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
- Qinghua HuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works187 from public data
- ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks8,870
This paper proposes an Efficient Channel Attention (ECA) module, which only involves a handful of parameters while bringing clear performance gain, and develops a method to adaptively select kernel size of 1D convolution, determining coverage of local cross-channel interaction.
- Detection and Tracking Meet Drones Challenge1,344
This work provides a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and concludes the challenge as well as propose future directions.
- 1,147
- Progressive Image Deraining Networks: A Better and Simpler Baseline1,052
A better and simpler baseline deraining network by considering network architecture, input and output, and loss functions is provided and is expected to serve as a suitable baseline in future deraining research.
- Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning745
An uncertainty-aware cross-modality vehicle detection (UA-CMDet) framework is proposed, which takes uncertainty as a weight to boost model learning more effectively while reducing bias caused by high-uncertainty objects.
- 562
- Unsupervised feature selection by regularized self-representation323
Experimental analysis on synthetic and real-world data demonstrates that the proposed regularized self-representation (RSR) model can effectively identify the representative features, outperforming many state-of-the-art unsupervised feature selection methods in terms of clustering accuracy, redundancy reduction and classification accuracy.
- 313
- 296
- 265
- VisDrone-DET2020: The Vision Meets Drone Object Detection in Image Challenge Results259
Based on the selected 29 robust detection methods, the experimental results comprehensively are discussed, which shows the effectiveness of ensemble learning and data augmentation in drone captured object detection.
- DetFusion: A Detection-driven Infrared and Visible Image Fusion Network246
A detection-driven infrared and visible image fusion network, termed DetFusion, is proposed, which utilizes object-related information learned in the object detection networks to guide multimodal image fusion and outperforms state-of-the-art methods in maintaining pixel intensity distribution and preserving texture details.
- Subspace clustering guided unsupervised feature selection209
Experimental results on benchmark datasets for unsupervised feature selection show that SCUFS outperforms the state-of-the-art UFS methods and can uncover the underlying multi-subspace structure of data.
- 200
- Multi-scale Patch Based Collaborative Representation for Face Recognition with Margin Distribution Optimization190
This work proposes a multi-scale patch based CRC method that outperforms many state-of-the-art patch based face recognition algorithms, while the ensemble of multi- scale outputs is achieved by regularized margin distribution optimization.
- Flexible Multi-View Representation Learning for Subspace Clustering174
This paper proposes to conduct subspace clustering based on Flexible Multi-view Representation (FMR) learning, which avoids using partial information for data reconstruction, and achieves superior clustering performance over other state-ofthe-art methods.
- Vision Meets Drones: Past, Present and Future173
The VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South, is described, being the largest such dataset ever published, and enables extensive evaluation and investigation of visual analysis algorithms on the drone platform.
- 171
- Multi-label feature selection with missing labels170
This paper presents a novel multi-label feature selection model under the circumstance of missing labels, where the most discriminative features are selected and missing labels are recovered simultaneously.
- Deterministic and probabilistic wind power forecasting using a variational Bayesian-based adaptive robust multi-kernel regression model160
An adaptive robust multi-kernel regression model is proposed that provides more accurate deterministic forecasts and more useful probabilistic forecasts, and has great potential for practical application in power systems.
- Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion152
Extensive experiments show that the proposed MoE-Fusion outperforms state-of-the-art methods in preserving multi-modal image texture and contrast through the local-to-global dynamic learning paradigm, and also achieves superior performance on detection tasks.
- 140
- Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark139
The Space-Time Neighbor-Aware Network (STNNet) is designed as a strong baseline to solve object detection, tracking and counting jointly in dense crowds and performs favorably against the state-of-the-arts.
- 1 Image Set based Collaborative Representation for Face Recognition138
The proposed model naturally and effectively extends the image-based collaborative representation to an image set based one, and the superiority of the proposed method to state-of-the-art ISFR methods under different set sizes in terms of both recognition rate and efficiency is shown.
