EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding

TL;DR

EgoPCA introduces a comprehensive framework for egocentric hand-object interaction recognition, addressing domain gaps and setting new benchmarks with curated datasets and effective training strategies.

Contribution

The paper proposes a novel framework combining probing, curation, and adaptation to improve Ego-HOI recognition, including new datasets, baseline models, and training strategies.

Findings

Achieved state-of-the-art performance on Ego-HOI benchmarks.

Developed comprehensive pre-train and test datasets.

Established effective mechanisms for future research.

Abstract

With the surge in attention to Egocentric Hand-Object Interaction (Ego-HOI), large-scale datasets such as Ego4D and EPIC-KITCHENS have been proposed. However, most current research is built on resources derived from third-person video action recognition. This inherent domain gap between first- and third-person action videos, which have not been adequately addressed before, makes current Ego-HOI suboptimal. This paper rethinks and proposes a new framework as an infrastructure to advance Ego-HOI recognition by Probing, Curation and Adaption (EgoPCA). We contribute comprehensive pre-train sets, balanced test sets and a new baseline, which are complete with a training-finetuning strategy. With our new framework, we not only achieve state-of-the-art performance on Ego-HOI benchmarks but also build several new and effective mechanisms and settings to advance further research. We believe our data and the findings will pave a new way for Ego-HOI understanding. Code and data are available at https://mvig-rhos.com/ego_pca