A key challenge in intelligent robotics is creating robots that are capable of directly
interacting with the world around them to achieve their goals. The last decade has seen …

One of the fundamental goals of visual perception is to allow agents to meaningfully interact
with their environment. In this paper, we take a step towards that long-term goal--we extract …

To teach robots skills, it is crucial to obtain data with supervision. Since annotating real world
data is time-consuming and expensive, enabling robots to learn in a self-supervised way is …

In this paper, we explore how we can build upon the data and models of Internet images and
use them to adapt to robot vision without requiring any extra labels. We present a framework …

Cascaded architectures have brought significant performance improvement in object
detection and instance segmentation. However, there are lingering issues regarding the …

Contrary to the vast literature in modeling, perceiving, and understanding agent-object (eg,
human-object, hand-object, robot-object) interaction in computer vision and robotics, very …

Abstract Convolutional Neural Networks (CNNs) have proved exceptional at learning
representations for visual object categorization. However, CNNs do not explicitly encode …

Contour-based instance segmentation methods are attractive due to their efficiency.
However, existing contour-based methods either suffer from lossy representation, complex …

People often use physical intuition when manipulating articulated objects, irrespective of
object semantics. Motivated by this observation, we identify an important embodied task …

Passive visual systems typically fail to recognize objects in the amodal setting where they
are heavily occluded. In contrast, humans and other embodied agents have the ability to …