Seonglae Chosegment-level에서 feature를 집계
입력 데이터 내에서 고수준 특징들의 시간 정보를 더 잘 보존
Learnable Dynamic Temporal Pooling for Time Series Classification
With the increase of available time series data, predicting their class labels has been one of the most important challenges in a wide range of disciplines. Recent studies on time series...
https://arxiv.org/abs/2104.02577
