Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks95 from public data
- 223
- Hierarchical Dense Correlation Distillation for Few-Shot Segmentation186
This work designs Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture and proposes a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation.
- 97
- 79
- Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction77
This paper proposes a new paradigm, named Historical Object Prediction (HoP), for multi-view 3D detection to leverage temporal information more effectively and can be easily incorporated into state-of-the-art BEV detection frameworks, including BEVFormer and BEVDet series.
- A Deep Transfer Learning Network for Structural Condition Identification with Limited Real-World Training Data77
The results show that even though the training data are from a different domain and with different types of labels, intrinsic physics can be learned through the pretraining process, and the TL results can be clearly improved, with the identification accuracy increasing from 81.8% to 89.1%.
- A Labeling Method for Financial Time Series Prediction Based on Trends77
Experiments showed that the proposed continuous trend labeling method is a much better state-of-the-art labeling method in terms of classification accuracy and some other classification evaluation metrics, and proved that deep learning models such as LSTM and GRU are more suitable for dealing with the prediction of financial time series data.
- Fitting smoothing splines to time-indexed, noisy points on nonlinear manifolds60
This paper derives certain geometrical elements, namely the exponential map and its inverse, parallel transport of tangents, and the curvature tensor, on these manifolds that are needed in the gradient-based search for smoothing splines.
- Elastic Functional Coding of Riemannian Trajectories59
The TSRVF representation, and accompanying statistical summaries of Riemannian trajectories, are utilized to extend existing coding methods such as PCA, KSVD and Label Consistent KSVD to Riemanni trajectories or more generally to R Siemannian functions, showing that such coding efficiently captures trajectories in applications such as action recognition, stroke rehabilitation, visual speech recognition, clustering and diverse sequence sampling.
- Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks46
VLU-Net is the first all-in-one DUN framework and outperforms current leading one-by-one and all-in-one end- to-end methods by 3.74 dB on the SOTS dehazing dataset and 1.70 dB on the Rain100L deraining dataset.
- 46
- 40
- Semi-supervised medical image segmentation via weak-to-strong perturbation consistency and edge-aware contrastive representation38
This paper proposes an innovative framework that effectively leverages unlabeled data to improve segmentation performance, especially in edge regions and introduces a weak-to-strong perturbation strategy with corresponding feature-perturbed consistency loss to efficiently utilize unlabeled data.
- Two-Person Graph Convolutional Network for Skeleton-Based Human Interaction Recognition38
A novel unified two-person graph to represent inter-body and intra-body correlations between joints and several graph labeling strategies are designed to supervise the model to learn discriminant spatial-temporal interactive features.
- 36
- Statistical analysis of manual segmentations of structures in medical images34
This paper uses statistical shape theory to generate joint inferences and analyze data generated by a new paradigm in medical image segmentation, termed Citizen Science, which involves a volunteer effort from multiple, possibly non-expert, human participants to estimate anatomical boundaries in the form of planar closed curves.
- 32
- A BERT Based Method for Continuous Estimation of Cross-Subject Hand Kinematics From Surface Electromyographic Signals32
The proposed method based on Bidirectional Encoder Representation from Transformers (BERT) structure to predict the movement of hands from the root mean square (RMS) feature of the sEMG signal following $\mu $ -law normalization achieved state-of-the-art performance in cross-subject evaluation as well as high performance in subject-specific tests on the Ninapro dataset.
- 31
- 31
- Rate-Invariant Analysis of Covariance Trajectories29
This work represents covariance trajectories using transported square-root vector fields, constructed by parallel translating scaled-velocity vectors of trajectories to their starting points, using a natural Riemannian metric on this vector bundle, which leads to a rate-invariant analysis of trajectory analysis.
- Online and offline based load balance algorithm in cloud computing27
A new load balancing method combined with the advantage of online and offline load balancing algorithms are proposed in this paper and good performance shows the efficiency of the proposed method.
- 24
- 24
- Detection, classification and estimation of individual shapes in 2D and 3D point clouds24
A generalized likelihood ratio test for detecting a shape in a point cloud, based on optimizing over some unknown parameters, including the pose and scale associated with hypothesized objects, and an empirical evaluation of the log-likelihood ratio distribution is developed.
