I
Ivor W. Tsang
Researcher at University of Technology, Sydney
Publications - 361
Citations - 22076
Ivor W. Tsang is an academic researcher from University of Technology, Sydney. The author has contributed to research in topics: Computer science & Support vector machine. The author has an hindex of 64, co-authored 322 publications receiving 18649 citations. Previous affiliations of Ivor W. Tsang include Hong Kong University of Science and Technology & Agency for Science, Technology and Research.
Papers
More filters
Journal Article
Differential-Critic GAN: Generating What You Want by a Cue of Preferences
TL;DR: Differential-Critic Generative Adversarial Network (DiCGAN) as mentioned in this paper introduces a differential critic that can learn the preference direction from the pairwise preferences over the entire dataset.
Journal Article
TRIP: Refining Image-to-Image Translation via Rival Preferences
TL;DR: TRIP as discussed by the authors uses adversarial ranking to refine image-to-image translation via a generator and a ranker, which can generate high-fidelity images which exhibit smooth changes with the strength of the attributes.
Posted Content
Efficiently Learning Nonlinear Classifiers for Domain Specific Performance Measures
TL;DR: In this paper, rather than learning the needed classifier by optimizing the concerned performance measure directly, a new framework ELperf is proposed to circumvent this problem, and it is shown that EL perf is effective and efficient in training classifiers that optimize performance measures, and even its classifier adaptation procedure is more efficient than linear SVMperf.
Proceedings ArticleDOI
An Empirical Study of Code Deobfuscations on Detecting Obfuscated Android Piggybacked Apps
TL;DR: In this paper, the authors conduct an empirical study of code deobfuscations on detecting obfuscated Android piggybacked apps, focusing on three types of malware detectors: commercial anti-malware products, machine learning based detectors, and similarity-based detectors.
Proceedings ArticleDOI
Infinite Decision Agent Ensemble Learning System for Credit Risk Analysis
TL;DR: The proposed Infinite DEcision Agent ensemble Learning (IDEAL) system can achieve better performance in term of sensitivity, specificity and overall accuracy in credit risk analysis.