ORCID Profile
0000-0001-7225-5449
Current Organisations
University of Science and Technology of China
,
University of London
,
University of Sydney
,
Chinese University of Hong Kong
,
The Hong Kong Polytechnic University
,
Nanyang Technological University
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.
Research Topics
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.
Top 5 Research Topics
ANZSRC Field of Research (FoR)
Artificial Intelligence and Image Processing | Pattern Recognition and Data Mining | Computer Vision | Statistics | Computer Hardware not elsewhere classified | Knowledge Representation and Machine Learning | Artificial Intelligence and Image Processing not elsewhere classified | Applied Statistics | Computer Hardware | Microelectromechanical Systems (MEMS) | Natural Resource Management | Business Information Management (incl. Records, Knowledge and Information Management, and Intelligence)
ANZSRC Socio-Economic Objective (SEO)
Film and Video Services (excl. Animation and Computer Generated Imagery) | Intelligence | Information Processing Services (incl. Data Entry and Capture) | Electronic Information Storage and Retrieval Services | Expanding Knowledge in the Information and Computing Sciences | Environmental Management Systems | Road Safety | Plant Production and Plant Primary Products not elsewhere classified | Social Structure and Health | Mental Health | Expanding Knowledge in Technology | Application Software Packages (excl. Computer Games) | Fisheries - Aquaculture not elsewhere classified | Application Tools and System Utilities | Information and Communication Services not elsewhere classified | Precious (Noble) Metal Ore Exploration | Property, Business Support Services and Trade not elsewhere classified | Mining Land and Water Management |
Related Links
Publications
On Combining Biclustering Mining and AdaBoost for Breast Tumor Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2020
A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning
Publisher: Association for Computing Machinery (ACM)
Date: 13-07-2023
DOI: 10.1145/3576918
Abstract: With the development of convolutional neural networks, hundreds of deep learning–based dehazing methods have been proposed. In this article, we provide a comprehensive survey on supervised, semi-supervised, and unsupervised single image dehazing. We first discuss the physical model, datasets, network modules, loss functions, and evaluation metrics that are commonly used. Then, the main contributions of various dehazing algorithms are categorized and summarized. Further, quantitative and qualitative experiments of various baseline methods are carried out. Finally, the unsolved issues and challenges that can inspire the future research are pointed out. A collection of useful dehazing materials is available at github.com/Xiaofeng-life/AwesomeDehazing .
Cascaded Correlation Refinement for Robust Deep Tracking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2021
Transforming Cooling Optimization for Green Data Center via Deep Reinforcement Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2020
Global-Local Interplay in Semantic Alignment for Few-Shot Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2022
Complementary, Heterogeneous and Adversarial Networks for Image-to-Image Translation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Edge-Sensitive Human Cutout With Hierarchical Granularity and Loopy Matting Guidance
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Greedy Batch-Based Minimum-Cost Flows for Tracking Multiple Objects
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2017
CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
On the learnability of quantum neural networks
Publisher: Research Square Platform LLC
Date: 25-09-2020
DOI: 10.21203/RS.3.RS-80242/V1
Abstract: Quantum neural network (QNN), or equivalently, the variational quantum circuits with a gradient-based classical optimizer, has been broadly applied to many experimental proposals for noisy intermediate scale quantum (NISQ) devices. However, the learning capability of QNN remains largely unknown due to the non-convex optimization landscape, the measurement error, and the unavoidable gate noise introduced by NISQ machines. In this study, we theoretically explore the learnability of QNN from the perspective of the trainability and generalization. Particularly, we derive the convergence performance of QNN under the NISQ setting, and identify classes of computationally hard concepts that can be efficiently learned by QNN. Our results demonstrate that large gate noise, few quantum measurements, and deep circuit depth will lead to poor convergence rates of QNN towards the empirical risk minimization. Moreover, we prove that any concept class, which is efficiently learnable by a restricted quantum statistical query (QSQ) learning model, can also be efficiently learned by QNN. Since the restricted QSQ learning model can tackle certain problems such as parity learning with a runtime speedup, our result suggests that QNN established on NISQ devices will retain the quantum advantage. Our work provides the theoretical guidance for developing advanced QNNs and opens up avenues for exploring quantum advantages using NISQ devices.
