Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks264 from public data
- Hetero-Center loss for cross-modality person Re-identification222
A novel loss function, called Hetero-Center loss (HC loss) is proposed to reduce the intra-class cross-modality variations and a simple and high-performance network architecture to learn local feature representations for cross- modality person re-identification is proposed, which can be a baseline for future research.
- Joint medical image fusion, denoising and enhancement via discriminative low-rank sparse dictionaries learning216
This paper develops a novel medical image fusion, denoising, and enhancement method based on low-rank sparse component decomposition and dictionary learning that consistently outperforms existing state-of-the-art methods in terms of both visual and quantitative evaluations.
- Person Re-Identification by Regularized Smoothing KISS Metric Learning174
This paper presents regularized smoothing KISS metric learning (RS-KISS) by seamlessly integrating smoothing and regularization techniques for robustly estimating covariance matrices and introduces incremental learning to RS-K ISS.
- 137
- 137
- 124
- Canonical correlation analysis networks for two-view image recognition123
A canonical correlation analysis network (CCANet) is presented to address image classification, in which images are represented by two-view features, and the experimental results demonstrate that the CCANet algorithm is more effective than PCANet, RandNet-1 andRandNet-2.
- Upper limb motion tracking with the integration of IMU and Kinect119
This paper investigated how to fuse data from internal sensors of IMU, and fuse IMU data with Kinect in order to provide robust hand position information compensated for the limitations of those sensors, and found the proposed IMU and Kinect fusion method can provide drift-free and smooth results.
- Semantic preserving distance metric learning and applications115
A Semantic Preserving Distance Metric Learning (SP-DML) algorithm is developed to explore the complementary characteristics of the visual features and pairwise constraints in a unified feature space to integrate semantic contents in distance metric learning.
- 112
- 111
- 109
- 109
- Hessian Regularized Support Vector Machines for Mobile Image Annotation on the Cloud108
A scheme for image annotation on the cloud is presented, which transmits mobile images compressed by Hamming compressed sensing to the cloud and conducts semantic annotation through a novel Hessian regularized support vector machine on thecloud.
- 106
- Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld105
This paper distill LLM's reflection outcomes in a text world's tasks to finetune the VLM on the same tasks of the visual world, resulting in an Embodied Multi-Modal Agent (EMMA) quickly adapting to the visual world dy-namics.
- 104
- Principal Component 2-D Long Short-Term Memory for Font Recognition on Single Chinese Characters104
It is proposed that font recognition on a single Chinese character is a sequence classification problem, which can be effectively solved by recurrent neural networks and integrated a principal component convolution layer with the 2-D long short-term memory (2DLSTM) and developed principal component 2 DLSTM (PC-2DL STM) algorithm.
- 103
- Multiview dimension reduction via Hessian multiset canonical correlations100
HesMCC is presented, which takes the advantage of Hessian and provides superior extrapolating capability and finally leverage the performance of TCCA, KMUDA, MCCA and LapMCC for multiview dimension reduction.
- 99
- Skeleton embedded motion body partition for human action recognition using depth sequences94
An effective approach, which is insensitive to various temporal duration and adequate for complex background, for human action recognition using depth sequences, is proposed by embedding the skeleton information into depth maps by taking account of the geometrical structure of human body and contribute to the recognition task in complex background.
- 93
- 93
- Deep features for person re-identification on metric learning92
This work summarizes the different types of features and metric learning approaches from a label attributes perspective, and conducts comprehensive experiments on metric learning methods with two datasets, showing that the relations of loss function with deep feature space and metriclearning.
- Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID91
A novel method is introduced that automatically identifies words in a description that do not correspond with the image, based on the similarity between one text and all patch token embeddings in the image, which alleviates the impact of noisy textual descriptions.
- 91
- 89
- 89
- DeepChart: Combining deep convolutional networks and deep belief networks in chart classification87
A novel framework to classify charts by combining convolutional networks and deep belief networks is proposed, which greatly outperforms existing methods and achieves better scalability and stability.
- Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More86
An innovative training strategy is proposed that learns the parameters of the student intertwined with the teachers, achieved by ``projecting'' its amalgamated features onto each teacher's domain and computing the loss.
- Multicolumn Bidirectional Long Short-Term Memory for Mobile Devices-Based Human Activity Recognition83
- Multi-view ensemble manifold regularization for 3D object recognition82
A novel 3D object recognizing method based on multi-view data fusion, called Multi-view Ensemble Manifold Regularization (MEMR), which model image features with a regularization term for SVM and demonstrates the effectiveness of the proposed method.
- CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-Identification81
A CLIP-Driven Semantic Discovery Network that consists of Modality-specific Prompt Learner, Semantic Information Integration (SII), and High-level Semantic Embedding (HSE) is proposed that embed rich high-level semantic information into visual representations, thereby promoting the modality invariance of visual representations.
- Rank Preserving Discriminant Analysis for Human Behavior Recognition on Wireless Sensor Networks81
A new scheme for human behavior recognition on WSNs is proposed, which transmits activities' signals compressed by Hamming compressed sensing to the network server and conducts behavior recognition through a collaboration between a new dimension reduction algorithm termed rank preserving discriminant analysis (RPDA) and a nearest neighbor classifier.
- 79
- Multiview Hessian regularized logistic regression for action recognition78
This paper carefully conduct extensive experiments on the unstructured social activity attribute (USAA) dataset and the experimental results demonstrate the effectiveness of the proposed multiview Hessian regularized logistic regression for human action recognition.
- Anti-counterfeiting digital watermarking algorithm for printed QR barcode77
The experimental results show that the detection rate of anti-counterfeiting watermark is greatly improved with the proposed multi-channel robust watermarking scheme based on discrete wavelet transform (DWT), and that it can be correctly extracted from printed QR image by choosing reasonable parameters.
- Ensemble Manifold Rank Preserving for Acceleration-Based Human Activity Recognition77
A nonmetric scheme that retains discriminative and robust frequency domain information by developing a novel ensemble manifold rank preserving (EMRP) algorithm is presented.
- 76
- 73
- Large-scale paralleled sparse principal component analysis69
This paper construct parallel implementations of the four optimization formulations of the generalized power method of SPCA (GP-SPCA), one of the most efficient and effective S PCA approaches, on a GPU.
- Automatic local exposure correction using bright channel prior for under-exposed images68
This paper proposes the bright channel prior based on the statistics of well-exposed images to estimate the relative exposure in local image regions and shows that the results generated by the exposure correction method are preferred over existing methods.
- 67
- 62
- HesGCN: Hessian graph convolutional networks for semi-supervised classification62
HesGCN can learn more efficient data features by fusing the original feature information with its structure information based on Hessian, and gets a more efficient convolution layer rule by optimizing the one-order spectral graph Hessian convolutions.
- Gapformer: Graph Transformer with Graph Pooling for Node Classification61
Gapformer is presented, a method for node classification that deeply incorporates Graph Transformer with Graph Pooling and coarsens the large-scale nodes of a graph into a smaller number of pooling node via local or global graph pooling methods, and then computes the attention solely with the pooling nodes rather than all other nodes.
- Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning61
This paper proposes a common feature learning scheme, in which the features of all teachers are transformed into a common space and the student is enforced to imitate them all so as to amalgamate the intact knowledge.
- Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition61
A new unsupervised feature fusion method termed multiview Cauchy estimator feature embedding (MCEFE) for human action recognition is proposed, which integrates the encoded complementary information in multiple views to find the unified data representation and the projection matrices.
- HSAE: A Hessian regularized sparse auto-encoders60
This paper incorporates both Hessian regularization and sparsity constraints into auto-encoders and proposed HSAE outperforms the related baseline algorithms and efficiently extracts the hidden structure in the data by using sparsity constraint.
- Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks59
A comprehensive graph gradual pruning framework termed CGP is proposed, designed by designing a during-training graph pruning paradigm to dynamically prune GNNs within one training process, which significantly reduces the computation costs.
