Search Results for author: Shanmin Pang

Found 13 papers, 3 papers with code

Sparse Semantic Map-Based Monocular Localization in Traffic Scenes Using Learned 2D-3D Point-Line Correspondences

no code implementations10 Oct 2022 Xingyu Chen, Jianru Xue, Shanmin Pang

The proposed sparse semantic map-based localization approach is robust against occlusion and long-term appearance changes in the environments.

Autonomous Vehicles

MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes

no code implementations CVPR 2021 Zhikai Chen, Lingxi Xie, Shanmin Pang, Yong He, Bo Zhang

This paper presents MagDR, a mask-guided detection and reconstruction pipeline for defending deepfakes from adversarial attacks.

Domain segmentation and adjustment for generalized zero-shot learning

no code implementations1 Feb 2020 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 unseen classes.

Generalized Zero-Shot Learning

Appending Adversarial Frames for Universal Video Attack

no code implementations10 Dec 2019 Zhikai Chen, Lingxi Xie, Shanmin Pang, Yong He, Qi Tian

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.

Classification General Classification +2

Visual Space Optimization for Zero-shot Learning

no code implementations30 Jun 2019 Xinsheng Wang, Shanmin Pang, Jihua Zhu, Zhongyu Li, Zhiqiang Tian, Yaochen Li

The other is to optimize the visual feature structure in an intermediate embedding space, and in this method we successfully devise a multilayer perceptron framework based algorithm that is able to learn the common intermediate embedding space and meanwhile to make the visual data structure more distinctive.

Zero-Shot Learning

Feature Concatenation Multi-view Subspace Clustering

1 code implementation30 Jan 2019 Qinghai Zheng, Jihua Zhu, Zhongyu Li, Shanmin Pang, Jun Wang, Yaochen Li

To this end, this paper proposes a novel multi-view subspace clustering approach dubbed Feature Concatenation Multi-view Subspace Clustering (FCMSC), which boosts the clustering performance by exploring the consensus information of multi-view data.

Clustering Multi-view Subspace Clustering

Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval

1 code implementation22 May 2018 Shanmin Pang, Jin Ma, Jianru Xue, Jihua Zhu, Vicente Ordonez

We show that by considering each deep feature as a heat source, our unsupervised aggregation method is able to avoid over-representation of \emph{bursty} features.

Image Retrieval Re-Ranking +1

Adaptive Co-weighting Deep Convolutional Features For Object Retrieval

no code implementations20 Mar 2018 Jiaxing Wang, Jihua Zhu, Shanmin Pang, Zhongyu Li, Yaochen Li, Xueming Qian

Aggregating deep convolutional features into a global image vector has attracted sustained attention in image retrieval.

Image Retrieval Object +1

K-means clustering for efficient and robust registration of multi-view point sets

no code implementations14 Oct 2017 Zutao Jiang, Jihua Zhu, Georgios D. Evangelidis, Changqing Zhang, Shanmin Pang, Yaochen Li

Subsequently, the shape comprised by all cluster centroids is used to sequentially estimate the rigid transformation for each point set.


Multi-view Registration Based on Weighted Low Rank and Sparse Matrix Decomposition of Motions

no code implementations25 Sep 2017 Congcong Jin, Jihua Zhu, Yaochen Li, Shanmin Pang, Lei Chen, Jun Wang

Then, it proposes the weighted LRS decomposition, where each block element is assigned with one estimated weight to denote its reliability.

Cannot find the paper you are looking for? You can Submit a new open access paper.