activity
20192021
most citedConservative Wasserstein Training for Pose Estimation

16 citations · 41 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV2021

Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation

Xiaofeng Liu, Site Li, Yubin Ge +3

The unsupervised domain adaptation (UDA) has been widely adopted to alleviate the data scalability issue, while the existing works usually focus on classifying independently discre…

cs.CV2021

Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate

Xiaofeng Liu, Zhenhua Guo, Site Li +5

In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r…

cs.CV2021

Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization

Yubin Ge, Site Li, Xuyang Li +4

The widely-used cross-entropy (CE) loss-based deep networks achieved significant progress w.r.t. the classification accuracy. However, the CE loss can essentially ignore the risk o…

cs.CV20218 cited

Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis

Xiaofeng Liu, Xiongchang Liu, Bo Hu +7

Recent advances in unsupervised domain adaptation (UDA) show that transferable prototypical learning presents a powerful means for class conditional alignment, which encourages the…

cs.CV20212 cited

Identity-aware Facial Expression Recognition in Compressed Video

Xiaofeng Liu, Linghao Jin, Xu Han +3

This paper targets to explore the inter-subject variations eliminated facial expression representation in the compressed video domain. Most of the previous methods process the RGB…

cs.CV20213 cited

Energy-constrained Self-training for Unsupervised Domain Adaptation

Xiaofeng Liu, Bo Hu, Xiongchang Liu +3

Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-t…