# Elderly Action Recognition Challenge at WACV2025 — Data

来源：https://www.kaggle.com/competitions/elderly-action-recognition-challenge-at-wacv-2025/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

**Important note:** The provided dataset is for **evaluation** purposes, participants should download cited dataset for training. Follow the instructions below.

To mitigate overfitting and promote generalization, participants could build training datasets using publicly available resources based on video format, such as ETRI-Activity3D [1], MUVIM [2], and ToyotaSmartHome [3]. However, some datasets require submitting a request before they can be downloaded.

Participants are not restricted to these datasets and are welcome to curate extensive datasets, combining multiple sources. A detailed report outlining the datasets used and their preparation and curation processes is mandatory.

Data Curation and Categorization
Participants must group activities into the following categories for efficient organization and analysis. The model output should also show categories and activities.

| **Category**          | **Actions**                                                                                                     |
|------------------------|-----------------------------------------------------------------------------------------------------------------|
| **Locomotion**         | walking, walking, entering a space, leaving a space, sitting, standing, sitting down, getting up, lying down    |
| **Manipulation**       | cooking, making coffee, making tea, wiping table, spreading bedding/folding bedding, cleaning dishes, vacuuming, looking for something, putting on/taking off shoes, putting on/taking off glasses, cleaning, writing |
| **Communication**      | talking, beckoning, waving a hand, clapping, pointing, shaking hands, phone calls, using a telephone, hugging   |
| **Hygiene**            | washing face, washing hands, brushing teeth, brushing hair, massaging a shoulder oneself, taking medicine       |
| **Eating_Drinking**    | eating, drinking                                                                                               |
| **Leisure**            | watching tv, reading, using a laptop, using a tablet, exercising                                               |


References
[1] Jang, J., Kim, D., Park, C., Jang, M., Lee, J., & Kim, J. (2020). ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly. arXiv:2003.01920

[2] Denkovski, S., Khan, S. S., Malamis, B., Moon, S. Y., Ye, B., & Mihailidis, A. (2022). Multi Visual Modality Fall Detection Dataset. arXiv:2206.12740

[3] R. Dai, S. Das, S. Sharma, L. Minciullo, L. Garattoni, F. Bremond, and G. Francesca, Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection, arXiv preprint arXiv:2010.14982, 2022. [Online]. Available: https://arxiv.org/abs/2010.14982