Search Results for author: Bin Zhu

Found 13 papers, 2 papers with code

TREATED:Towards Universal Defense against Textual Adversarial Attacks

no code implementations13 Sep 2021 Bin Zhu, Zhaoquan Gu, Le Wang, Zhihong Tian

Recent work shows that deep neural networks are vulnerable to adversarial examples.

Adversarial Defense

Transferable Adversarial Examples for Anchor Free Object Detection

no code implementations3 Jun 2021 Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu, Bin Zhu, Youbing Yin, Qi Song, Xi Wu

Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result.

Adversarial Attack Object Detection

Imperceptible Adversarial Examples for Fake Image Detection

no code implementations3 Jun 2021 Quanyu Liao, Yuezun Li, Xin Wang, Bin Kong, Bin Zhu, Siwei Lyu, Youbing Yin, Qi Song, Xi Wu

Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society.

Face Swapping Fake Image Detection

Pyramid Fusion Dark Channel Prior for Single Image Dehazing

no code implementations21 May 2021 Qiyuan Liang, Bin Zhu, Chong-Wah Ngo

In this paper, we propose the pyramid fusion dark channel prior (PF-DCP) for single image dehazing.

Image Dehazing Single Image Dehazing

An Optimized H.266/VVC Software Decoder On Mobile Platform

no code implementations5 Mar 2021 Yiming Li, Shan Liu, Yu Chen, Yushan Zheng, Sijia Chen, Bin Zhu, Jian Lou

As the successor of H. 265/HEVC, the new versatile video coding standard (H. 266/VVC) can provide up to 50% bitrate saving with the same subjective quality, at the cost of increased decoding complexity.

A new strong bound on sub-GeV dark matter from Migdal effect

no code implementations17 Dec 2020 Victor V. Flambaum, Liangliang Su, Lei Wu, Bin Zhu

Migdal effect provides a new way to search for sub-GeV dark matter.

High Energy Physics - Phenomenology Cosmology and Nongalactic Astrophysics

Line Spectrum Representation for Vector Processes With Application to Frequency Estimation

no code implementations24 Jun 2020 Bin Zhu

A positive semidefinite Toeplitz matrix, which often arises as the finite covariance matrix of a stationary random process, can be decomposed as the sum of a nonnegative multiple of the identity corresponding to a white noise, and a singular term corresponding to a purely deterministic process.

Time Series

CookGAN: Causality Based Text-to-Image Synthesis

no code implementations CVPR 2020 Bin Zhu, Chong-Wah Ngo

Particularly, a cooking simulator sub-network is proposed to incrementally make changes to food images based on the interaction between ingredients and cooking methods over a series of steps.

Image Generation

CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection

1 code implementation7 Mar 2020 Bin Zhu, Qing Song, Lu Yang, Zhihui Wang, Chun Liu, Mengjie Hu

In object detection, offset-guided and point-guided regression dominate anchor-based and anchor-free method separately.

Object Detection

An Empirical Bayes Approach to Frequency Estimation

no code implementations21 Oct 2019 Giorgio Picci, Bin Zhu

In this paper we show that the classical problem of frequency estimation can be formulated and solved efficiently in an empirical Bayesian framework by assigning a uniform a priori probability distribution to the unknown frequency.

R2GAN: Cross-Modal Recipe Retrieval With Generative Adversarial Network

no code implementations CVPR 2019 Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Yanbin Hao

Representing procedure text such as recipe for crossmodal retrieval is inherently a difficult problem, not mentioning to generate image from recipe for visualization.

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