activity
20182022
most citedUnsupervised Deep Features for Privacy Image Classification

15 citations · 55 across the 22 of their papers we have counts for

collaborators

32 papers

cs.CV20221 cited

Graph Classification via Discriminative Edge Feature Learning

Yang Yi, Xuequan Lu, Shang Gao +2

Spectral graph convolutional neural networks (GCNNs) have been producing encouraging results in graph classification tasks. However, most spectral GCNNs utilize fixed graphs when a…

cs.CV20221 cited

SPCNet: Stepwise Point Cloud Completion Network

Fei Hu, Honghua Chen, Xuequan Lu +5

How will you repair a physical object with large missings? You may first recover its global yet coarse shape and stepwise increase its local details. We are motivated to imitate th…

cs.CV20222 cited

CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping

Jilan Xu, Junlin Hou, Yuejie Zhang +5

Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a clas…

eess.IV2022

AI-based Carcinoma Detection and Classification Using Histopathological Images: A Systematic Review

Swathi Prabhua, Keerthana Prasada, Antonio Robels-Kelly +1

Histopathological image analysis is the gold standard to diagnose cancer. Carcinoma is a subtype of cancer that constitutes more than 80% of all cancer cases. Squamous cell carcino…

eess.IV2022

3D Intracranial Aneurysm Classification and Segmentation via Unsupervised Dual-branch Learning

Di Shao, Xuequan Lu, Xiao Liu

Intracranial aneurysms are common nowadays and how to detect them intelligently is of great significance in digital health. While most existing deep learning research focused on me…

cs.CV20221 cited

Towards Uniform Point Distribution in Feature-preserving Point Cloud Filtering

Shuaijun Chen, Jinxi Wang, Wei Pan +3

As a popular representation of 3D data, point cloud may contain noise and need to be filtered before use. Existing point cloud filtering methods either cannot preserve sharp featur…