Although an object may appear in numerous contexts, we often describe it in a limited
number of ways. Language allows us to abstract away visual variation to represent and …

Recent advances in zero-shot image recognition suggest that vision-language models learn
generic visual representations with a high degree of semantic information that may be …

Vision-based robot policy learning, which maps visual inputs to actions, necessitates a
holistic understanding of diverse visual tasks beyond single-task needs like classification or …

Reinforcement Learning (RL) can be considered as a sequence modeling task: given a
sequence of past state-action-reward experiences, an agent predicts a sequence of next …

Abstract Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite
their success, ViTs lack inductive biases, which can make it difficult to train them with limited …

Understanding action recognition in egocentric videos has emerged as a vital research topic
with numerous practical applications. With the limitation in the scale of egocentric data …

We humans are good at translating third-person observations of hand-object interactions
(HOI) into an egocentric view. However, current methods struggle to replicate this ability of …

Unpaired image translation algorithms can be used for sim2real tasks, but many fail to
generate temporally consistent results. We present a new approach that combines …

Human perception of surroundings is often guided by the various poses present within the
environment. Many computer vision tasks, such as human action recognition and robot …

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 …