2 papers
cs.CV2026
Skeletonization-Based Adversarial Perturbations on Large Vision Language Model's Mathematical Text Recognition
Masatomo Yoshida, Haruto Namura, Nicola Adami +1
This work explores the visual capabilities and limitations of foundation models by introducing a novel adversarial attack method utilizing skeletonization to reduce the search spac…
cs.SD2024
Spectrogram-Based Detection of Auto-Tuned Vocals in Music Recordings
Mahyar Gohari, Paolo Bestagini, Sergio Benini +1
In the domain of music production and audio processing, the implementation of automatic pitch correction of the singing voice, also known as Auto-Tune, has significantly transforme…