Enhanced Tensor RPCA and its Application
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2021
State-Aware Anti-Drift Object Tracking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2019
IDRLP: Image Dehazing Using Region Line Prior
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Heterogeneous Multitask Metric Learning Across Multiple Domains
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2018
A Regularization Approach for Instance-Based Superset Label Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2018
SPRNet: Single-Pixel Reconstruction for One-Stage Instance Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2021
VSA: Learning Varied-Size Window Attention in Vision Transformers
Publisher: Springer Nature Switzerland
Date: 2022
Truncated Cauchy Non-Negative Matrix Factorization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
ROMIR: Robust Multi-View Image Re-Ranking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
On Exploring Multiplicity of Primitives and Attributes for Texture Recognition in the Wild
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Early Expression Detection via Online Multi-Instance Learning With Nonlinear Extension
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2019
LogDet Metric-Based Domain Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2020
Towards High Performance Human Keypoint Detection
Publisher: Springer Science and Business Media LLC
Date: 07-2021
Solving Jigsaw Puzzles via Nonconvex Quadratic Programming With the Projected Power Method
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Robust Kernelized Multiview Self-Representation for Subspace Clustering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2021
Top-k Feature Selection Framework Using Robust 0–1 Integer Programming
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2021
Multi-Sentence Auxiliary Adversarial Networks for Fine-Grained Text-to-Image Synthesis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
End2End Occluded Face Recognition by Masking Corrupted Features
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2022
Multi-Task Consistency-Preserving Adversarial Hashing for Cross-Modal Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Distributed Energy Trading and Scheduling Among Microgrids via Multiagent Reinforcement Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Improving Video Instance Segmentation via Temporal Pyramid Routing
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
One-Pass Multi-Task Networks With Cross-Task Guided Attention for Brain Tumor Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Unified Instance and Knowledge Alignment Pretraining for Aspect-Based Sentiment Analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Transferring Knowledge Fragments for Learning Distance Metric from a Heterogeneous Domain
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Distributed Complementary Binary Quantization for Joint Hash Table Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2020
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2023
Efficient Bipartite Entanglement Detection Scheme with a Quantum Adversarial Solver
Publisher: American Physical Society (APS)
Date: 14-03-2022
TransVOD: End-to-End Video Object Detection With Spatial-Temporal Transformers
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2023
Loss Decomposition and Centroid Estimation for Positive and Unlabeled Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2021
3D Skeletal Gesture Recognition via Hidden States Exploration
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
RegionCL: Exploring Contrastive Region Pairs for Self-supervised Representation Learning
Publisher: Springer Nature Switzerland
Date: 2022
Hierarchical Deep Click Feature Prediction for Fine-Grained Image Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2022
A Comprehensive Survey of Dataset Distillation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Iterative Privileged Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2020
Training Robust Deep Neural Networks via Adversarial Noise Propagation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2023
A Light Dual-Task Neural Network for Haze Removal
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2018
Adapting Stochastic Block Models to Power-Law Degree Distributions
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2019
Gait Phase Classification for a Lower Limb Exoskeleton System Based on a Graph Convolutional Network Model
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2022
Transforming Device Fingerprinting for Wireless Security via Online Multitask Metric Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Adaptive Context-Aware Multi-Modal Network for Depth Completion
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Recursive Context Routing for Object Detection
Publisher: Springer Science and Business Media LLC
Date: 19-08-2021
Bridging Composite and Real: Towards End-to-End Deep Image Matting
Publisher: Springer Science and Business Media LLC
Date: 04-01-2022
SIN: Semantic Inference Network for Few-Shot Streaming Label Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
GraMMaR: Ground-aware Motion Model for 3D Human Motion Reconstruction
Publisher: ACM
Date: 27-04-2242
Brain Age Estimation From MRI Using Cascade Networks With Ranking Loss
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2021
Prescribed Safety Performance Imitation Learning from A Single Expert Dataset
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
An Underwater Image Enhancement Benchmark Dataset and Beyond
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Compositional Attention Networks With Two-Stream Fusion for Video Question Answering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Matching Seqlets: An Unsupervised Approach for Locality Preserving Sequence Matching
