Generative Resident Separation and Multi-label Classification for Multi-person Activity Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910405946769408 |
|---|---|
| author | Chen, Xi Cumin, Julien Ramparany, Fano Vaufreydaz, Dominique |
| author_facet | Chen, Xi Cumin, Julien Ramparany, Fano Vaufreydaz, Dominique |
| contents | This paper presents two models to address the problem of multi-person activity recognition using ambient sensors in a home. The first model, Seq2Res, uses a sequence generation approach to separate sensor events from different residents. The second model, BiGRU+Q2L, uses a Query2Label multi-label classifier to predict multiple activities simultaneously. Performances of these models are compared to a state-of-the-art model in different experimental scenarios, using a state-of-the-art dataset of two residents in a home instrumented with ambient sensors. These results lead to a discussion on the advantages and drawbacks of resident separation and multi-label classification for multi-person activity recognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07245 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generative Resident Separation and Multi-label Classification for Multi-person Activity Recognition Chen, Xi Cumin, Julien Ramparany, Fano Vaufreydaz, Dominique Machine Learning Artificial Intelligence Signal Processing This paper presents two models to address the problem of multi-person activity recognition using ambient sensors in a home. The first model, Seq2Res, uses a sequence generation approach to separate sensor events from different residents. The second model, BiGRU+Q2L, uses a Query2Label multi-label classifier to predict multiple activities simultaneously. Performances of these models are compared to a state-of-the-art model in different experimental scenarios, using a state-of-the-art dataset of two residents in a home instrumented with ambient sensors. These results lead to a discussion on the advantages and drawbacks of resident separation and multi-label classification for multi-person activity recognition. |
| title | Generative Resident Separation and Multi-label Classification for Multi-person Activity Recognition |
| topic | Machine Learning Artificial Intelligence Signal Processing |
| url | https://arxiv.org/abs/2404.07245 |