2 papers
cs.LG2026
Rotary Masked Autoencoders are Versatile Learners
Uros Zivanovic, Serafina Di Gioia, Andre Scaffidi +3
Applying Transformers to irregular time-series typically requires specializations to their baseline architecture, which can result in additional computational overhead and increase…
cs.CV2025
Pay Attention to the Keys: Visual Piano Transcription Using Transformers
Uros Zivanovic, Ivan Pilkov, Carlos Eduardo Cancino-Chacón
Visual piano transcription (VPT) is the task of obtaining a symbolic representation of a piano performance from visual information alone (e.g., from a top-down video of the piano k…