858 citations
- The University of AdelaideAU53 papers
- The University of SydneyAU40 papers
- Australian National UniversityAU38 papers
- Queensland University of TechnologyAU28 papers
- Data61AU14 papers
- Monash UniversityAU10 papers
- University of Technology SydneyAU9 papers
- Commonwealth Scientific and Industrial Research OrganisationAU7 papers
- Northwestern Polytechnical UniversityCN7 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- The University of QueenslandAU4 papers
- Vision AustraliaAU4 papers
14 papers · 2 filters
Scalable Deep -Subspace Clustering
Tong Zhang, Pan Ji, Mehrtash Harandi +2
Subspace clustering algorithms are notorious for their scalability issues because building and processing large affinity matrices are demanding. In this paper, we introduce a metho…
Phase-only Image Based Kernel Estimation for Single-image Blind Deblurring
Liyuan Pan, Richard Hartley, Miaomiao Liu +1
The image blurring process is generally modelled as the convolution of a blur kernel with a latent image. Therefore, the estimation of the blur kernel is essentially important for…
Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition
Hui Li, Peng Wang, Chunhua Shen +1
Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion. Most existing approac…
Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks
Zhibin Liao, Tom Drummond, Ian Reid +1
In this paper, we introduce a novel methodology for characterising the performance of deep learning networks (ResNets and DenseNet) with respect to training convergence and general…
3D Geometry-Aware Semantic Labeling of Outdoor Street Scenes
Yiran Zhong, Yuchao Dai, Hongdong Li
This paper is concerned with the problem of how to better exploit 3D geometric information for dense semantic image labeling. Existing methods often treat the available 3D geometry…
Open-World Stereo Video Matching with Deep RNN
Yiran Zhong, Hongdong Li, Yuchao Dai
Deep Learning based stereo matching methods have shown great successes and achieved top scores across different benchmarks. However, like most data-driven methods, existing deep st…