activity
20182023
most cited3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes

207 citations · 466 across the 18 of their papers we have counts for

collaborators
Showing 2021Show all

5 papers · 1 filter

cs.CV2021★ 1 cited

MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution

Chenyu You, Lianyi Han, Aosong Feng +3

Space-time video super-resolution (STVSR) aims to construct a high space-time resolution video sequence from the corresponding low-frame-rate, low-resolution video sequence. Inspir…

cs.CV2021

Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds

Longkun Zou, Hui Tang, Ke Chen +1

The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to d…

cs.CV2021★ 19 cited

Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images

Jingru Yi, Pengxiang Wu, Hui Tang +7

Instance segmentation is of great importance for many biological applications, such as study of neural cell interactions, plant phenotyping, and quantitatively measuring how cells…

cs.LG2021★ 8 cited

On Universal Black-Box Domain Adaptation

Bin Deng, Yabin Zhang, Hui Tang +2

In this paper, we study an arguably least restrictive setting of domain adaptation in a sense of practical deployment, where only the interface of source model is available to the…

cs.CV2021★ 18 cited

Vicinal and categorical domain adaptation

Hui Tang, Kui Jia

Unsupervised domain adaptation aims to learn a task classifier that performs well on the unlabeled target domain, by utilizing the labeled source domain. Inspiring results have bee…