Research map / Video / Video-language understanding
Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 acceleration features to visual features (ablation) | EnergyRCN · Stanford-ECM | mAP, all activities: 76.2 -> 78.1 | Helped |
| add acceleration features to visual features (ablation) | EnergyRCN · Stanford-ECM | absolute error (kcal · m−1): 0.75 ± 0.29 -> 0.70 ± 0.27 | Helped |
| add visual features to acceleration features (ablation) | EnergyRCN · Stanford-ECM | mAP, all activities: 52.3 -> 78.1 | Helped |
| add visual features to acceleration features (ablation) | EnergyRCN · Stanford-ECM | absolute error (kcal · m−1): 0.77 ± 0.36 -> 0.70 ± 0.27 | Helped |
| jointly train activity detection and energy regression instead of activity detection alone (ablation) | EnergyRCN (V+A) · Stanford-ECM | mAP, all activities: 76.7 -> 78.1 | Helped |
| jointly train activity detection and energy regression (ablation) | EnergyRCN (V+A) · Stanford-ECM | absolute error (kcal · m−1): 0.699 -> 0.696 | No clear effect |
| fuse visual and acceleration features rather than use visual features alone (ablation) | EnergyRCN · Stanford-ECM, vigorous activities | mAP: 82.3 -> 82.2 | No clear effect |
| fuse visual and acceleration features rather than use visual features alone (ablation) | EnergyRCN · Stanford-ECM, moderate activities | mAP: 89.9 -> 92.1 | Helped |
| fuse visual and acceleration features rather than use visual features alone (ablation) | EnergyRCN · Stanford-ECM, light activities | mAP: 70.5 -> 78.3 | Helped |
| fuse visual and acceleration features rather than use visual features alone (ablation) | EnergyRCN · Stanford-ECM, sedentary activities | mAP: 71.0 -> 70.8 | No clear effect |
Closest papers by meaning
- EgoLM: Multi-Modal Language Model of Egocentric Motions (CVPR 2025 · similarity 0.84)
- egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-world Tasks (NeurIPS 2025 · similarity 0.84)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.84)
- EgoLife: Towards Egocentric Life Assistant (CVPR 2025 · similarity 0.83)
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (CVPR 2024 · similarity 0.83)
- Test-Time Adaptation for Combating Missing Modalities in Egocentric Videos (ICLR 2025 · similarity 0.83)
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.