ORCID Profile
0000-0002-4756-0609
Current Organisation
University of Sydney
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Pattern Recognition and Data Mining | Artificial Intelligence and Image Processing | Computer Vision | Deep learning | Computer vision | Machine learning | Computer System Security |
Expanding Knowledge in the Information and Computing Sciences | Film and Video Services (excl. Animation and Computer Generated Imagery) | Application Tools and System Utilities
Publisher: IEEE
Date: 12-2015
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2017
Abstract: In this paper, we propose a principled Tag Disentangled Generative Adversarial Networks (TD-GAN) for re-rendering new images for the object of interest from a single image of it by specifying multiple scene properties (such as viewpoint, illumination, expression, etc.). The whole framework consists of a disentangling network, a generative network, a tag mapping net, and a discriminative network, which are trained jointly based on a given set of images that are completely artially tagged (i.e., supervised/semi-supervised setting). Given an input image, the disentangling network extracts disentangled and interpretable representations, which are then used to generate images by the generative network. In order to boost the quality of disentangled representations, the tag mapping net is integrated to explore the consistency between the image and its tags. Furthermore, the discriminative network is introduced to implement the adversarial training strategy for generating more realistic images. Experiments on two challenging datasets demonstrate the state-of-the-art performance of the proposed framework in the problem of interest.
Publisher: ACM
Date: 26-10-2021
Publisher: Elsevier BV
Date: 09-2017
Publisher: Wiley
Date: 28-05-2022
DOI: 10.1111/GEB.13548
Abstract: To estimate loss of above‐ground carbon (AGC) and conversion of live carbon to dead carbon following understorey and canopy fire. South‐eastern Australia. 2019–2020. Four widespread resprouting eucalypt forests. Above‐ground carbon was measured in 15 plots in each of four forest types one‐year post‐fire. We also assessed topkill, that is, trees subject to canopy loss that failed to resprout epicormically. While canopy fire was associated with greater declines in AGC than understorey fire, this was only statistically significant for only one forest type, where AGC declined from 154 to 85 Mg C ha −1 following canopy fire. Significant post‐fire increases in dead AGC were observed in one forest type, where dead carbon increased from 22 to 60% after canopy fire. Topkill of trees following canopy fire (48–78% of stems) was higher than topkill after understorey fire (36–53% of stems) and in unburnt forest (12–55%). Topkill occurred primarily in small‐diameter stems. Consequently, there was no effect of fire on the proportion of dead AGC in trees, with the exception of the forest with lowest productivity (i.e., lowest biomass) and lowest annual rainfall, where dead tree carbon increased from 8% in unburnt forest to 13 and 53% after understorey and canopy fire, respectively. AGC in understorey vegetation and coarse woody debris was similar or lower in burnt compared with unburnt forest. Litter carbon was significantly lower and pyrogenic carbon significantly higher in burnt forest, with no difference between understorey and canopy fire. While increased fire severity was associated with increased changes to carbon stocks, there were differences among forest types. Specifically, the driest forest type had the highest rates of topkill following canopy fire. These results highlight the importance of spatial variability in fire severity and forest type in determining the effects of fire on carbon stocks.
Publisher: IEEE
Date: 06-2020
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or filters without data, e.g., pruning and decomposition. In contrast, we study this problem from a different perspective by respecting the difference between data. An instance-wise feature pruning is developed by identifying informative features for different instances. Specifically, by investigating a feature decay regularization, we expect intermediate feature maps of each instance in deep neural networks to be sparse while preserving the overall network performance. During online inference, subtle features of input images extracted by intermediate layers of a well-trained neural network can be eliminated to accelerate the subsequent calculations. We further take coefficient of variation as a measure to select the layers that are appropriate for acceleration. Extensive experiments conducted on benchmark datasets and networks demonstrate the effectiveness of the proposed method.
