Underwater object detection (UOD) plays an important role in the exploitation of marine ecological resources. Different from terrestrial images, the complex underwater environment leads to significant ...

In contrast to them, we propose FRA ctal CAL ibration (FRACAL): a novel post-calibration method for long-tailed object detection. FRACAL devises a logit adjustment method that utilises the fractal ...

NVA goes beyond simple object detection to recognize relationships between objects, detect procedural violations, and identify complex risk factors in real time.

I tried using DINOv3 as the pre-trained model for the detector and encountered an issue. When defining the Transformer, self.reference_points（not two-stage） is initialized as follows: if two_stage: ...

Open-world object detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects ...