This is Morris. Morris is a local celebrity: the only known Northern Gannet ( Morus bassanus ) in the entire Pacific Ocean.

Northern Gannet, Great Blue Heron, California Brown Pelican

The photographer captured a Northern Gannet, Great Blue Heron, and California Brown Pelican in Monterey Bay National Marine Sanctuary, California, using a 200‑800mm Canon EF lens. The birds were observed congregating beneath a harbor sign, providing a striking image of wildlife in their natural habitat.

California Brown Pelican

The California Brown Pelican has taken over the Pacifica Pier in San Mateo County, CA, after the pier was shut down in early June due to a cracked concrete walkway that made it unsafe for public access. The pelicans have occupied the area, effectively replacing human use of the pier. The incident highlights how wildlife can quickly reclaim abandoned or unsafe human structures.

The Falcon has landed in the Hugging Face ecosystem

Falcon Perception

GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price

Simon Willison comments on GPT 6.1‑Sol, describing it as "Near‑Astra intelligence for a fifth of the price." He notes that the model’s pelican illustrations are similar to those of the GPT‑6 family and provides links to the live‑blog of the keynote and to the pelican images. The post is tagged with AI, OpenAI, generative‑AI, LLMs, and playful references to pelican‑riding‑a‑bicycle.

Strip Convolution and Direction-Aware Exclusion Loss for Oriented Ship Detection

The paper introduces a new oriented ship detector that combines a C3k2_Strip module, which uses orthogonal strip convolutions to better capture elongated hull structures, with a Class-Aware Direction-Aware Exclusion Loss (CA-DAEL) that suppresses redundant predictions by leveraging class, direction, and confidence cues. Experiments on HRSC2016 and DIOR-R datasets show the method achieving 78.45% and 53.71% mAP50:95, respectively, with only 2.91M parameters. On HRSC2016, the approach outperforms the YOLOv11-OBB baseline by 6.32 percentage points in mAP50:95, highlighting its effectiveness for accurate oriented ship detection.

What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in Visual Representations

The study investigates whether Vision Transformer (ViT)-based animal re-identification models learn biologically meaningful concepts. Using a DINOv3 backbone fine‑tuned on Western lowland gorilla images, the authors find that sex and age emerge as linear directions in the model’s representations, generalizing to unseen individuals with high AUROC scores. They demonstrate that the sex direction is causally used by the model, that fine‑tuning relocates these concepts within the network, and that the representations reflect a graded biological axis encoded redundantly across the population.

Planktonzilla: Multimodal dataset and models for understanding plankton ecosystems

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.

Geometric Coastline Localization using Vision-Language Models

arXiv:2606.10468v2 Announce Type: replace Abstract: Coastline detection in remotely sensed imagery is commonly formulated as pixel-wise segmentation, even though coastlines used in coastal monitoring...

GrabVG: Graph-Attentive Binding for Visual Grounding in UAV Imagery

GrabVG is a visual grounding framework for UAV imagery that tackles the challenges of small, densely packed, and visually similar objects. It splits the task into preattentive hypothesis search and graph‑attentive feature binding, using distillation‑guided proposals and a sparse graph to capture intra‑ and inter‑instance relationships. Experiments on AerialVG and AerialSense show that GrabVG achieves higher accuracy and speed, outperforming baselines by significant margins.

Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection

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.