140 citations · 365 across the 14 of their papers we have counts for
14 papers
Sparse Semantic Map-Based Monocular Localization in Traffic Scenes Using Learned 2D-3D Point-Line Correspondences
Xingyu Chen, Jianru Xue, Shanmin Pang
Vision-based localization in a prior map is of crucial importance for autonomous vehicles. Given a query image, the goal is to estimate the camera pose corresponding to the prior m…
MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes
Zhikai Chen, Lingxi Xie, Shanmin Pang +2
Deepfakes raised serious concerns on the authenticity of visual contents. Prior works revealed the possibility to disrupt deepfakes by adding adversarial perturbations to the sourc…
Consistent and Complementary Graph Regularized Multi-view Subspace Clustering
Qinghai Zheng, Jihua Zhu, Zhongyu Li +3
This study investigates the problem of multi-view clustering, where multiple views contain consistent information and each view also includes complementary information. Exploration…
Registration of multi-view point sets under the perspective of expectation-maximization
Jihua Zhu, Jing Zhang, Huimin Lu +1
Registration of multi-view point sets is a prerequisite for 3D model reconstruction. To solve this problem, most of previous approaches either partially explore available informati…
Domain segmentation and adjustment for generalized zero-shot learning
Xinsheng Wang, Shanmin Pang, Jihua Zhu
In the generalized zero-shot learning, synthesizing unseen data with generative models has been the most popular method to address the imbalance of training data between seen and u…
Appending Adversarial Frames for Universal Video Attack
Zhikai Chen, Lingxi Xie, Shanmin Pang +2
There have been many efforts in attacking image classification models with adversarial perturbations, but the same topic on video classification has not yet been thoroughly studied…
Visual Space Optimization for Zero-shot Learning
Xinsheng Wang, Shanmin Pang, Jihua Zhu +3
Zero-shot learning, which aims to recognize new categories that are not included in the training set, has gained popularity owing to its potential ability in the real-word applicat…
Constrained Bilinear Factorization Multi-view Subspace Clustering
Qinghai Zheng, Jihua Zhu, Zhiqiang Tian +3
Multi-view clustering is an important and fundamental problem. Many multi-view subspace clustering methods have been proposed, and most of them assume that all views share a same c…
Feature Concatenation Multi-view Subspace Clustering
Qinghai Zheng, Jihua Zhu, Zhongyu Li +3
Multi-view clustering is a learning paradigm based on multi-view data. Since statistic properties of different views are diverse, even incompatible, few approaches implement multi-…
Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval
Shanmin Pang, Jin Ma, Jianru Xue +2
Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance in popular benchmarks. In this paper, we present a unified solution to address de…
Multi-view registration of unordered range scans by fast correspondence propagation of multi-scale descriptors
Jihua Zhu, Siyu Xu, Zutao Jiang +3
This paper proposes a global approach for the multi-view registration of unordered range scans. As the basis of multi-view registration, pair-wise registration is very pivotal. The…
Adaptive Co-weighting Deep Convolutional Features For Object Retrieval
Jiaxing Wang, Jihua Zhu, Shanmin Pang +3
Aggregating deep convolutional features into a global image vector has attracted sustained attention in image retrieval. In this paper, we propose an efficient unsupervised aggrega…
K-means clustering for efficient and robust registration of multi-view point sets
Zutao Jiang, Jihua Zhu, Georgios D. Evangelidis +3
Generally, there are three main factors that determine the practical usability of registration, i.e., accuracy, robustness, and efficiency. In real-time applications, efficiency an…
Multi-view Registration Based on Weighted Low Rank and Sparse Matrix Decomposition of Motions
Congcong Jin, Jihua Zhu, Yaochen Li +3
Recently, the low rank and sparse (LRS) matrix decomposition has been introduced as an effective mean to solve the multi-view registration. It views each available relative motion…