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
Book ChapterDOI
Deep Representations to Model User ‘Likes’
TL;DR: This work presents a deep bi-modal knowledge representation of images based on their visual content and associated tags (text) and a mapping step between the different levels of visual and textual representations allows for the transfer of semantic knowledge between the two modalities.
Posted Content
Transfer Hashing with Privileged Information
TL;DR: Transfer Hashing with Privileged Information (THPI) as discussed by the authors extends the standard learning to hash method, Iterative Quantization (ITQ), in a transfer learning manner, namely ITQ+, where a new slack function is learned from auxiliary data to approximate the quantization error.
Posted Content
Deep Learning from Noisy Image Labels with Quality Embedding
TL;DR: Li et al. as mentioned in this paper proposed a contrastive-additive noise network (CAN) which consists of two important layers: (1) the contrastive layer estimates the quality variable in the embedding space to reduce noise effect; and (2) the additive layer aggregates the prior predictions and noisy labels as the posterior to train the classifier.
Journal ArticleDOI
Exploratory analysis of cell-based screening data for phenotype identification in drug-siRNA study.
TL;DR: The method to eliminate phenotype-labelling requirement and GUI visualisation to facilitate parameter-setting for phenotypes refinement is presented, and an auto-merging procedure to reduce phenotype redundancy is introduced.
Posted Content
N-ary Error Correcting Coding Scheme.
TL;DR: This paper presents a novel N-ary coding scheme that decomposes the original multi-class problem into simpler multi- class subproblems, which is similar to applying a divide-and-conquer method and shows that the proposed coding scheme achieves superior prediction performance over the state-of-the-art coding methods.