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2021
DCT Regularized Extreme Visual Recovery
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2017
Overcoming Catastrophic Forgetting in Continual Learning by Exploring Eigenvalues of Hessian Matrix
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Query-Adaptive Hash Code Ranking for Large-Scale Multi-View Visual Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2016
Laplacian Welsch Regularization for Robust Semisupervised Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
CODON: On Orchestrating Cross-Domain Attentions for Depth Super-Resolution
Publisher: Springer Science and Business Media LLC
Date: 04-01-2022
Multibranch Adversarial Regression for Domain Adaptative Hand Pose Estimation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2022
Large Sparse Cone Non-negative Matrix Factorization for Image Annotation
Publisher: Association for Computing Machinery (ACM)
Date: 20-04-2017
DOI: 10.1145/2987379
Abstract: Image annotation assigns relevant tags to query images based on their semantic contents. Since Non-negative Matrix Factorization (NMF) has the strong ability to learn parts-based representations, recently, a number of algorithms based on NMF have been proposed for image annotation and have achieved good performance. However, most of the efforts have focused on the representations of images and annotations. The properties of the semantic parts have not been well studied. In this article, we revisit the sparseness-constrained NMF (sNMF) proposed by Hoyer [2004]. By endowing the sparseness constraint with a geometric interpretation and sNMF with theoretical analyses of the generalization ability, we show that NMF with such a sparseness constraint has three advantages for image annotation tasks: (i) The sparseness constraint is more ℓ 0 -norm oriented than the ℓ 1 -norm-based sparseness, which significantly enhances the ability of NMF to robustly learn semantic parts. (ii) The sparseness constraint has a large cone interpretation and thus allows the reconstruction error of NMF to be smaller, which means that the learned semantic parts are more powerful to represent images for tagging. (iii) The learned semantic parts are less correlated, which increases the discriminative ability for annotating images. Moreover, we present a new efficient large sparse cone NMF (LsCNMF) algorithm to optimize the sNMF problem by employing the Nesterov’s optimal gradient method. We conducted experiments on the PASCAL VOC07 dataset and demonstrated the effectiveness of LsCNMF for image annotation.
A Survey on Canonical Correlation Analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2021
Transferable Coupled Network for Zero-Shot Sketch-Based Image Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
The Dilemma of Quantum Neural Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Targeted Attention Attack on Deep Learning Models in Road Sign Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 15-03-2021
GAN-MDF: An Enabling Method for Multifidelity Data Fusion
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2022
Heterogeneous Federated Learning: State-of-the-art and Research Challenges
Publisher: Association for Computing Machinery (ACM)
Date: 21-10-2023
DOI: 10.1145/3625558
AniPixel: Towards Animatable Pixel-Aligned Human Avatar
Publisher: ACM
Date: 26-10-2023
Robust Visual Tracking Revisited: From Correlation Filter to Template Matching
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2018
Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
A Distributed Learning Scheme for Variational Quantum Algorithms
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Robust Student Network Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Beyond Bilinear: Generalized Multimodal Factorized High-Order Pooling for Visual Question Answering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Long-Term Video Prediction via Criticization and Retrospection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
SERF: A Simple, Effective, Robust, and Fast Image Super-Resolver From Cascaded Linear Regression
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2016
Enhancing the Robustness of Neural Collaborative Filtering Systems Under Malicious Attacks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2019
Deep Corner
Publisher: Springer Science and Business Media LLC
Date: 05-07-2023
DOI: 10.1007/S11263-023-01837-3
Abstract: Recent studies have shown promising results on joint learning of local feature detectors and descriptors. To address the lack of ground-truth keypoint supervision, previous methods mainly inject appropriate knowledge about keypoint attributes into the network to facilitate model learning. In this paper, inspired by traditional corner detectors, we develop an end-to-end deep network, named Deep Corner, which adds a local similarity-based keypoint measure into a plain convolutional network. Deep Corner enables finding reliable keypoints and thus benefits the learning of the distinctive descriptors. Moreover, to improve keypoint localization, we first study previous multi-level keypoint detection strategies and then develop a multi-level U-Net architecture, where the similarity of features at multiple levels can be exploited effectively. Finally, to improve the invariance of descriptors, we propose a feature self-transformation operation, which transforms the learned features adaptively according to the specific local information. The experimental results on several tasks and comprehensive ablation studies demonstrate the effectiveness of our method and the involved components.
