Abstract We present Ego-Exo4D a diverse large-scale multimodal multiview video dataset
and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric …

We pursue the goal of developing robots that can interact zero-shot with generic unseen
objects via a diverse repertoire of manipulation skills and show how passive human videos …

The focal point of egocentric video understanding is modelling hand-object interactions.
Standard models, eg CNNs or Vision Transformers, which receive RGB frames as input …

What will the future be? We wonder! In this survey, we explore the gap between current
research in egocentric vision and the ever-anticipated future, where wearable computing …

Self-supervised learning (SSL) has revolutionized visual representation learning, but has
not achieved the robustness of human vision. A reason for this could be that SSL does not …

Neural rendering is fuelling a unification of learning, 3D geometry and video understanding
that has been waiting for more than two decades. Progress, however, is still hampered by a …

In this paper we study multi-label atomic activity recognition. Despite the notable progress in
action recognition it is still challenging to recognize atomic activities due to a deficiency in …

We address a novel cross-domain few-shot learning task (CD-FSL) with multimodal input
and unlabeled target data for egocentric action recognition. This paper simultaneously …

Egocentric videos provide comprehensive contexts for user and scene understanding,
spanning multisensory perception to behavioral interaction. We propose Spherical World …

Electric (e)-scooters have emerged as a popular, ubiquitous, and first/last-mile micromobility
transportation option within and across many cities worldwide. With the increasing situation …