- Spatial Attention Pyramid Network for Unsupervised Domain Adaptation137
A new spatial attention pyramid network that combines the dense global structure representation and local texture patterns at each spatial location effectively using the spatial attention mechanism to focus on the discriminative regions with context information for domain adaption.
- 137
- 136
- 136
- 135
- VisDrone-DET2018: The Vision Meets Drone Object Detection in Image Challenge Results133
A large-scale drone-based dataset, including 8, 599 images with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc, is released, to narrow the gap between current object detection performance and the real-world requirements.
- Multi-View Information-Bottleneck Representation Learning127
A novel and flexible unsupervised multi-view representation learning model termed Collaborative Multi-View Information Bottleneck Networks (CMIB-Nets), which comprehensively explores the common latent structure and the view-specific intrinsic information, and discards the superfluous information in the data significantly improving the generalization capability of the model.
- 120
- Towards a scalable resource-driven approach for detecting repackaged Android applications118
New features for characterizing apps are defined, two kinds of algorithms for searching similar apps are investigated, and a two-stage methodology to speed up the detection of repackaged apps is proposed.
- Latent Semantic Aware Multi-View Multi-Label Classification115
A novel approach for multi-view multi-label learning based on matrix factorization to exploit complementarity among different views and provides theoretical guarantee for the strict convexity for this method by properly setting parameters.
- 111
- 110
- 108
- Learning Self-supervised Low-Rank Network for Single-Stage Weakly and Semi-supervised Semantic Segmentation98
A Self-supervised Low-Rank Network (SLRNet) for single-stage WSSS and SSSS, which reformulate the LR representation learning as a collective matrix factorization problem and optimize it jointly with the network learning in an end-to-end manner, proving its good generalizability and efficacy.
- RGB-T Crowd Counting from Drone: A Benchmark and MMCCN Network96
A multi-modal crowd counting network (MM-CCN) with a multi-scale feature learning module, a modal alignment module and an adaptive fusion module is proposed to exploit the complementary information in both visible and thermal infrared modalities.
- 92
- VisDrone-SOT2018: The Vision Meets Drone Single-Object Tracking Challenge Results87
The evaluation protocol of the VisDrone-SOT2018 challenge is presented and the results of a comparison of 22 trackers on the benchmark dataset are presented, which are publicly available on the challenge website.
- Multi-Drone-Based Single Object Tracking With Agent Sharing Network83
An agent sharing network (ASNet) is proposed by self-supervised template sharing and view-aware fusion of the target from multiple drones, which can improve the tracking accuracy significantly compared with single drone tracking.
- 82
- VisDrone-VDT2018: The Vision Meets Drone Video Detection and Tracking Challenge Results81
A large-scale video object detection and tracking dataset, which consists of 79 video clips with about 1.5 million annotated bounding boxes in 33, 366 frames, and the evaluation protocol of the VisDrone-VDT2018 challenge and the results of the algorithms on the benchmark dataset are presented.
- Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning76
This paper proposes a multi-task graph learning model, called collaborative graph convolutional networks (CGCN), composed of an attributed graph clustering network and a semi-supervised node classification network, designed by combining variational graph auto-encoder with Gaussian mixture models (GMM-VGAE).
- 76
- 76
- 75
- 72
- Local Generic Representation for Face Recognition with Single Sample per Person72
A local generic representation (LGR) based framework for face recognition with SSPP, which takes the advantages of patch based local representation and generic variation representation and uses correntropy to measure the representation residual of each patch.
- Latent Heterogeneous Graph Network for Incomplete Multi-View Learning69
A novel Latent Heterogeneous Graph Network (LHGN) for incomplete multi-view learning is proposed, which aims to use multiple incomplete views as fully as possible in a flexible manner and explores the complex relationship between samples and latent representations.
- Coupled Dictionary Learning for Unsupervised Feature Selection69
This work proposed a novel coupled analysis-synthesis dictionary learning method, which is free of generating labels, to solve the L2p-norm optimization problem and proved it can converge to a fixed point.