Publisher: IEEE
Date: 06-2020
Publisher: IEEE
Date: 10-2021
Publisher: IEEE
Date: 10-2019
Publisher: IEEE
Date: 06-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 06-2020
Publisher: IEEE
Date: 09-2012
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2018
Abstract: In practice, the circumstance that training and test data are clean is not always satisfied. The performance of existing methods in the learning using privileged information (LUPI) paradigm may be seriously challenged, due to the lack of clear strategies to address potential noises in the data. This paper proposes a novel Robust SVM+ (RSVM+) algorithm based on a rigorous theoretical analysis. Under the SVM+ framework in the LUPI paradigm, we study the lower bound of perturbations of both ex le feature data and privileged feature data, which will mislead the model to make wrong decisions. By maximizing the lower bound, tolerance of the learned model over perturbations will be increased. Accordingly, a novel regularization function is introduced to upgrade a variant form of SVM+. The objective function of RSVM+ is transformed into a quadratic programming problem, which can be efficiently optimized using off-the-shelf solvers. Experiments on real-world datasets demonstrate the necessity of studying robust SVM+ and the effectiveness of the proposed algorithm.
Publisher: IEEE
Date: 06-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Springer Science and Business Media LLC
Date: 17-07-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Publisher: ACM
Date: 22-02-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: IEEE
Date: 06-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Springer International Publishing
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: IEEE
Date: 06-2021
Publisher: IEEE
Date: 10-2019
Publisher: ACM
Date: 13-08-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 17-07-2019
DOI: 10.1609/AAAI.V33I01.3301647
Abstract: Geographic information systems’ (GIS) research is widely used within the social and physical sciences and plays a crucial role in the development and implementation by governments of economic, education, environment and transportation policy. While machine learning methods have been applied to GIS datasets, the uptake of powerful deep learning CNN methodologies has been limited in part due to challenges posed by the complex and often poorly structured nature of the data. In this paper, we demonstrate the utility of GCNNs for GIS analysis via a multi-graph hierarchical spatial-filter GCNN network model in the context of GIS systems to predict election outcomes using socio-economic features drawn from the 2016 Australian Census. We report a marked improvement in performance accuracy of Hierarchical GCNNs over benchmark generalised linear models and standard GCNNs, especially in semi-supervised tasks. These results indicate the widespread potential for GIS-GCNN research methods to enrich socio-economic GIS analysis, aiding the social sciences and policy development.
Publisher: Springer Nature Switzerland
Date: 2022
Publisher: IEEE
Date: 12-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 17-07-2019
DOI: 10.1609/AAAI.V33I01.33013731
Abstract: Generative Adversarial Networks (GANs) have demonstrated a strong ability to fit complex distributions since they were presented, especially in the field of generating natural images. Linear interpolation in the noise space produces a continuously changing in the image space, which is an impressive property of GANs. However, there is no special consideration on this property in the objective function of GANs or its derived models. This paper analyzes the perturbation on the input of the generator and its influence on the generated images. A smooth generator is then developed by investigating the tolerable input perturbation. We further integrate this smooth generator with a gradient penalized discriminator, and design smooth GAN that generates stable and high-quality images. Experiments on real-world image datasets demonstrate the necessity of studying smooth generator and the effectiveness of the proposed algorithm.
Publisher: ISCA
Date: 25-10-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Springer Nature Switzerland
Date: 2022
Publisher: IEEE
Date: 06-2021
Publisher: IEEE
Date: 11-2019
Publisher: Springer Science and Business Media LLC
Date: 08-04-2020
Publisher: Elsevier BV
Date: 06-2018
Publisher: IEEE
Date: 11-2018
Publisher: ACM
Date: 19-07-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2016
Publisher: Elsevier BV
Date: 05-2020
Publisher: IEEE
Date: 06-2021
Publisher: Springer International Publishing
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2020
Publisher: Springer Nature Switzerland
Date: 2022
Publisher: IEEE
Date: 06-2021
Publisher: IEEE
Date: 06-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: ACM
Date: 04-08-2017
Publisher: IEEE
Date: 06-2020
Publisher: Elsevier BV
Date: 08-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: IEEE
Date: 11-2018
Publisher: Association for Computing Machinery (ACM)
Date: 11-05-2016
DOI: 10.1145/2894753
Abstract: Circuit clustering is usually done through discrete optimizations to enable circuit size reduction or design-specific cluster formation. In this article, we are interested in the register-clustering technique for clock-power reduction by leveraging new opportunities introduced by multibit flip-flop (MBFF). Currently, INTEGRA is the only existing postplacement MBFF clustering optimizer with a subquadratic time complexity. However, it severely degrades the wirelength, especially for realistic designs, which may nullify the benefits of MBFF clustering. In contrast, we formulate an analytical clustering score with a nonlinear programming framework, in which the wirelength objective can be seamlessly integrated and the solver has empirical subquadratic time complexity. With the MBFF library, the application of our analytical clustering method achieves comparable clock power to the state-of-the-art techniques, but further reduces the wirelength by about 25%. Even without the MBFF library, we can still achieve 30% clock wirelength reduction. In addition, the proposed method can potentially be integrated into an in-placement MBFF clustering solver and be applied to other problems that require formulating clustering scores in their objective functions.
