Research map / Video / Action recognition
EPFL-Smart-Kitchen: An Ego-Exo Multi-Modal Dataset for Challenging Action and Motion Understanding in Video-Language Models
Andy Bonnetto, Haozhe Qi, Franklin Leong, Matea Tashkovska, Mahdi Rad, Solaiman Shokur, Friedhelm Hummel, Silvestro Micera, Marc Pollefeys, Alexander Mathis
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces EPFL-Smart-Kitchen-30, an ego-exo multi-modal kitchen dataset captured with a noninvasive motion capture platform, for challenging action and motion understanding in video-language models.
Problem
Understanding human behavior in complex, multi-step kitchen tasks requires datasets that capture humans performing these tasks with rich motion and cognitive detail; existing video-language benchmarks are limited for this.
Approach
A kitchen-based ego-exo multi-modal dataset recorded with nine static RGB cameras plus motion capture, designed to challenge action and motion understanding in video-language models.
Closest papers by meaning
- The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines (TPAMI 2020 · similarity 0.90)
- ActionSense: A Multimodal Dataset and Recording Framework for Human Activities Using Wearable Sensors in a Kitchen Environment (NeurIPS 2022 · similarity 0.90)
- LLaVAction: evaluating and training multi-modal large language models for action understanding (ICLR 2026 · similarity 0.87)
- HD-EPIC: A Highly-Detailed Egocentric Video Dataset (CVPR 2025 · similarity 0.87)
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (CVPR 2024 · similarity 0.86)
- Action Scene Graphs for Long-Form Understanding of Egocentric Videos (CVPR 2024 · similarity 0.85)
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.
