Luyao Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Luyao Liu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Zi Huang
The University of Queensland, Brisbane, Queensland, Australia
4 shared publications - Fumin Shen
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications - Lei Zhu
Tongji University, Shanghai, China
2 shared publications - Zheng Zhang
University of California Santa Barbara
2 shared publications Fumin Shen
UESTC
1 shared publication- Guangming Lu
Harbin Institute of Technology, Shenzhen, Shenzhen, China
1 shared publication
Latest Publications
- 1 November 2021
- Published by University of Queensland Library
Towards efficient similarity search with semantic hashing techniques
The University of Queensland's institutional repository, UQ eSpace, aims to create global visibility and accessibility of UQ’s scholarly research.
- 1 November 2021
- Published by University of Queensland Library
Towards efficient similarity search with semantic hashing techniques
The University of Queensland's institutional repository, UQ eSpace, aims to create global visibility and accessibility of UQ’s scholarly research.
- 9 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32 (10) , 4514-4528
Inductive Structure Consistent Hashing via Flexible Semantic Calibration
Semantic-preserving hashing establishes efficient multimedia retrieval by transferring knowledge from original data to hash codes so that the latter can preserve the underlying visual and semantic similarities. However, it becomes a crucial bottleneck: how to effectively bridge the trilateral domain gaps (i.e., the visual, semantic, and hashing spaces) to further improve the retrieval accuracy. In this article, we propose an inductive structure consistent hashing (ISCH) method, which can interactively coordinate the semantic correlations between the visual feature space, the binary class space, and the discrete hashing space. Specifically, an inductive semantic space is formulated by a simple multilayer stacking class-encoder, which transforms the naive class information into flexible semantic embeddings. Meanwhile, we design a semantic dictionary learning model to facilitate the bilateral visual-semantic bridging and guide the class-encoder toward reliable semantics, which could well alleviate the visual-semantic bias problem. In particular, the visual descriptors and respective semantic class representations are regularized with a coinciding alignment module. In order to generate privileged hash codes, we further explore semantic and prototype binary code learning to jointly quantify the semantic and latent visual representations into unified discrete hash codes. Moreover, an efficient optimization algorithm is developed to address the resulting discrete programming problem. Comprehensive experiments conducted on four large-scale data sets, i.e., CIFAR-10, NUSWIDE, ImageNet, and MSCOCO, demonstrate the superiority of our method over the state-of-the-art alternatives against different evaluation protocols.
- 9 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32 (10) , 4514-4528
Inductive Structure Consistent Hashing via Flexible Semantic Calibration
Semantic-preserving hashing establishes efficient multimedia retrieval by transferring knowledge from original data to hash codes so that the latter can preserve the underlying visual and semantic similarities. However, it becomes a crucial bottleneck: how to effectively bridge the trilateral domain gaps (i.e., the visual, semantic, and hashing spaces) to further improve the retrieval accuracy. In this article, we propose an inductive structure consistent hashing (ISCH) method, which can interactively coordinate the semantic correlations between the visual feature space, the binary class space, and the discrete hashing space. Specifically, an inductive semantic space is formulated by a simple multilayer stacking class-encoder, which transforms the naive class information into flexible semantic embeddings. Meanwhile, we design a semantic dictionary learning model to facilitate the bilateral visual-semantic bridging and guide the class-encoder toward reliable semantics, which could well alleviate the visual-semantic bias problem. In particular, the visual descriptors and respective semantic class representations are regularized with a coinciding alignment module. In order to generate privileged hash codes, we further explore semantic and prototype binary code learning to jointly quantify the semantic and latent visual representations into unified discrete hash codes. Moreover, an efficient optimization algorithm is developed to address the resulting discrete programming problem. Comprehensive experiments conducted on four large-scale data sets, i.e., CIFAR-10, NUSWIDE, ImageNet, and MSCOCO, demonstrate the superiority of our method over the state-of-the-art alternatives against different evaluation protocols.
- 16 March 2020
- Published by Springer Nature in Neural Processing Letters
- Vol. 52 (3) , 1765-1791
Flexible Discrete Multi-view Hashing with Collective Latent Feature Learning
- 16 March 2020
- Published by Springer Nature in Neural Processing Letters
- Vol. 52 (3) , 1765-1791
Flexible Discrete Multi-view Hashing with Collective Latent Feature Learning
- Open Access
- 3 November 2018
- Published by Springer Nature in Data Science and Engineering
- Vol. 3 (4) , 307-322
Learning Discrete Hashing Towards Efficient Fashion Recommendation
- 3 November 2018
- Published by Springer Nature in Data Science and Engineering
- Vol. 3 (4) , 307-322
Open AccessLearning Discrete Hashing Towards Efficient Fashion Recommendation
- 13 May 2018
- Published by Springer Nature
- p. 116-132
Discrete Binary Hashing Towards Efficient Fashion Recommendation
- 13 May 2018
- Published by Springer Nature
- p. 116-132
Discrete Binary Hashing Towards Efficient Fashion Recommendation
- 20 September 2017
- Published by Springer Nature
- p. 110-122
Learning Robust Graph Hashing for Efficient Similarity Search
- 20 September 2017
- Published by Springer Nature
- p. 110-122
Learning Robust Graph Hashing for Efficient Similarity Search