On the Guaranteed Almost Equivalence Between Imitation Learning From Observation and Demonstration
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2023
Quantum Differentially Private Sparse Regression Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2022
Video Saliency Detection Using Object Proposals
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2018
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
Publisher: Springer Nature Switzerland
Date: 2022
A Hybrid Level Set With Semantic Shape Constraint for Object Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2019
Ensemble Teaching for Hybrid Label Propagation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2019
Joint Deep Multi-View Learning for Image Clustering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2021
Aspect-Aware Graph Attention Network for Heterogeneous Information Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Hyper-Laplacian Regularized Multilinear Multiview Self-Representations for Clustering and Semisupervised Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2020
Motion-Aware Rapid Video Saliency Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2020
Short-Term Lesion Change Detection for Melanoma Screening With Novel Siamese Neural Network
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2021
FogChain: A Blockchain-Based Peer-to-Peer Solar Power Trading System Powered by Fog AI
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2022
Bi-Phase Evolutionary Searching for Biclusters in Gene Expression Data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2019
Tutorials at The Web Conference 2023
Publisher: ACM
Date: 30-04-2023
Triplet-Based Deep Hashing Network for Cross-Modal Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2018
OMG: Towards Effective Graph Classification Against Label Noise
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
GoDec+: Fast and Robust Low-Rank Matrix Decomposition Based on Maximum Correntropy
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2018
Quantum circuit architecture search for variational quantum algorithms
Publisher: Springer Science and Business Media LLC
Date: 23-05-2022
DOI: 10.1038/S41534-022-00570-Y
Abstract: Variational quantum algorithms (VQAs) are expected to be a path to quantum advantages on noisy intermediate-scale quantum devices. However, both empirical and theoretical results exhibit that the deployed ansatz heavily affects the performance of VQAs such that an ansatz with a larger number of quantum gates enables a stronger expressivity, while the accumulated noise may render a poor trainability. To maximally improve the robustness and trainability of VQAs, here we devise a resource and runtime efficient scheme termed quantum architecture search (QAS). In particular, given a learning task, QAS automatically seeks a near-optimal ansatz (i.e., circuit architecture) to balance benefits and side-effects brought by adding more noisy quantum gates to achieve a good performance. We implement QAS on both the numerical simulator and real quantum hardware, via the IBM cloud, to accomplish data classification and quantum chemistry tasks. In the problems studied, numerical and experimental results show that QAS cannot only alleviate the influence of quantum noise and barren plateaus but also outperforms VQAs with pre-selected ansatze.