- Semi-supervised classification by graph p-Laplacian convolutional networks55
This paper exploits the manifold structure information of data by the graph p -Laplacian matrix and proposes the graph p -Laplacian convolutional networks (GpLCN), which can extract more abundant sample features and improves the classification performance utilizing graph p -Laplacian to preserve the rich intrinsic data manifold structure information.
- 55
- The spatial Laplacian and temporal energy pyramid representation for human action recognition using depth sequences55
This work proposes an effective method for human action recognition using depth sequences captured by depth cameras, and demonstrates its advantages over existing methods and is likely to be highly useful for online applications.
- Event-based large scale surveillance video summarization52
This paper proposes a novel approach of large scale surveillance video summarization on the basis of event detection, and designs a disjoint max-coverage algorithm to generate a summarized sequence with maximum coverage of interested events and minimum number of frames.
- 51
- Discriminative dictionary learning via Fisher discrimination K-SVD algorithm51
Experimental results demonstrate that the proposed Fisher Discriminative K-SVD method outperforms many other state-of-the art methods for face and palmprint recognition.
- 50
- Rank Preserving Sparse Learning for Kinect Based Scene Classification49
A new scheme for scene classification is proposed, which applies locality-constrained linear coding (LLC) to local SIFT features for representing the RGB-D samples and classifies scenes through the cooperation between a new rank preserving sparse learning (RPSL) based dimension reduction and a simple classification method.
- Reinforcement online learning for emotion prediction by using physiological signals46
A reinforcement online learning (ROL) method for real-time emotion state prediction by exploiting the reward to modify the predictor during the online training iterations is proposed and gains both significant time reduction and prominent performance.
- Road Detection by Using a Generalized Hough Transform46
The experimental results demonstrate that the proposed generalized Hough transform implementation for road detection in remote sensing images is superior to the traditional algorithms in terms of accuracy and computing complexity.
- 44
- 42
- 36
- Sample-Cohesive Pose-Aware Contrastive Facial Representation Learning34
A Pose-disentangled Contrastive Facial Representation Learning (PCFRL) framework to enhance pose awareness for SFRL by explicitly disentangled the pose-aware features from non-pose face-aware features and introducing appropriate sample calibration schemes for better CL with the disentangled features.
- Robust Sparse Coding for Mobile Image Labeling on the Cloud31
A novel mobile image labeling scheme on the cloud is presented, in which mobile images are first and efficiently transmitted to the cloud by Hamming compressed sensing, such that the heavy computation for image understanding is transferred to thecloud for quick response to the queries of the users.
- LMAE: A large margin Auto-Encoders for classification30
The Large Margin Auto-Encoders (LMAE) is proposed to further boost the discriminability by enforcing different class samples to be large marginally distributed in hidden feature space and demonstrates that the proposed LMAE outperforms the traditional Auto-encoders algorithm.
- Human pose recovery by supervised spectral embedding30
A subspace learning algorithm based on supervised manifold learning techniques to address the problem of inferring 3D human poses from monocular video frames by obtaining a global linear projection from the embedding whereby the Euclidean distances between transformed feature vectors can faithfully reflect the corresponding pose distances.
- 30
- 29
- 29
- 29
- 28
- 28
- 28
- Local structure preserving discriminative projections for RGB-D sensor-based scene classification28
A new subspace selection scheme called local structure preserving discriminative projections (LSPDP) is presented, which simultaneously considers two issues: achieving a balance between the local patch structure and global within-class structure and maximizing between-class distances.
- 26
- 26
- 26
- Affective Computing for Healthcare: Recent Trends, Applications, Challenges, and Beyond25
An extensive literature review of related studies published in the last five years of affective computing methods devised for healthcare is provided to identify and discuss some ongoing challenges in the field as evidenced by the literature.
- 25
- 25
- Color Transfer Pulse-Coupled Neural Networks for Underwater Robotic Visual Systems24
In this scheme, pulse-coupled neural network (PCNN)-based image enhancement and color transfer algorithms are combined to enhance the underwater image to avoid color imbalance and enhance details while suppressing noise.
