Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Yao LuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works83 from public data
- 472
- 399
- RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection284
This work introduces RealNet, a feature reconstruction network with realistic synthetic anomaly and adaptive feature selection, and develops Anomaly-aware Features Selection (A FS), a method for selecting repre-sentative and discriminative pre-trained feature subsets to improve anomaly detection performance while controlling computational costs.
- 271
- 218
- 181
- Kinship verification from facial images under uncontrolled conditions153
This paper collects a kinship face database by searching 400+ pairs of public figures and celebrities from the internet, and automatically detect them with the Viola-Jones face detector and proposes a new spatial pyramid learning-based (SPLE) feature descriptor for face representation and applies support vector machine (SVM) for kinship verification.
- Gabor-based gradient orientation pyramid for kinship verification under uncontrolled environments123
When combined with the discriminative support vector machine (SVM) classifier, GGOP demonstrates the best performance in the authors' experiments, in comparison with several state-of-the-art face feature descriptors.
- 98
- Ensemble similarity learning for kinship verification from facial images in the wild96
Experiments results demonstrate that the proposed Ensemble similarity learning (ESL) method is superior to some state-of-the-art methods in terms of both verification rate and computational efficiency.
- 79
- Learning deep compact similarity metric for kinship verification from face images74
This work proposes a new kinship metric learning (KML) method with a coupled deep neural network (DNN) model, and introduces the property of hierarchical compactness into the coupled network to facilitate deep metric learning with limited amount of kinship training data.
- 72
- Equidistant prototypes embedding for single sample based face recognition with generic learning and incremental learning64
Although it is fairly simple and parameter-free, LRA, combined with commonly used local descriptors, such as Gabor representation and local binary patterns, outperforms the state-of-the-art methods for several standard experiments on the Extended Yale B, CMU PIE, AR, and FERET databases.
- Multi-feature multi-manifold learning for single-sample face recognition54
Experimental results on the widely used AR, FERET and LFW datasets demonstrate the efficacy of the proposed M^3L method, and a multi-feature manifold-manifold distance measure is presented to recognize the probe subjects.
- Kinship verification from facial images by scalable similarity fusion53
This paper proposes a scalable similarity learning (SSL) method for KVFI, which aims to learn a diagonal bilinear similarity model by online truncated gradient learning, which enjoys superiority in scalability and computational efficiency for practical KV FI with high-dimensional data.
- NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results52
The first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4, develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development.
- 43
- Fast single image dehazing based on a regression model42
Experimental results demonstrate that the proposed approach has a lower computational complexity, and the dehazing results are visually appealing even on extremely challenging photos, such as street views, thick fog, and sky regions.
- 42
- 40
- Kinship verification in the wild: The first kinship verification competition40
The key goal of this competition is to compare the performance of different methods on a new-collected dataset with the same evaluation protocol and develop the first standardized benchmark for kinship verification in the wild.
- 39
- NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results35
The 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results establishes a new benchmark for stereo image SR.
- 35
- 33
- 33
- Deep Transformation Learning for Depression Diagnosis from Facial Images30
A novel deep transformation learning (DTL) method for visual-based depression recognition that learns a set of hierarchical nonlinear transformations to project original input features into a new feature subspace, so as to capture the non-linear manifold of depression data.
- 28
- Learning a Genetic Measure for Kinship Verification Using Facial Images25
Experimental results show that the proposed new kinship verification approach by learning a sparse similarity measure in an online fashion is highly competitive to the state-of-the-art alternatives in terms of verification accuracy, yet it is superior in Terms of scalability for practical applications.
- Learning content‐adaptive feature pooling for facial depression recognition in videos22
The authors introduce the memory attention mechanism in a regression network to learn a deep discriminative depression representation, where the residual network module aims at learning frame-level deep feature, while the attention module acts as a pooling layer by adaptively learning the weights emphasising or suppressing face images with varying poses and imaging conditions.
- Multiple face tracking and recognition with identity-specific localized metric learning22
This paper introduces the constraints of inter-frame temporal smoothness and within-frame identity exclusivity on multiple faces in videos, and model the tasks of multiple face recognition (MFR) and multiple face tracking (MFT) jointly in an alternative optimization framework and shows this joint formulation for two different tasks leads to significantly improved MFR accuracy.
- 19
- 19
- 16
- 15
- Conformal Depression Prediction14
Con conformal depression prediction (CDP) is introduced, a depression prediction method with uncertainty quantification based on conformal prediction (CP), giving valid confidence intervals with theoretical coverage guarantees for the model predictions.
- $L^{2}$FMamba: Lightweight Light Field Image Super-Resolution With State Space Model10
A lightweight network, $L^{2}$FMamba (Lightweight Light Field Mamba), which integrates the LF-VSSM block to leverage light field features for super-resolution tasks while overcoming the computational challenges of Transformer-based approaches.
- 10
- 10
- 9
- 9
- Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval9
An efficient VLP framework named Masked Contrastive and Reconstruction (MCR) is proposed, which takes masked data as the sole input for both tasks, which enhances task connections, reducing information interference and competition between them, while also substantially decreasing the required GPU memory and training time.
- Confidence-Calibrated Face and Kinship Verification9
This work introduces an effective confidence measure that allows verification models to convert a similarity score into a confidence score for any given face pair, and proposes a confidence-calibrated approach, termed Angular Scaling Calibration (ASC), which is easy to implement and readily applied to existing verification models without model modifications.
