Although widely used in many applications, accurate and efficient human action recognition
remains a challenging area of research in the field of computer vision. Most recent surveys …

Scene graph is a structured representation of a scene that can clearly express the objects,
attributes, and relationships between objects in the scene. As computer vision technology …

Abstract Vision-language (V+ L) pretraining models have achieved great success in
supporting multimedia applications by understanding the alignments between images and …

We present an approach that can reconstruct hands in 3D from monocular input. Our
approach for Hand Mesh Recovery HaMeR follows a fully transformer-based architecture …

This paper addresses the task of detecting and recognizing human-object interactions (HOI)
in images and videos. We introduce the Graph Parsing Neural Network (GPNN), a …

We tackle the challenging problem of human-object interaction (HOI) detection. Existing
methods either recognize the interaction of each human-object pair in isolation or perform …

We investigate the problem of producing structured graph representations of visual scenes.
Our work analyzes the role of motifs: regularly appearing substructures in scene graphs. We …

Hands are the central means by which humans manipulate their world and being able to
reliably extract hand state information from Internet videos of humans engaged in their …

This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions
(AVA). The AVA dataset densely annotates 80 atomic visual actions in 437 15-minute video …

Understanding a visual scene goes beyond recognizing individual objects in isolation.
Relationships between objects also constitute rich semantic information about the scene. In …