Research map / Video / Action recognition
Toyota Smarthome: Real-World Activities of Daily Living
Srijan Das, Rui Dai, Michal Koperski, Luca Minciullo, Lorenzo Garattoni, Francois Bremond, Gianpiero Francesca
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 separable spatio-temporal attention (ablation) | I3D · NTU-CS | accuracy: 85.5 -> 92.2 | Improved |
| add separable spatio-temporal attention (ablation) | I3D · NTU-CV | accuracy: 87.3 -> 94.6 | Improved |
| add separable spatio-temporal attention (ablation) | I3D · NUCLA | accuracy: 85.5 -> 92.5 | Improved |
| add separable spatio-temporal attention (ablation) | I3D · Smarthome cross-subject | accuracy: 72 -> 75.3 | Improved |
| add separable spatio-temporal attention (ablation) | I3D · Smarthome cross-view CV1 | accuracy: 56.6 -> 61 | Improved |
| add separable spatio-temporal attention (ablation) | I3D · Smarthome cross-view CV2 | accuracy: 61.6 -> 68.2 | Improved |
| add spatial attention alone (ablation) | I3D · Smarthome cross-view CV1 | accuracy: 56.6 -> 60.3 | Improved |
| add temporal attention alone (ablation) | I3D · Smarthome cross-view CV1 | accuracy: 56.6 -> 43 | Hurt |
| add temporal attention alone (ablation) | I3D · NUCLA | accuracy: 85.5 -> 79.3 | Hurt |
| add temporal attention alone (ablation) | I3D · NTU-CS | accuracy: 85.5 -> 90.8 | Improved |
| couple temporal attention after spatial attention (SA+TA) instead of separable (ablation) | Separable STA · NUCLA | accuracy: 92.5 -> 74.6 | Hurt |
| couple spatial after temporal attention (TA+SA) instead of separable (ablation) | Separable STA · Smarthome cross-view CV1 | accuracy: 61 -> 40.9 | Hurt |
Closest papers by meaning
- Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection (TPAMI 2022 · similarity 0.91)
- VPN: Learning Video-Pose Embedding for Activities of Daily Living (ECCV 2020 · similarity 0.87)
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (CVPR 2016 · similarity 0.86)
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (TPAMI 2019 · similarity 0.86)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.85)
- LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living (CVPR 2025 · similarity 0.82)
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.
