FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding

TL;DR

FEEL introduces a large-scale egocentric dataset with force measurements from custom gloves, enabling improved physical action understanding through contact segmentation and self-supervised action representation learning.

Contribution

The paper presents FEEL, the first large-scale dataset pairing force data with egocentric video, facilitating new research in physical action understanding.

Findings

State-of-the-art contact segmentation results

Competitive pixel-level segmentation without manual annotations

Improved transfer performance in action understanding tasks

Abstract

We introduce FEEL (Force-Enhanced Egocentric Learning), the first large-scale dataset pairing force measurements gathered from custom piezoresistive gloves with egocentric video. Our gloves enable scalable data collection, and FEEL contains approximately 3 million force-synchronized frames of natural unscripted manipulation in kitchen environments, with 45% of frames involving hand-object contact. Because force is the underlying cause that drives physical interaction, it is a critical primitive for physical action understanding. We demonstrate the utility of force for physical action understanding through application of FEEL to two families of tasks: (1) contact understanding, where we jointly perform temporal contact segmentation and pixel-level contacted object segmentation; and, (2) action representation learning, where force prediction serves as a self-supervised pretraining objective for video backbones. We achieve state-of-the-art temporal contact segmentation results and competitive pixel-level segmentation results without any need for manual contacted object segmentation annotations. Furthermore we demonstrate that action representation learning with FEEL improves transfer performance on action understanding tasks without any manual labels over EPIC-Kitchens, SomethingSomething-V2, EgoExo4D and Meccano.