- Grassmann multimodal implicit feature selection24
A new multimodal feature selection algorithm, termed Grassmann manifold feature selection (GMFS), is proposed, which proposes supervised/unsupervised feature selection algorithms to achieve a physically meaningful embedding of the multi-feature features.
- 23
- 22
- 21
- 20
- 20
- 20
- 20
- 18
- 18
- 17
- 17
- Semantic Adversarial Network with Multi-Scale Pyramid Attention for Video Classification17
A new two-stream based deep framework for video classification to discover spatial and temporal information only from RGB frames is proposed and the multi-scale pyramid attention (MPA) layer and the semantic adversarial learning (SAL) module is introduced and integrated in this framework.
- Clustering Multivariate Time Series Data via Multi-Nonnegative Matrix Factorization in Multi-Relational Networks17
A novel multivariate time series clustering method using multi-nonnegative matrix factorization (MNMF) in multi-relational networks to trace the evolutionary trends of clusters, thereby extending MNMF to dynamic MNMF.
- Support vector machine active learning by Hessian regularization17
A semi-supervised algorithm is introduced to learn the classifier and then an active learning scheme is performed on top of the semi- supervised scheme to achieve a better performance than the traditional active learning methods.
- Data-driven facial animation via semi-supervised local patch alignment17
A novel data-driven facial animation technique which drives a neutral source face to get the expressive target face using a semi-supervised local patch alignment framework which demonstrates its superiority to existing methods.
- 17
- Genetic algorithm for spanning tree construction in P2P distributed interactive applications17
It is shown that the peer incurred delays are closely related to the topology of the spanning tree topology, and the problem of building spanning tree with minimum total end- to-end delay to receivers in peer-to-peer DIAs is proven to be NP-complete.
- Hessian Regularized Sparse Coding for Human Action Recognition17
HessianSC significantly outperforms LaplacianSC and the traditional sparse coding algorithm for action recognition and is presented as a fast iterative shrinkage-thresholding algorithm (FISTA) for HessianSC.
- 16
- Chasing Consistency in Text-to-3D Generation from a Single Image16
Experimental results demonstrate that Consist3D produces more consistent, faithful, and photo-realistic 3D assets compared to previous state-of-the-art methods.
- 16
- Semantic embedding for indoor scene recognition by weighted hypergraph learning16
A novel approach to classify scenes by embedding semantic information in the weighted hypergraph learning is proposed, and hypergraph regularization is improved by optimizing weights of hyperedges and the semantic gap is narrowed.
- 16
- 15
- 15
- MuEP: A Multimodal Benchmark for Embodied Planning with Foundation Models14
Experimental results show that foundation models based on textual representations of environments usually outperform their visual counterparts, suggesting a gap in embodied planning abilities with multimodal observations.
- 14
- 14
- Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation14
This work proposes a Domain-invariant Graph Learning (DGL) approach for domain adaptation with only a few labeled source samples and introduces the Nyström method to construct a plastic graph that shares similar geometric property with the target domain.
- 14
- 13
- 13
- 13
- 13
- 13
- 13
- High-level attributes modeling for indoor scenes classification13
A hypergraph learning algorithm based feature selection method for indoor scene classification that performs feature selection by hypergraph regularization, which not only considers the interaction among features but also the interaction between the feature selection heuristics and the corresponding classifier.
- SpliceMix: A Cross-Scale and Semantic Blending Augmentation Strategy for Multi-Label Image Classification12
This article introduces a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix, and provides a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the potential of extending the authors' SpliceMix.
- 12
- 12
- 12
- A tensor framework for geosensor data forecasting of significant societal events12
A tensor pattern is used to model the geosensor data, based on which a tensor decomposition algorithm is then developed to estimate future values of geos sensor data, and a rank increasing strategy and a sliding window strategy are used to improve the prediction accuracy.
- 12
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- Online tracking based on efficient transductive learning with sample matching costs9
An efficient transductive learning for online tracking is proposed by utilizing the correspondences among the generated unlabeled and labeled samples, modeled by a matching costs function to achieve more efficient learning of representative separators.
- AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification8
An Adaptive Graph Mixup framework for semi-supervised node classification that introduces a subgraph-centric approach, which treats each subgraph similarly to how images are handled in Euclidean domains, thus facilitating a more natural integration of mixup into graph-based learning.
- Masked Graph Auto-Encoder Constrained Graph Pooling8
The experimental results reveal that MGAP has the capacity to consistently improve the performance of all the three node drop pooling models in the graph classification task and is a plug-and-play technique that can be directly adopted in the current node drop pooling methods.
- 8
- 8
- Online learning using projections onto shrinkage closed balls for adaptive brain-computer interface8
The effectiveness of the proposed adaptive projected sub-gradient method for adaptive EEG classification is revealed, making it a promising tool for on-device training and updating of wearable/portable BCIs, as well as for application in other related fields, such as EEG-based biometrics.
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 6
- Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning6
A Direct-Indirect Reasoning (DIR) method is proposed, which considers DR and IR as multiple parallel reasoning paths that are merged to derive the final answer and demonstrates that this method significantly outperforms all the original methods.
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- Multimodal Feature Analysis for Surgery Duration Predication5
The proposed multimodal feature fusion method outperforms the second competitor in terms of MAE, RMSE, MAPE, MAPE, and R2 by 4.6%, 5.9%, 6.0%, and 34.7%, respectively, demonstrating the proposed method’s superiority.
- Free-Form Composition Networks for Egocentric Action Recognition5
A free-form composition network (FFCN) that can simultaneously learn disentangled verb, preposition, and noun representations, and then use them to compose new samples in the feature space for rare classes of action videos is proposed.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- HAG-Former: A Temporal-Polarimetric Relationship Inference Network From Local to Global4
A novel Hybrid Attention-GRU Transformer (HAG-Former) model is introduced, which harnesses the power of pixel-level temporal-polarimetric change analysis and captures the dynamic variations in polarization scattering properties, thereby enhancing classification robustness and versatility.
- 4
- Deep Similarity Feature Learning for Person Re-identification4
This paper proposes a novel deep learning method called deep similarity feature learning DSFL to extract more effective deep features for image pairs and demonstrates the effectiveness and robustness of DSFL.
- 3
- 3
- 3
- CRmix: A regularization by clipping images and replacing mixed samples for imbalanced classification3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- RGD-VNet: Raw, Generative, and Discriminant Views Network for Boosting Postoperative Complication Prediction2
A novel framework named Raw, Generative, and Discriminant Views Network (RGD-VNet) for PCP that can better mine the internal connections between labeled and unlabeled data is proposed.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Cauchy estimator discriminant analysis for face recognition2
A novelty subspace learning algorithm for face recognition named Cauchy estimator discriminant analysis (CEDA) is proposed, based on the patch alignment framework (PAF) and Cauche estimator theory, and large errors caused by samples that are easy to confuse could be overcome.
- 2
- 2
- 2
- Skeleton correspondence construction and its applications in animation style reusing2
A novel method which can extract motions from existing animation sequences and retarget them to other cartoon characters and apply inverse kinematics to transform the motion onto the target skeleton is provided.
- 1
- 1
- ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs1
This work introduces a Progressive framework designed to offer flexible and on-demand trade-offs between inference cost and accuracy for GNN-to-MLP knowledge distillation (ProGMLP), demonstrating that ProGMLP maintains high accuracy while dynamically adapting to varying runtime scenarios, making it highly effective for deployment in diverse application settings.
- 1
- 1
- 1
- 1
- 1
- A Comprehensive Data Preprocessing Framework towards Improving Internet Chinese Medical Data Quality1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- JOTGLNet: A Guided Learning Network with Joint Offset Tracking for Multiscale Deformation Monitoring–
- –
- –
- –
- –
- –
- An Efficient Multi-prior Hybrid Approach for Consistent 3D Generation from Single Images–
Experimental results demonstrate the approach generates more consistent and realistic 3D assets than previous state-of-the-art methods in visual quality and quantitative metrics.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.