Abstract Large Vision & Language models pretrained on web-scale data provide
representations that are invaluable for numerous V &L problems. However, it is unclear how …

Active recognition enables robots to intelligently explore novel observations thereby
acquiring more information while circumventing undesired viewing conditions. Recent …

Active recognition which allows intelligent agents to explore observations for better
recognition performance serves as a prerequisite for various embodied AI tasks such as …

In this work, we investigate Active Vision Reinforcement Learning (ActiveVision-RL), where
an embodied agent simultaneously learns action policy for the task while also controlling its …

This paper considers the active recognition scenario, where the agent is empowered to
intelligently acquire observations for better recognition. The agents usually compose two …

Visual recognition, a core area of computer vision, aims to interpret semantic information
from images and videos. With advancements in deep neural networks and substantial …