# FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding Source: [FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding]() Collection index: [llms.txt]() Data updated: 2026-03-19T05:00:05.030Z Authors: Eadom Dessalene, Botao He, Michael Maynord, Yonatan Tussa, Pavan Mantripragada, Yianni Karabati, Nirupam Roy, Yiannis Aloimonos Published: 2026-03-16T19:29:04.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Spatial contact segmentation on FEEL (val)](): Spatial contact segmentation; FEEL (val); IoU: 62.5. - [Temporal contact detection on VISOR (val)](): Temporal contact detection; VISOR (val); BC: 87.3. - [Temporal contact detection on FEEL (val)](): Temporal contact detection; FEEL (val); BC: 95.6. - [Temporal contact detection on HOI4D (val)](): Temporal contact detection; HOI4D (val); BC: 82.2. - [Spatial contact segmentation on HOI4D (val)](): Spatial contact segmentation; HOI4D (val); IoU: 75.1. - [Spatial contact segmentation on EPIC-VISOR (val)](): Spatial contact segmentation; EPIC-VISOR (val); IOU: 39.9. ## Original sources and implementation [Original paper]() [PDF]()