2 papers
cs.CV2025
Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization
Han Guo, Ramtin Hosseini, Ruiyi Zhang +4
Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing the…
eess.SP2024
UniMTS: Unified Pre-training for Motion Time Series
Xiyuan Zhang, Diyan Teng, Ranak Roy Chowdhury +4
Motion time series collected from mobile and wearable devices such as smartphones and smartwatches offer significant insights into human behavioral patterns, with wide applications…