Metraipolis › archive › dc_b76d49ced2b4

Multi-Task Multi-Frame Visual Piano Transcription — arXiv:2608.03419

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03419
License (as archived)
CC0-1.0
Archived
2026-10-31T12:19:15.042Z
SHA-256 of the archived text
a0dd1b445ac4425b043d112fa31dfacae44f0ec832a1ebb2a2e83ccc724ceb05
Stable URL of this page
https://metraipolis.com/documento/dc_b76d49ced2b4

How to cite

Multi-Task Multi-Frame Visual Piano Transcription — arXiv:2608.03419 — arXiv (en), https://arxiv.org/abs/2608.03419 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b76d49ced2b4 (Metraipolis archive dc_b76d49ced2b4, sha256 a0dd1b445ac4425b043d112fa31dfacae44f0ec832a1ebb2a2e83ccc724ceb05)
BibTeX
@misc{dcb76d49ced2b4,
  title = {Multi-Task Multi-Frame Visual Piano Transcription — arXiv:2608.03419},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03419},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b76d49ced2b4; sha256 a0dd1b445ac4425b043d112fa31dfacae44f0ec832a1ebb2a2e83ccc724ceb05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03419. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Audio-based piano transcription performs well on onset, pitch, and velocity, but the sustain pedal lets sound persist long after key release, so audio systems predict pedal-extended offsets rather than physical key release. Yet existing Visual Piano Transcription (VPT) systems focus on onset detection from short video windows, offset accuracy lags onset by a wide margin, and note-level velocity has not been reported. To address these gaps, we present V2N (Video to Notes), the first complete VPT system: a shared temporal backbone feeds task-specific heads for onset, offset, key hold, and velocity, jointly trained with per-frame supervision rather than only at the window center. Ablations show that multi-task supervision enables offset and velocity prediction while improving onset accuracy; longer temporal context yields further improvements. V2N sets new state-of-the-art results on PianoVAM and R3.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2608.03419 — 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 2026-10-31T12:05:53.042Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).