Abstract: Visual grounding aims to use a natural language expression to find specific objects in an image, whether in a bounding box or a segmentation mask. The vision research community has ...

🔔 The automatic evaluation on CodaLab are under construction. The MathVista dataset is derived from three newly collected datasets: IQTest, FunctionQA, and Paper, as well as 28 other source datasets.

Bring bold style and fearless attitude to your sketchbook with this Exotic Cruella De Vil drawing that feels like high fashion meets cinematic character art. This tutorial focuses on capturing Cruella ...

Abstract: Interactive visual grounding in Human-Robot Interaction (HRI) is challenging yet practical due to the inevitable ambiguity in natural languages. It requires robots to disambiguate the user’s ...