Holistic CNN Compression via Low-Rank Decomposition with Knowledge Transfer
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Multi-Task Structure-Aware Context Modeling for Robust Keypoint-Based Object Tracking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Generalization Bounds of Multitask Learning From Perspective of Vector-Valued Function Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2021
Collaborative Knowledge Distillation via Multiknowledge Transfer
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Deep Coattention-Based Comparator for Relative Representation Learning in Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2021
Heterogeneous Face Recognition: A Common Encoding Feature Discriminant Approach
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2017
Batch Coherence-Driven Network for Part-Aware Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Correntropy-Induced Robust Low-Rank Hypergraph
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2019
Information-Theoretic Odometry Learning
Publisher: Springer Science and Business Media LLC
Date: 12-08-2022
DOI: 10.1007/S11263-022-01659-9
Abstract: In this paper, we propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation, a crucial component of many robotics and vision tasks such as navigation and virtual reality where relative camera poses are required in real time. We formulate this problem as optimizing a variational information bottleneck objective function, which eliminates pose-irrelevant information from the latent representation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language. Specifically, we bound the generalization errors of the deep information bottleneck framework and the predictability of the latent representation. These provide not only a performance guarantee but also practical guidance for model design, s le collection, and sensor selection. Furthermore, the stochastic latent representation provides a natural uncertainty measure without the needs for extra structures or computations. Experiments on two well-known odometry datasets demonstrate the effectiveness of our method.
Advancing Plain Vision Transformer Toward Remote Sensing Foundation Model
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
A Human-Like Dual-Forklift Collaborative Mechanism for Container Handling
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2021
Homologous Component Analysis for Domain Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Visual Relationship Detection: A Survey
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2022
Feature Learning Using Spatial-Spectral Hypergraph Discriminant Analysis for Hyperspectral Image
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2019
An Empirical Study of Remote Sensing Pretraining
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions
Publisher: ACM
Date: 26-10-2023
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2018
VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
3D-FUTURE: 3D Furniture Shape with TextURE
Publisher: Springer Science and Business Media LLC
Date: 15-10-2021
Terra: A Smart and Sensible Digital Twin Framework for Robust Robot Deployment in Challenging Environments
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 15-09-2021
Data Subset Selection With Imperfect Multiple Labels
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2019
Robust Subspace Clustering by Cauchy Loss Function
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2019
Multistage GAN for Fabric Defect Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 15-05-2021
DARC: Distribution-Aware Re-Coloring Model for Generalizable Nucleus Segmentation
Publisher: Springer Nature Switzerland
Date: 2023
Harnessing Side Information for Classification Under Label Noise
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2020
Boundary-Assisted Region Proposal Networks for Nucleus Segmentation
Publisher: Springer International Publishing
Date: 2020
Matrix Infinitely Divisible Series: Tail Inequalities and Their Applications
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2020
Open-Set Hypothesis Transfer With Semantic Consistency
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Packing Convolutional Neural Networks in the Frequency Domain
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2019
Orthogonal Deep Neural Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2021
Learning Student Networks via Feature Embedding
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Imposing Semantic Consistency of Local Descriptors for Few-Shot Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Deep Multi-scale Discriminative Networks for Double JPEG Compression Forensics
Publisher: Association for Computing Machinery (ACM)
Date: 15-02-2019
DOI: 10.1145/3301274
Abstract: As JPEG is the most widely used image format, the importance of t ering detection for JPEG images in blind forensics is self-evident. In this area, extracting effective statistical characteristics from a JPEG image for classification remains a challenge. Effective features are designed manually in traditional methods, suggesting that extensive labor-consuming research and derivation is required. In this article, we propose a novel image t ering detection method based on deep multi-scale discriminative networks (MSD-Nets). The multi-scale module is designed to automatically extract multiple features from the discrete cosine transform (DCT) coefficient histograms of the JPEG image. This module can capture the characteristic information in different scale spaces. In addition, a discriminative module is also utilized to improve the detection effect of the networks in those difficult situations when the first compression quality ( QF 1) is higher than the second one ( QF 2). A special network in this module is designed to distinguish the small statistical difference between authentic and t ered regions in these cases. Finally, a probability map can be obtained and the specific t ering area is located using the last classification results. Extensive experiments demonstrate the superiority of our proposed method in both quantitative and qualitative metrics when compared with state-of-the-art approaches.