- Sky detection by effective context inference9
This paper presents an novel algorithm for sky detection by combining the merits of superpixels and context inference, which has a higher detection accuracy than the state-of-the-art methods under various weather conditions.
- Hybrid generative-discriminative learning for online tracking of sperm cell9
HGDT retains most of the desirable properties of generative trackers while improving the classification performance to separate the visual sperm from the background distracters, and an energy-biased stochastic approximation Monte Carlo sampling algorithm is proposed for more effective Bayesian tracking.
- 7
- Activity-based person identification using sparse coding and discriminative metric learning7
This paper presents a new activity-based person identification method using sparse coding and discriminative metric learning that aims to recognize people from different activities such as running, jumping, skipping, and so on.
- 6
- Fair Uncertainty Quantification for Depression Prediction5
This work investigates the algorithmic fairness of UQ, namely equal opportunity of coverage (EOC) fairness, and proposes fair uncertainty quantification (FUQ) for depression prediction, which enables the model to preserve predictive reliability while adapting to the heterogeneous uncertainty levels across demographic groups, thereby achieving optimal fairness.
- Efficient Stochastic Approximation Monte Carlo Sampling for Heterogeneous Redundancy Allocation Problem5
Experimental results performed on a range of benchmark instances demonstrated the superiority of the proposed optimization approach compared with the state-of-the-art alternatives in terms of the solution quality or computational efficiency.
- 5
- Activity-Based Person Identification Using Discriminative Sparse Projections and Orthogonal Ensemble Metric Learning5
An activity-based human identification approach using discriminative sparse projections (DSP) and orthogonal ensemble metric learning (OEML) to identify people from more general types of human activities such as eating, drinking, running, and so on.
- Towards High-Resolution Industrial Image Anomaly Detection4
High-resolution anomaly detection using a dual-branch architecture that integrates anomaly cues across different scales to comprehensively capture both subtle and large-scale anomalies and incorporates a multi-resolution feature fusion strategy to tackle the challenges posed by fine-grained texture variations in high-resolution images.
- 4
- 3
- 3
- ZigzagNet: Efficient Deep Learning for Real Object Recognition Based on 3D Models3
A 6.2 MB compact parametric model called ZigzagNet based on SqueezeNet is proposed to improve the performance for recognition by applying moving normalization inside micro architecture and adding channel wise convolutional bypass through macro architecture.
- Learning spatially regularized similarity for robust visual tracking3
Evaluations show the robustness to partial occlusion with high matching accuracy, and the results demonstrate that the proposed spatially weighted similarity fusion scheme can achieve competitive or better tracking performance in various challenging tracking scenarios.
- 3
- 3
- 2
- 2
- A novel research on network security situation prediction based on iteratively optimized RBF-NN2
This paper proposes a novel iterative optimized RBF-NN method for NSS prediction that leverages a resource allocation network (RAN) to dynamically determine the optimal number of neurons in the hidden layer, ensuring a balance between model complexity and prediction accuracy.
- A Graph Similarity Algorithm Based on Graph Partitioning and Attention Mechanism2
The experimental results indicated that the proposed learning algorithm outperformed the traditional algorithms and similar computing models in terms of graph similarity computation performance.
- 2
- 2
- 2
- UniADC: A Unified Framework for Anomaly Detection and Classification1
UniADC is proposed, a model designed to effectively perform both anomaly detection and classification as separate tasks with only a few or even no anomaly images, and consistently outperforms existing methods in anomaly detection, localization, and classification.
- Weakly Supervised Anomaly Detection for Chest X-Ray Image1
WSCXR is proposed, a weakly supervised anomaly detection framework for CXR that refines the anomaly image features by eliminating normal region features through anomaly feature mining, thus fully leveraging the scarce yet crucial features of diseased areas.
- Model-Based Proposal Learning for Monte Carlo Optimization of Redundancy Allocation Problem1
A rejection-free Monte Carlo method to sample from the target distribution over the combinatorial space to address the problem of where to sample for efficient optimization of heterogeneous RAP is introduced.
- 1
- 1
- 1
- 1
- Learning to Calibrate for Reliable Visual Fire Detection–
This work proposes transforming the Expected Calibration Error (ECE), a metric for measuring uncertainty, into a differentiable ECE loss function, and introduces a curriculum learning-based approach that dynamically adjusts the weight of the ECE loss during training to achieve a good balance between classification accuracy and reliable decision.
- –
- Billet Number Recognition Based on Test-Time Adaptation–
This work proposes a billet number recognition method that integrates test-time adaptation with prior knowledge, and introduces a validation mechanism into the CTC algorithm using prior knowledge to address its limitations in recognizing damaged characters.
- –
- –
- Low-Light Image Enhancement Based on Constrained Norm Estimation–
An effective method to constrain the illumination map t by estimating the norm and constructing the constraint coefficients, which is called LieCNE is proposed, which exhibits better performance under a variety of lighting conditions in enhancement results and image spillover prevention.
- An adaptive particle filter tracking algorithm based on the integration of color and texture–
The multi-feature weighted histogram is proposed, which can describe the color and texture characteristics of the tracking target, and updates the reference target model adaptively to the changed target.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.