484 citations
- National University of SingaporeSG7 papers
- Chinese Academy of SciencesCN3 papers
- University of Chinese Academy of SciencesCN3 papers
- Beijing Academy of Artificial IntelligenceCN1 paper
- Beijing Information Science & Technology UniversityCN1 paper
- Carnegie Mellon UniversityUS1 paper
- Hefei University of TechnologyCN1 paper
- Institute of SoftwareCN1 paper
- Meta (United States)US1 paper
- National Polytechnic University of ArmeniaAM1 paper
- Peking UniversityCN1 paper
- Search-Lab (Hungary)HU1 paper
5 papers · 1 filter
Security Risks in Deep Learning Implementations
Qixue Xiao, Kang Li, Deyue Zhang +1
Advance in deep learning algorithms overshadows their security risk in software implementations. This paper discloses a set of vulnerabilities in popular deep learning frameworks i…
Using Argument-based Features to Predict and Analyse Review Helpfulness
Haijing Liu, Yang Gao, Pin Lv +4
We study the helpful product reviews identification problem in this paper. We observe that the evidence-conclusion discourse relations, also known as arguments, often appear in pro…
A Location-Sentiment-Aware Recommender System for Both Home-Town and Out-of-Town Users
Hao Wang, Yanmei Fu, Qinyong Wang +3
Spatial item recommendation has become an important means to help people discover interesting locations, especially when people pay a visit to unfamiliar regions. Some current rese…
Softmax GAN
Min Lin
Softmax GAN is a novel variant of Generative Adversarial Network (GAN). The key idea of Softmax GAN is to replace the classification loss in the original GAN with a softmax cross-e…
Training Group Orthogonal Neural Networks with Privileged Information
Yunpeng Chen, Xiaojie Jin, Jiashi Feng +1
Learning rich and diverse representations is critical for the performance of deep convolutional neural networks (CNNs). In this paper, we consider how to use privileged information…