Recognition of Daily Activities Through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living
Kooshan Hashemifard, Pau Climent-Pérez, Francisco Florez-Revuelta · 2026
Read Recognition of Daily Activities Through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living by Kooshan Hashemifard, Pau Climent-Pérez, Francisco Florez-Revuelta (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13522300.txt.
Description
Kooshan Hashemifard, Pau Climent-Pérez and Francisco Florez-Revuelta fuse in 2026 video, body pose and object context to spot daily acts of older adults at home. The goal is home support that guards safety yet keeps self rule.
One network reads motion from video in three dims. A graph network reads skeleton pose over time. An object spotter adds scene context through weighted fusion. Tests used a public smart-home set of real indoor acts. Accuracy stayed strong across varied acts. Look-alike acts, shifted cameras and cluttered rooms tested the system hard. Home safety platforms are the target use.
Catalog record
| CREATOR | Kooshan Hashemifard, Pau Climent-Pérez, Francisco Florez-Revuelta |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 98334 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |