Search Results for author: Fuqiang Liu

Found 8 papers, 1 papers with code

Energy-Efficient Clustered Cell-Free Networking with Access Point Selection

no code implementations1 Mar 2024 Ouyang Zhou, Junyuan Wang, Fuqiang Liu, Jiangzhou Wang

Ultra-densely deploying access points (APs) to support the increasing data traffic would significantly escalate the cell-edge problem resulting from traditional cellular networks.

Spatially Focused Attack against Spatiotemporal Graph Neural Networks

no code implementations10 Sep 2021 Fuqiang Liu, Luis Miranda-Moreno, Lijun Sun

However, despite that recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to carefully designed perturbations in multiple domains like objection classification and graph representation, current adversarial works cannot be directly applied to spatiotemporal forecasting due to the causal nature and spatiotemporal mechanisms in forecasting models.

Management Traffic Prediction

Polarized Self-Attention: Towards High-quality Pixel-wise Regression

6 code implementations arXiv preprint 2021 Huajun Liu, Fuqiang Liu, Xinyi Fan, Dong Huang

Pixel-wise regression is probably the most common problem in fine-grained computer vision tasks, such as estimating keypoint heatmaps and segmentation masks.

Ranked #2 on Keypoint Detection on MS COCO (Validation AP metric)

2D Pose Estimation Keypoint Detection +4

One Vertex Attack on Graph Neural Networks-based Spatiotemporal Forecasting

no code implementations1 Jan 2021 Fuqiang Liu, Luis Miranda Moreno, Lijun Sun

Empirical studies prove that perturbations in one vertex can be diffused into most of the graph when spatiotemporal GNNs are under One Vertex Attack.

Graph Classification

Towards Accurate and High-Speed Spiking Neuromorphic Systems with Data Quantization-Aware Deep Networks

no code implementations8 May 2018 Fuqiang Liu, C. Liu

However, weights and signals of DNNs are required to be quantized when deploying the DNNs on the SNC, which results in unacceptable accuracy loss.

Quantization

Object Recognition Based on Amounts of Unlabeled Data

no code implementations25 Mar 2016 Fuqiang Liu, Fukun Bi, Liang Chen

Using 2% labeled data and 98% unlabeled data, the accuracies of the proposed method on the two data sets are 78. 39% and 50. 77% respectively.

Object Object Recognition

Boost Picking: A Universal Method on Converting Supervised Classification to Semi-supervised Classification

no code implementations18 Feb 2016 Fuqiang Liu, Fukun Bi, Yiding Yang, Liang Chen

It is theoretically proved that Boost Picking could train a supervised model mainly by un-labeled data as effectively as the same model trained by 100% labeled data, only if recalls of the two weak classifiers are all greater than zero and the sum of precisions is greater than one.

Classification General Classification

Feature-Area Optimization: A Novel SAR Image Registration Method

no code implementations18 Feb 2016 Fuqiang Liu, Fukun Bi, Liang Chen, Hao Shi, Wei Liu

This letter proposes a synthetic aperture radar (SAR) image registration method named Feature-Area Optimization (FAO).

Image Registration

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