Research map / 3D vision / Human pose estimation
Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals
Yuto Shibata, Yutaka Kawashima, Mariko Isogawa, Go Irie, Akisato Kimura, Yoshimitsu Aoki
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 |
|---|---|---|---|
| use the proposed acoustic pose estimator rather than the strongest baseline | 3D pose estimation from low-level acoustic signals · Anechoic chamber, cross subject | RMSE: 0.83 -> 0.73 | Improved |
| use the proposed acoustic pose estimator rather than the strongest baseline | 3D pose estimation from low-level acoustic signals · Classroom, cross subject | PCKh@0.5: 0.68 -> 0.67 | Hurt |
| add the subject discriminator module (ablation) | proposed pose estimator · Anechoic chamber, cross subject | RMSE: 0.79 -> 0.73 | Improved |
| add the subject discriminator module (ablation) | proposed pose estimator · Classroom, cross subject | RMSE: 0.98 -> 0.97 | No clear effect |
| add the intensity vector (ablation) | proposed pose estimator · Anechoic chamber, cross subject | RMSE: 0.77 -> 0.73 | Improved |
| add the intensity vector (ablation) | proposed pose estimator · Classroom, cross subject | RMSE: 0.93 -> 0.97 | Hurt |
| use standard deviation loss instead of discriminator loss Ld (ablation) | subject discriminator module · Anechoic chamber, cross subject | RMSE: 0.78 -> 0.73 | Improved |
| extract features at 20 fps rather than 30 or 40 fps (ablation) | proposed pose estimator · Anechoic chamber, cross subject | PCKh@0.5: 0.68 -> 0.72; 0.66 -> 0.72 | Improved |
| use the intensity vector (ablation) | proposed pose estimator · Anechoic chamber, cross subject | PCKh@0.5: 0.68 -> 0.72 | Improved |
Closest papers by meaning
- Sound-based Multi-Person 3D Pose Estimation (ECCV 2026 · similarity 0.91)
- Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio (NeurIPS 2023 · similarity 0.90)
- Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes (CVPR 2025 · similarity 0.86)
- Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild (AAAI 2024 · similarity 0.85)
- ChatHuman: Chatting about 3D Humans with Tools (CVPR 2025 · similarity 0.85)
- FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions (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.
