OBER (OBject-Effect Removal) is a hybrid dataset designed to support research in object removal with effects, combining both camera-captured and simulated data. 🔥 We have released the full dataset ...

Abstract: Referring camouflaged object detection (Ref-COD) is a recently proposed task, aiming to segment specified camouflaged objects by leveraging visual reference, i.e., a small set of referring ...

With the rise of AI coding assistants continuing apparently unabated, some project maintainers have begun striking back. Ars Technica reports on projects putting hostile directions into the ...

Abstract: Fine-grained object detection (FGOD) extends object detection with the capability of fine-grained recognition. In recent two-stage FGOD methods, the region proposal serves as a crucial link ...

Modern web scraping has quietly stopped being a parsing problem. What used to be a straightforward task of downloading HTML and extracting structured elements has evolved into something much closer to ...