Toward Realistic Face Photo–Sketch Synthesis via Composition-Aided GANs
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2021
Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2018
Shared Predictive Cross-Modal Deep Quantization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2018
Stagewise Unsupervised Domain Adaptation With Adversarial Self-Training for Road Segmentation of Remote-Sensing Images
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Why ResNet Works? Residuals Generalize
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2020
Heterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain Adaptation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2022
Dualityfree Methods for Stochastic Composition Optimization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-Based Sentiment Analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2023
Multiobject Tracking by Submodular Optimization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2019
Object-Agnostic Transformers for Video Referring Segmentation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Principal Component Adversarial Example
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Unveiling Hidden Implicit Similarities for Cross-Domain Recommendation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Domain-Specific Risk Minimization for Domain Generalization
Publisher: ACM
Date: 04-08-2023
Siamese Local and Global Networks for Robust Face Tracking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
TimeAutoAD: Autonomous Anomaly Detection With Self-Supervised Contrastive Loss for Multivariate Time Series
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2022
ASTS: A Unified Framework for Arbitrary Shape Text Spotting
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
Publisher: Springer Nature Switzerland
Date: 2022
Vision-Assisted Autonomous Lower-Limb Exoskeleton Robot
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2021
Multi-View Object Retrieval via Multi-Scale Topic Models
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2016
Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Incorporating Distribution Matching into Uncertainty for Multiple Kernel Active Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Graph Edge Convolutional Neural Networks for Skeleton-Based Action Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2020
Self-Training With Progressive Representation Enhancement for Unsupervised Cross-Domain Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Efficient Unsupervised Dimension Reduction for Streaming Multiview Data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
FAMED-Net: A Fast and Accurate Multi-Scale End-to-End Dehazing Network
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Cross-modal & Cross-domain Learning for Unsupervised LiDAR Semantic Segmentation
Publisher: ACM
Date: 26-10-2023
Deep Multi-View Learning Using Neuron-Wise Correlation-Maximizing Regularizers
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2019
Removing Turbulence Effect via Hybrid Total Variation and Deformation-Guided Kernel Regression
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2016
The Double-Accelerated Stochastic Method for Regularized Empirical Risk Minimization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
IC9600: A Benchmark Dataset for Automatic Image Complexity Assessment
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Learning to Purification for Unsupervised Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Multifeature Anisotropic Orthogonal Gaussian Process for Automatic Age Estimation
Publisher: Association for Computing Machinery (ACM)
Date: 04-09-2017
DOI: 10.1145/3090311
Abstract: Automatic age estimation is an important yet challenging problem. It has many promising applications in social media. Of the existing age estimation algorithms, the personalized approaches are among the most popular ones. However, most person-specific approaches rely heavily on the availability of training images across different ages for a single subject, which is usually difficult to satisfy in practical application of age estimation. To address this limitation, we first propose a new model called Orthogonal Gaussian Process (OGP), which is not restricted by the number of training s les per person. In addition, without sacrifice of discriminative power, OGP is much more computationally efficient than the standard Gaussian Process. Based on OGP, we then develop an effective age estimation approach, namely anisotropic OGP (A-OGP), to further reduce the estimation error. A-OGP is based on an anisotropic noise level learning scheme that contributes to better age estimation performance. To finally optimize the performance of age estimation, we propose a multifeature A-OGP fusion framework that uses multiple features combined with a random s ling method in the feature space. Extensive experiments on several public domain face aging datasets (FG-NET, MORPH Album1, and MORPH Album 2) are conducted to demonstrate the state-of-the-art estimation accuracy of our new algorithms.