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2017
Abstract: Supporting vector machine (SVM) is the most frequently used classifier for machine learning tasks. However, its training time could become cumbersome when the size of training data is very large. Thus, many kinds of representative subsets are chosen from the original dataset to reduce the training complexity. In this paper, we propose to choose the representative points which are noted as anchors obtained from non-negative matrix factorization (NMF) in a ide-and-conquer framework, and then use the anchors to train an approximate SVM. Our theoretical analysis shows that the solving the DCA-SVM can yield an approximate solution close to the primal SVM. Experimental results on multiple datasets demonstrate that our DCA-SVM is faster than the state-of-the-art algorithms without notably decreasing the accuracy of classification results.
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2017
Abstract: The positive and unlabeled (PU) learning problem focuses on learning a classifier from positive and unlabeled data. Some methods have been developed to solve the PU learning problem. However, they are often limited in practical applications, since only binary classes are involved and cannot easily be adapted to multi-class data. Here we propose a one-step method that directly enables multi-class model to be trained using the given input multi-class data and that predicts the label based on the model decision. Specifically, we construct different convex loss functions for labeled and unlabeled data to learn a discriminant function F. The theoretical analysis on the generalization error bound shows that it is no worse than k√k times of the fully supervised multi-class classification methods when the size of the data in k classes is of the same order. Finally, our experimental results demonstrate the significance and effectiveness of the proposed algorithm in synthetic and real-world datasets.
Publisher: Elsevier BV
Date: 02-2019
Publisher: IEEE
Date: 10-2021
Publisher: Springer International Publishing
Date: 2020
Publisher: IEEE
Date: 06-2019
Publisher: IEEE
Date: 06-2019
Publisher: IEEE
Date: 06-2021
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: This paper expands the strength of deep convolutional neural networks (CNNs) to the pedestrian attribute recognition problem by devising a novel attribute aware pooling algorithm. Existing vanilla CNNs cannot be straightforwardly applied to handle multi-attribute data because of the larger label space as well as the attribute entanglement and correlations. We tackle these challenges that h ers the development of CNNs for multi-attribute classification by fully exploiting the correlation between different attributes. The multi-branch architecture is adopted for fucusing on attributes at different regions. Besides the prediction based on each branch itself, context information of each branch are employed for decision as well. The attribute aware pooling is developed to integrate both kinds of information. Therefore, attributes which are indistinct or tangled with others can be accurately recognized by exploiting the context information. Experiments on benchmark datasets demonstrate that the proposed pooling method appropriately explores and exploits the correlations between attributes for the pedestrian attribute recognition.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2023
Publisher: arXiv
Date: 2022
Publisher: IEEE
Date: 23-05-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2018
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: Deep recurrent neural networks have achieved impressive success in forecasting human motion with a sequence to sequence architecture. However, forecasting in longer time horizons often leads to implausible human poses or converges to mean poses, because of error accumulation and difficulties in keeping track of longerterm information. To address these challenges, we propose to retrospect human dynamics with attention. A retrospection module is designed upon RNN to regularly retrospect past frames and correct mistakes in time. This significantly improves the memory of RNN and provides sufficient information for the decoder networks to generate longer term prediction. Moreover, we present a spatial attention module to explore and exploit cooperation among joints in performing a particular motion. Residual connections are also included to guarantee the performance of short term prediction. We evaluate the proposed algorithm on the largest and most challenging Human 3.6M dataset in the field. Experimental results demonstrate the necessity of investigating motion prediction in a self audit manner and the effectiveness of the proposed algorithm in both short term and long term predictions.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2017
Publisher: Springer International Publishing
Date: 2018
Publisher: Elsevier BV
Date: 09-2016
Publisher: IEEE
Date: 06-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2014
