1. D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation
2. Representation Learning via Global Temporal Alignment and Cycle-Consistency
3. On the potential of simple framewise approaches to piano transcription;kelz;Proc Int Soc Music Information Retrieval Conf (ISMIR),2016
4. Onsets and frames: Dual-objective piano transcription;hawthorne;Proc Int Soc Music Information Retrieval Conf (ISMIR),2018
5. Soft-DTW: a differentiable loss function for time-series;cuturi;Proc Int Conf Machine Learning (ICML),2017