H2O: Two Hands Manipulating Objects for First Person Interaction Recognition

By Taein Kwon, Bugra Tekin, Jan Stühmer, Federica Bogo, Marc Pollefeys. IEEE International Conference on Computer Vision, 2021

299 citations recorded by the source corpus.

We present a comprehensive framework for egocentric interaction recognition using markerless 3D annotations of two hands manipulating objects. To this end, we propose a method to create a unified dataset for egocentric 3D interaction recognition. Our method produces annotations of the 3D pose of two hands and the 6D pose of the manipulated objects, along with their interaction labels for each frame. Our dataset, called H2O (2 Hands and Objects), provides synchronized multi-view RGB-D images, interaction labels, object classes, ground-truth 3D poses for left & right hands, 6D object poses, ground-truth camera poses, object meshes and scene point clouds. To the best of our knowledge, this is the first benchmark that enables the study of first-person actions with the use of the pose of both left and right hands manipulating objects and presents an unprecedented level of detail for egocentric 3D interaction recognition. We further propose the method to predict interaction classes by estimating the 3D pose of two hands and the 6D pose of the manipulated objects, jointly from RGB images. Our method models both inter- and intra-dependencies between both hands and objects by learning the topology of a graph convolutional network that predicts interactions. We show that our method facilitated by this dataset establishes a strong baseline for joint hand-object pose estimation and achieves state-of-the-art accuracy for first person interaction recognition.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/3cb0a29bc4414d5979a9d3a94ec30dcab3ae43f7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Human-Computer Interaction

Citations in the corpus

Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities (2022, methodology): “Implementation details: We use the publicly available Py-Torch [23] code for 2s-AGCN and MS-G3D.”
Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos (2021, background): “Very recently, [10] and [32] propose to collect annotations using hybrid methods to collect reliable labels.”
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (2023, unknown): “More recent ego-exo efforts focus on specific activities in one or two environments.”
MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain (2022, background): “The authors of [52] proposed a uniﬁed approach to recognize hand-object interactions predicting the 3D pose of the two interacting hands and the 6D pose of manipulated objects simultaneously.”
Human Hands as Probes for Interactive Object Understanding (2021, background): “Several works have sought to build a data-driven understanding of human hands and how they manipulate objects from RGB images [63], RGB-D images [51], egocentric data [31], videos [17] and other sensors [2, 58].”
ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation (2022, background): “Existing hand-object datasets [8,22,23,37,41] are captured with 1−8 commodity RGB-D cameras, which is insufficient to eliminate occlusion.”
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction (2022, methodology): “Recently some efforts [18, 19, 22] have been made to fulfill such needs.”