Staged Sketch-to-Image Synthesis via Semi-supervised Generative Adversarial Networks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
DUT: Learning Video Stabilization by Simply Watching Unstable Videos
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Spatial Pyramid-Enhanced NetVLAD With Weighted Triplet Loss for Place Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2020
Fluid Micelle Network for Image Super-Resolution Reconstruction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Robust Visual Tracking Using Multi-Frame Multi-Feature Joint Modeling
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Active Transfer Learning Network: A Unified Deep Joint Spectral–Spatial Feature Learning Model for Hyperspectral Image Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2019
Two-Stream Deep Hashing With Class-Specific Centers for Supervised Image Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2020
Attentive Cascaded Pyramid Network for Online Video Stabilization
Publisher: Springer Nature Switzerland
Date: 2022
Robust Graph-Based Semisupervised Learning for Noisy Labeled Data via Maximum Correntropy Criterion
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Hierarchical Multi-Attention Transfer for Knowledge Distillation
Publisher: Association for Computing Machinery (ACM)
Date: 27-09-2023
DOI: 10.1145/3568679
Wide-Angle Image Rectification: A Survey
Publisher: Springer Science and Business Media LLC
Date: 31-01-2022
Visual Superordinate Abstraction for Robust Concept Learning
Publisher: Springer Science and Business Media LLC
Date: 10-01-2023
Robust Object Detection via Adversarial Novel Style Exploration
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Recent Advances for Quantum Neural Networks in Generative Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Not All Instances Contribute Equally: Instance-Adaptive Class Representation Learning for Few-Shot Visual Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Curvature Consistent Network for Microscope Chip Image Super-Resolution
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
CartoonLossGAN: Learning Surface and Coloring of Images for Cartoonization
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Tensorized Bipartite Graph Learning for Multi-View Clustering
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Unsupervised Semantic-Preserving Adversarial Hashing for Image Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2019
Distilling Channels for Efficient Deep Tracking
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Efficient Measure for the Expressivity of Variational Quantum Algorithms
Publisher: American Physical Society (APS)
Date: 25-02-2022
Adversarial Examples for Hamming Space Search
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2020
Anchor Cascade for Efficient Face Detection
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2019
Multi-Task Learning With Coarse Priors for Robust Part-Aware Person Re-Identification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
Semantic-Preserving Adversarial Text Attacks
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Self-Supervised Multiscale Adversarial Regression Network for Stereo Disparity Estimation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2021
Progressive Cross-Modal Semantic Network for Zero-Shot Sketch-Based Image Retrieval
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Unifying Flow, Stereo and Depth Estimation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2023
Explainable Cluster-Based Rules Generation for Image Retrieval and Classification
Publisher: Springer International Publishing
Date: 2020
Knowledge Distillation: A Survey
Publisher: Springer Science and Business Media LLC
Date: 22-03-2021
Large-Margin Label-Calibrated Support Vector Machines for Positive and Unlabeled Learning
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2019
Eigenfunction-Based Multitask Learning in a Reproducing Kernel Hilbert Space
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2019
Toward Intelligent Product Retrieval for TV-to-Online (T2O) Application: A Transfer Metric Learning Approach
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2018
Related Organisations
University Of London
Location: United Kingdom of Great Britain and Northern Ireland
Related Funding Activities
ARC Future Fellowships - Grant ID: FT130101457
Start Date: 2014
End Date: 12-2017
Amount: $916,144.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP140100569
Start Date: 09-2015
End Date: 10-2015
Amount: $510,000.00
Funder: Australian Research Council
View Funded ActivityAustralian Laureate Fellowships - Grant ID: FL170100117
Start Date: 2018
End Date: 12-2025
Amount: $3,208,192.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP150100671
Start Date: 06-2016
End Date: 12-2019
Amount: $550,000.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP140102164
Start Date: 2014
End Date: 12-2017
Amount: $400,000.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP180103424
Start Date: 06-2018
End Date: 06-2021
Amount: $392,893.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP120103730
Start Date: 2012
End Date: 11-2015
Amount: $378,000.00
Funder: Australian Research Council
View Funded ActivityIndustrial Transformation Research Hubs - Grant ID: IH180100002
Start Date: 03-2019
End Date: 03-2024
Amount: $5,000,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Infrastructure, Equipment And Facilities - Grant ID: LE140100061
Start Date: 2014
End Date: 07-2015
Amount: $1,000,000.00
Funder: Australian Research Council
View Funded ActivityIndustrial Transformation Training Centres - Grant ID: IC190100031
Start Date: 08-2020
End Date: 08-2025
Amount: $3,973,202.00
Funder: Australian Research Council
View Funded Activity