activity
20162022
most citedRotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation

5 citations · 11 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV2022

An Iterative Co-Training Transductive Framework for Zero Shot Learning

Bo Liu, Lihua Hu, Qiulei Dong +1

In zero-shot learning (ZSL) community, it is generally recognized that transductive learning performs better than inductive one as the unseen-class samples are also used in its tra…

cs.CV2022

Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector

Bo Liu, Qiulei Dong, Zhanyi Hu

Zero-shot learning (ZSL) aims to recognize objects from unseen classes, where the kernel problem is to transfer knowledge from seen classes to unseen classes by establishing approp…

cs.CV2022

Pursuing 3D Scene Structures with Optical Satellite Images from Affine Reconstruction to Euclidean Reconstruction

Pinhe Wang, Limin Shi, Bao Chen +3

How to use multiple optical satellite images to recover the 3D scene structure is a challenging and important problem in the remote sensing field. Most existing methods in literatu…

cs.CV2022★ 1 cited

HardBoost: Boosting Zero-Shot Learning with Hard Classes

Bo Liu, Lihua Hu, Zhanyi Hu +1

This work is a systematical analysis on the so-called hard class problem in zero-shot learning (ZSL), that is, some unseen classes disproportionally affect the ZSL performances tha…

cs.CV2021★ 5 cited

Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation

Shuang Deng, Bo Liu, Qiulei Dong +1

Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis. In this paper, we aim to provide…

cs.CV2021

Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds

Shuang Deng, Qiulei Dong, Bo Liu +1

3D point cloud semantic segmentation is a challenging topic in the computer vision field. Most of the existing methods in literature require a large amount of fully labeled trainin…