- Co-regularized unsupervised feature selection68
Joint l2,1-norm co-regularization is imposed on multiple feature selection matrices to ensure that the selected features can both preserve data distribution and data reconstruction.
- Joint representation and pattern learning for robust face recognition67
A novel joint representation and pattern learning (JRPL) model is proposed, in which the feature pattern weight is simultaneously learned with the representation of query image, which shows the advantage of the proposed JRPL in accuracy and efficiency.
- Multi-view label embedding65
Experiments on benchmark databases show that MVLE outperforms the state-of-the-art LSDR algorithms in both multi-view settings and different multi-View learning strategies.
- 60
- Rule extraction from support vector machines based on consistent region covering reduction58
A rule extraction technique from support vector machines via analyzing the distribution of samples is proposed, and a covering reduction algorithm is developed for extracting compact representation of classes, thus a minimal set of decision rules is derived.
- 56
- On estimating uncertainty of wind energy with mixture of distributions56
The experimental results indicate that, the proposed model outperforms single and mixture models, and a nested expectation maximization algorithm is introduced, which develops a technique to estimate wind energy potential.
- Adaptive neighborhood granularity selection and combination based on margin distribution optimization52
Experimental analysis shows that the proposed method can adaptively select a proper granularity, and combining the models trained in multi-granularity spaces leads to competent performance.
- 51
- FISH-MML: Fisher-HSIC Multi-View Metric Learning48
This work presents a simple yet effective model for multi-view metric learning, which aims to improve the classification of data with multiple views, e.g., multiple modalities or multiple types of features, based on Fisher discriminant analysis and Hilbert-Schmidt Independence Criteria.
- 47
- M-RRFS: A Memory-Based Robust Region Feature Synthesizer for Zero-Shot Object Detection46
A novel memory-based robust region feature synthesizer (M-RRFS) is proposed for ZSD, which is equipped with the Intra-class Semantic Diverging (IntraSD), the Inter-class Structure Preserving (InterSP), and the Cross-Domain Contrast Enhancing (CrossCE) mechanisms to overcome the inadequate intra-class diversity, insufficient inter-class separability, and weak inter-domain contrast problems.
- 44
- 44
- 44
- 41
- 41
- Non-convex regularized self-representation for unsupervised feature selection41
This paper proposes a non-convex regularized self-representation (RSR) model where features can be represented by a linear combination of other features, and proposes to impose L2,p-norm (0 p < 1) regularization on self- Representation coefficients for unsupervised feature selection.
- Integrated Heterogeneous Graph Attention Network for Incomplete Multi-modal Clustering40
The proposed Integrated Heterogeneous Graph ATtention network can form a complete latent space where incomplete information can be supplemented by other related samples via the learned intrinsic structure.
- Hierarchical Feature Selection with Recursive Regularization40
This paper proposes a new technique for hierarchical feature selection based on recursive regularization, which takes the hierarchical information of the class structure into account and selects different feature subsets for each node in a hierarchical tree structure using the parent-children relationships and the sibling relationships for hierarchical regularization.
- 40
- 39
- Multi-granularity distance metric learning via neighborhood granule margin maximization39
Experiments on UCI datasets, gender classification and object categorization tasks show that the proposed method is superior to the state-of-the-art distance metric learning algorithms.
- Adaptive and Robust Partition Learning for Person Retrieval With Policy Gradient37
The novel Adaptive Partition Network (APN) utilizes deep reinforcement learning and applies an agent to generate optimal partitioning strategies dynamically for different input images, demonstrating the superiority of APN over the state-of-the-art models.
- 35
- 35
- Large-margin nearest neighbor classifiers via sample weight learning35
An approach to learning sample weights for enlarging margin by using a gradient descent algorithm to minimize margin based classification loss and consistently outperforms nearest neighbor classification and some other state-of-the-art methods.
- AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning33
A novel AMU-Tuning method is proposed to learn effective logit bias for CLIP-based few-shot classification by exploiting the appropriate Auxiliary features and an Uncertainty-based fusion is developed to incorporate logit bias into CLIP for few-shot classification.
