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 ArticleDOI
Guest Editorial Special Issue on Structured Multi-Output Learning: Modeling, Algorithm, Theory, and Applications
TL;DR: This paper presents a meta-modelling framework for solving structured multioutput learning problems in video analysis, image annotation/retrieval, gene function prediction, and brain science, which considers multiple structured outputs prediction for a given input.
Journal ArticleDOI
Causal Intervention for Abstractive Related Work Generation
TL;DR: Li et al. as discussed by the authors proposed a causal intervention module for related work generation (CaM) to effectively capture causalities in the generation process and improve the quality and coherence of the generated related works.
Proceedings ArticleDOI
Deep N-ary Error Correcting Output Codes
TL;DR: In this paper, the authors proposed three different variants of parameter sharing architectures for deep N-ary ECOC and evaluated their performance on both image and text classification tasks with different deep neural network architectures.
Proceedings ArticleDOI
Learning Smooth Representation for Multi-view Subspace Clustering
TL;DR: This paper proposes to achieve a smooth representation for each view and thus facilitate the downstream clustering task and achieves the smooth representation learning as well as multi-view clustering interactively in a unified framework, hence it is an end-to-end single-stage learning problem.
Posted Content
Is Matching Pursuit Solving Convex Problems
TL;DR: A novel convex relaxation model is presented, which is solved by a general matching pursuit (GMP) algorithm under the convex programming framework and achieves better performance than other methods in terms of sparse recovery ability and efficiency.