Weiqing Huang
Chinese Academy of Sciences
102 Papers
156 Citations
Weiqing Huang is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Computer science & Spectral centroid. The author has an hindex of 7, co-authored 91 publications. Previous affiliations of Weiqing Huang include Beijing Jiaotong University.
Chat about Author
Papers
Restoration as a Defense Against Adversarial Perturbations for Spam Image Detection
Jianguo Jiang,Boquan Li,Min Yu,Chao Liu,Weiqing Huang,Lejun Fan,Jianfeng Xia +6 more
- 17 Sep 2019
TL;DR: Zhang et al. as discussed by the authors applied image restoration as a defense against adversarial perturbations, which focuses on restoring the perturbed adversarial images to their original versions by a lightweight preprocessing network, which takes the adversarial image as input and outputs their restored versions for classification.
3
Patent
Spectral centroid based automatic detection method and system for video leakage signal
Degang Sun,Jun Shi,Dong Wei,Meng Zhang,Weiqing Huang +4 more
- 29 Apr 2015
TL;DR: In this paper, a spectral centroid based automatic detection method for a video leakage signal is proposed, which comprises steps as follows: acquiring a power spectrum of an observed signal and dividing the power spectrum into a plurality of sub-bands; acquiring a spectral center of each sub-band and acquiring a spectrum centroid interval of each Sub-band; judging whether the signal is the video leakage or not according to the uniformity degree of the spectral center interval distribution of the signal.
2
AMQAN: Adaptive Multi-Attention Question-Answer Networks for Answer Selection
Haitian Yang,Weiqing Huang,Xuan Zhao,Yan Wang,Yuyan Chen,Bin Lv,Rui Mao,Ning Li +7 more
- 14 Sep 2020
TL;DR: AMQAN as mentioned in this paper proposes an adaptive multi-attention question-answer network with embeddings at different levels, which makes comprehensive use of semantic information in questions and answers, and alleviates the noise issue at the same time.
2
PEPC: A Deep Parallel Convolutional Neural Network Model with Pre-trained Embeddings for DGA Detection
Weiqing Huang,Yangyang Zong,Zhixin Shi,Leiqi Wang,Pengcheng Liu +4 more
- 18 Jul 2022
TL;DR: This paper proposes a deep learning model, called PEPC, to detect and classify DGA domain names with only a small dataset, which consists of the pre-trained embeddings (PTE) module to quantify domain names to numeric vectors and the deep parallel convolutional neural networks (DPCNN) modules to better extract features of vectors for prediction.
2