Deep learning models and graphics processing units have completely transformed the field
of machine learning. Recurrent neural networks and long short-term memories have been …

We present a comprehensive framework for egocentric interaction recognition using
markerless 3D annotations of two hands manipulating objects. To this end, we propose a …

Abstract Human-Object Interaction Detection tackles the problem of joint localization and
classification of human object interactions. Existing HOI transformers either adopt a single …

Human action is naturally compositional: humans can easily recognize and perform actions
with objects that are different from those used in training demonstrations. In this paper, we …

It is difficult to construct a data collection including all possible combinations of human
actions and interacting objects due to the combinatorial nature of human-object interactions …

Telehealth and remote health monitoring have become increasingly important during the
SARS-CoV-2 pandemic and it is widely expected that this will have a lasting impact on …

Human actions involving hand manipulations are structured according to the making and
breaking of hand-object contact, and human visual understanding of action is reliant on …

Skeleton-based human action recognition has received extensive attention due to its
efficiency and robustness to complex backgrounds. Though the human skeleton can …

Human-Object Interaction (HOI) Detection is an important task to understand how humans
interact with objects. Most of the existing works treat this task as an exhaustive triplet< …

Human actions are typically of combinatorial structures or patterns, ie, subjects, objects, plus
spatio-temporal interactions in between. Discovering such structures is therefore a …