Research map / Video / Action recognition
FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding
Eadom Dessalene, Botao He, Michael Maynord, Yonatan Tussa, Pavan Mantripragada, Yianni Karabatis, Nirupam Roy, Yiannis Aloimonos
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add FEEL force-prediction pretraining | Hiera-B (frozen) · EPIC-Kitchens verb | top-1 accuracy: 41.65 -> 46.50 | Improved |
| add FEEL force-prediction pretraining | Hiera-B (frozen) · EPIC-Kitchens noun | top-1 accuracy: 15.12 -> 21.38 | Improved |
| add FEEL force-prediction pretraining | Hiera-B (frozen) · SSV2 action | top-1 accuracy: 36.08 -> 39.04 | Improved |
| add FEEL force-prediction pretraining | Hiera-B (frozen) · Ego-Exo4D action | top-1 accuracy: 13.11 -> 20.83 | Improved |
| add FEEL force-prediction pretraining | Hiera-B (frozen) · Meccano action | top-1 accuracy: 26.42 -> 29.57 | Improved |
| add FEEL force-prediction pretraining | EgoVideo-B (frozen) · EPIC-Kitchens verb | top-1 accuracy: 59.24 -> 62.00 | Improved |
| add FEEL force-prediction pretraining | EgoVideo-B (frozen) · SSV2 action | top-1 accuracy: 49.61 -> 54.34 | Improved |
| add FEEL force-prediction pretraining | EgoVideo-B (frozen) · Ego-Exo4D action | top-1 accuracy: 26.00 -> 27.75 | Improved |
| add FEEL force-prediction pretraining | EgoVideo-B (frozen) · Meccano action | top-1 accuracy: 36.59 -> 38.23 | Improved |
| add FEEL force-prediction pretraining | Hiera-B (unfrozen) · Ego-Exo4D action | top-1 accuracy: 35.25 -> 41.19 | Improved |
| add FEEL force-prediction pretraining | Hiera-B (unfrozen) · EPIC-Kitchens verb | top-1 accuracy: 68.34 -> 68.24 | No clear effect |
| add FEEL force-prediction pretraining | EgoVideo-B (unfrozen) · Ego-Exo4D action | top-1 accuracy: 40.92 -> 40.75 | No clear effect |
Closest papers by meaning
- EgoPHI: Estimating 3D Hand-Object Contact and Force from Egocentric Vision (ECCV 2026 · similarity 0.91)
- Forecasting Action Through Contact Representations From First Person Video (TPAMI 2021 · similarity 0.90)
- EgoTac: In-the-wild Tactile Prediction from Egocentric Vision (NeurIPS 2026 · similarity 0.89)
- Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects (CVPR 2020 · similarity 0.89)
- Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning (ICLR 2025 · similarity 0.88)
- ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