- 30
- 29
- 29
- 28
- 26
- 26
- 25
- Towards Generalized and Efficient Metric Learning on Riemannian Manifold25
This paper makes an attempt to propose a generalized and efficient Riemannian manifold metric learning (RMML) method, which can be flexibly adopted to both SPD and Grassmann manifolds, and demonstrates the RMML performs favorably against its counterparts in terms of both accuracy and efficiency.
- 25
- 24
- 21
- 20
- 19
- 17
- 16
- 16
- 16
- 16
- 15
- 15
- Beyond Similar and Dissimilar Relations : A Kernel Regression Formulation for Metric Learning15
The proposed RAML method formulates metric learning as a kernel regression problem, which can be efficiently optimized by the standard regression solvers and achieves favorable performance against the state-of-the-art methods.
- 15
- The 2nd Workshop on UAVs in Multimedia: Capturing the World from a New Perspective13
This workshop will cover various topics related to UAV multimedia, including aerial image and video processing, machine learning for UAV data analysis, UAV swarm technology, and UAV-based multimedia applications.
- 12
- 12
- 10
- SPL-MLL: Selecting Predictable Landmarks for Multi-label Learning10
This work proposes to select a small subset of labels as landmarks which are easy to predict according to input (predictable) and can well recover the other possible labels (representative) to ensure both the representativeness and predictableness for selected landmarks.
- 10
- 9
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- Generalized Multi-view Unsupervised Feature Selection6
A novel unsupervised feature selection method is proposed, termed as generalized Multi-View Unsupervised Feature Selection (gMUFS), to simultaneously explore the complementarity of multiple views, and complex correlation between cluster structure and selected features as well.
- Semi-Supervised Multi-view Multi-label Classification Based on Nonnegative Matrix Factorization6
This work proposes a novel semi-supervised multi-view multi-label classification method based on nonnegative matrix factorization (NMF), which explores the complementary information by adopting multi- view NMF, regularizes the learned labels of each view towards a common consensus labeling, and obtains the labels of the unlabeled data guided by supervised information.
- Robust Multi-label Feature Selection with Missing Labels6
This paper proposes a robust model that recovers the missing labels by a linear regression model and select the most discriminative feature subsets simultaneously and has superior performance over the state-of-the-art algorithms.
- 6
- 5
- 5
- 5
- Multi-view Representative and Informative Induced Active Learning5
A novel method is proposed, called Multi-view Representative and Informative-induced Active Learning (MRI-AL), which selects samples of both representativeness and informativeness with the help of complementarity of multiple views using subspace reconstruction with structure sparsity technique.
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- Unsupervised Subspace Learning via Analysis Dictionary Learning4
Experiments show that the proposed unsupervised dimension reduction model outperforms the state-of-the-art methods.
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Latent Subspace Representation for Multiclass Classification1
This paper proposes a Latent Subspace Representation for Multiclass Classification (LSRMC), and learns the projection, subspace representation and classifier in a unified model, and solves the problem efficiently by using Augmented Lagrangian Multiplier with Alternating Direction Minimization.
- 1
- 1
- Multi-view Label Space Dimension Reduction1
Experiments show that the proposed multi-view learning model outperforms the best single-view model and the majority voting method and the proposed LSDR model for multi-label classification.
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation–
BasicAVSR significantly outperforms existing methods in terms of super-resolution quality, generalization ability, and inference speed and extends its core components to multiple frameworks for diverse scenarios.
- –
- –
- –
- Joint Metric Learning on Riemannian Manifold of Global Gaussian Distributions–
Experiments on video based face recognition, object recognition and material classification show that JML is superior to the state-of-the-art metric learning algorithms for Gaussians.
- –
- –
- Set to Set Visual Tracking–
Both qualitative and quantitative analyses on several challenging image sequences show that the proposed SSVT algorithm outperforms the state-of-the-art trackers.
- –
- –
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 2026-10-13. 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.