Imagine it’s a rainy Tuesday in February 2026. An autonomous delivery robot is navigating a busy metropolitan sidewalk. Its sensors detect an object fifty feet ahead: a crumpled, brownish shape lying ...

Hi, thank you for this impressive work! I am diving into the data processing pipeline described in Section III-A in your paper, specifically regarding the object motion data. While the paper mentions ...

Visual surveys by autonomous underwater vehicles (AUVs) and other underwater platforms provide a valuable method for analysing and understanding the benthic environment. Scientists can measure the ...

Abstract: Existing object detection and annotation methods in surveillance systems often suffer from inefficiencies due to manual labeling and a lack of accurate distance estimation, which limits ...

I would like to segment multiple object within a 1-2 min short video clips. But sometimes there are other object entering the scene and I want to segment them also. I have tried adding all annotations ...

Abstract: Deep learning-based computer vision models are typically data-hungry, resulting in the rise of dataset sizes. The consensus for computer vision datasets is that larger datasets lead to ...