← Search

Dongxin Liu

2 accepted papers

2023

FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space

NeurIPS 2023poster

This paper proposes a novel contrastive learning framework, called FOCAL, for extracting comprehensive features from multimodal time-series sensing signals through self-supervised training. Existing multimodal contrastive frameworks mostly rely on the shared information between sensory modalities, b…

2020

ControlVAE: Controllable Variational Autoencoder

ICML 2020poster

Variational Autoencoders (VAE) and their variants have been widely used in a variety of applications, such as dialog generation, image generation and disentangled representation learning. However, the existing VAE models may suffer from KL vanishing in language modeling and low reconstruction qualit…

Cited by 137SourcePDFScholar