Publisher: Springer Science and Business Media LLC
Date: 2020
Publisher: ACM
Date: 19-04-2021
Publisher: arXiv
Date: 2022
Publisher: Springer Science and Business Media LLC
Date: 02-03-2022
Publisher: Elsevier BV
Date: 05-2018
Publisher: ACM
Date: 17-08-2013
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2017
Abstract: Collaborative filtering plays a crucial role in reducing excessive information in online consuming by suggesting products to customers that fulfil their potential interests. Observing that a user's review comments on purchases are often in companion with ratings, recent works exploit the review texts in representing user or item factors and have achieved prominent performance. Although effectiveness of reviews has been verified, one major defect of existing works is that reviews are used in justifying the learning of either user or item factors without noticing that each review associates a pair of user and item concurrently. To better explore the value of review comments, this paper presents the privileged matrix factorization method that utilize reviews in the learning of both user and item factors. By mapping review texts into the privileged feature space, a learned privileged function compensates the discrepancies between predicted ratings and groundtruth values rating-wisely. Thus by minimizing discrepancies and prediction errors, our method harnesses the information present in the review comments for the learning of both user and item factors. Experiments on five real datasets testify the effectiveness of the proposed method.
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2017
Abstract: This paper studies the collaborative rating allocation problem, in which each user has limited ratings on all items. These users are termed ``energy limited''. Different from existing methods which treat each rating independently, we investigate the geometric properties of a user's rating vector, and design a matrix completion method on the simplex. In this method, a user's rating vector is estimated by the combination of user profiles as basis points on the simplex. Instead of using Euclidean metric, a non-linear pull-back distance measurement from the sphere is adopted since it can depict the geometric constraints on each user's rating vector. The resulting objective function is then efficiently optimized by a Riemannian conjugate gradient method on the simplex. Experiments on real-world data sets demonstrate our model's competitiveness versus other collaborative rating prediction methods.
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2017
Abstract: This paper presents privileged multi-label learning (PrML) to explore and exploit the relationship between labels in multi-label learning problems. We suggest that for each in idual label, it cannot only be implicitly connected with other labels via the low-rank constraint over label predictors, but also its performance on ex les can receive the explicit comments from other labels together acting as an Oracle teacher. We generate privileged label feature for each ex le and its in idual label, and then integrate it into the framework of low-rank based multi-label learning. The proposed algorithm can therefore comprehensively explore and exploit label relationships by inheriting all the merits of privileged information and low-rank constraints. We show that PrML can be efficiently solved by dual coordinate descent algorithm using iterative optimization strategy with cheap updates. Experiments on benchmark datasets show that through privileged label features, the performance can be significantly improved and PrML is superior to several competing methods in most cases.
Publisher: IEEE
Date: 06-2020
Publisher: ACM
Date: 04-08-2023
Publisher: ACM
Date: 14-08-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: IEEE
Date: 06-2020
Publisher: ACM
Date: 25-04-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: IEEE
Date: 06-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 10-2019
Publisher: IEEE
Date: 06-2021
Publisher: IEEE
Date: 10-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2015
Publisher: Elsevier BV
Date: 10-2021
Publisher: Springer Science and Business Media LLC
Date: 23-05-2014
Publisher: Elsevier BV
Date: 04-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2022
Publisher: IEEE
Date: 06-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2023
Publisher: Elsevier BV
Date: 05-2022
Publisher: IEEE
Date: 06-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2015
Publisher: ACM
Date: 29-03-2015
Publisher: ACM
Date: 12-10-2020
Publisher: IEEE
Date: 05-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Start Date: 2018
End Date: 12-2020
Amount: $356,446.00
Funder: Australian Research Council
View Funded ActivityStart Date: 06-2021
End Date: 10-2024
Amount: $480,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 06-2018
End Date: 06-2021
Amount: $392,893.00
Funder: Australian Research Council
View Funded ActivityStart Date: 06-2024
End Date: 06-2028
Amount: $960,341.00
Funder: Australian Research Council
View Funded Activity