Metraipolis › archive › dc_6f5eaaa47814
KeyWise: Efficient Video-Only Piano Transcription with a Lightweight Per-Key Architecture — arXiv:2611.04476
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04476
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:55:55.184Z
- SHA-256 of the archived text
d7ec4f60abc9630c14931c7d0dd3081f428c3b61517bc43115bb4cb01fd4a4df- Stable URL of this page
https://metraipolis.com/documento/dc_6f5eaaa47814
How to cite
KeyWise: Efficient Video-Only Piano Transcription with a Lightweight Per-Key Architecture — arXiv:2611.04476 — arXiv (en), https://arxiv.org/abs/2611.04476 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6f5eaaa47814 (Metraipolis archive dc_6f5eaaa47814, sha256 d7ec4f60abc9630c14931c7d0dd3081f428c3b61517bc43115bb4cb01fd4a4df)
BibTeX
@misc{dc6f5eaaa47814,
title = {KeyWise: Efficient Video-Only Piano Transcription with a Lightweight Per-Key Architecture — arXiv:2611.04476},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04476},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6f5eaaa47814; sha256 d7ec4f60abc9630c14931c7d0dd3081f428c3b61517bc43115bb4cb01fd4a4df},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04476. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Audio-based piano transcription is hampered by the sustain pedal and by noisy or missing soundtracks, problems that video-only transcription avoids, since a top-view video shows directly when each key is pressed and released. Most visual transcription networks, however, describe the whole keyboard with one global feature vector and must learn where each key is. In this paper, we propose KeyWise, a lightweight per-key architecture that exploits the known geometry of the keyboard instead of learning it. The rectified keyboard is divided into 88 equal tiles that serve as regions of interest (ROIs), and one small recurrent network, shared by all keys, follows each key over time. On PianoVAM, KeyWise reaches the onset accuracy of the state-of-the-art V2N (95.0% vs. 94.7% onset F1 at 50 ms and 97.8% vs. 97.0% at 100 ms) with 1.3 M instead of 28.2 M parameters, and it runs 4.7 times faster on the same GPU. At 100 ms, it is also significantly more accurate when the key releases (97.0% vs. 95.5% F1) or the velocities (89.4% vs. 84.5% F1) must be correct as well. On PianoYT, KeyWise pre-trained on PianoVAM reaches 69.4% onset F1 at 100 ms, comparable to the best published result, although it needs fine-tuning for new recording conditions. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.04476 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T18:35:37.532Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).