- A Stochastic Shortest Path Algorithm for Optimizing Spaced Repetition Scheduling23
A spaced repetition scheduler guaranteed to minimize the review cost by a stochastic shortest path algorithm that has been successfully deployed in the online language-learning app MaiMemo to help millions of students.
- Feature Distribution Matching by Optimal Transport for Effective and Robust Coreset Selection20
It is found that the closer the feature distribution of the coreset is to that of the entire dataset, the better the generalization performance of the coreset, particularly under extreme pruning.
- 19
- 19
- 17
- Multi-view Ensemble Clustering via Low-rank and Sparse Decomposition: From Matrix to Tensor16
Two novel multi-view ensemble clustering methods are proposed, which tangibly decrease computational complexity and adopt the alternating direction method of multipliers to solve two convex models by dividing them into several subproblems with closed-form solution.
- 16
- Spatially Coherent Interpretations of Videos Using Pattern Theory14
A combinatorial approach that handles known challenges—appearance variabilities, errors in object labels, object clutter, simultaneous events, etc—without the need for exponentially-large (labeled) training data is presented.
- Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing12
A lightweight Mamba-based binary neural network designed for efficient and high-performing demosaicing of HybridEVS RAW images and a binarized Mamba (Bi-Mamba), which binarizes all projections while retaining the core Selective Scan in full precision are proposed.
- KAN or MLP? Point Cloud Shows the Way Forward10
This work proposes PointKAN, which applies Kolmogorov-Arnold Network (KAN) to point cloud analysis tasks to investigate their efficacy in hierarchical feature representation and highlights the unique advantages of KAN over MLP in point cloud analysis and opens new avenues for research in point cloud understanding.
- 10
- A distance weighted linear regression classifier based on optimized distance calculating approach for face recognition10
A novel algorithm named the Distance Weighted Regression Classifier (DWLRC), based on the theory that images in the same class will also belong to same linear subspace and they can be represented through a linear equation, which can be used for face recognition under different expression and illumination conditions through a distance weighted method.
- 10
- Cross-Subject Lifelong Learning for Continuous Estimation From Surface Electromyographic Signal9
The proposed Cross-Subject Lifelong Network incorporates a novel lifelong learning approach, maintaining the patterns of sEMG signals across a varied user population and across different temporal scales, and enhances the generalization of acquired patterns, making it applicable to various individuals and temporal contexts.
- MIPI 2024 Challenge on Demosaic for Hybridevs Camera: Methods and Results9
A total of 110 participants from both industrial and academic backgrounds contributed many valuable solutions to address the difficulty of the restoration of HybridEVS’s raw data, thus raising the reconstructed performance to a new height.
- Atrial Fibrillation Detection from Compressed ECG Measurements for Wireless Body Sensor Network8
The experiment results well demonstrate that the on-device AF detection algorithm can approach the performance of those implemented on the raw signals.
- 8
- 8
- Multi-feature based fire detection in video8
A new mathematical tool based on fractal dimensions, along with the chromatic features, to make a raw localization of fire regions first is presented and shown how they can be applied to fire detection to improve the fire detection performance.
- RV-ESA: A novel computer-aided elastic shape analysis system for retinal vessels in diabetic retinopathy7
A novel computer-aided shape analysis system for retinal vessels is provided and it is shown that there is a certain correlation between the variation of retinal vascular shape and DR progression, and the Graph PCA scores ofretinal vessels are negatively correlated with DR grades.
- Pattern theory for representation and inference of semantic structures in videos7
A combinatorial approach to represent and infer semantic interpretations of video contents using tools from Grenanders pattern theory, able to obtain 20% higher classification rates, compared to a purely machine learning-based baseline, despite artificial insertion of low-level processing errors.
- 6
- 6
- BrainCognizer: Brain Decoding with Human Visual Cognition Simulation for fMRI-to-Image Reconstruction5
This work proposes BrainCognizer, a novel brain decoding model inspired by human visual cognition, which explores multilevel semantics and correlations without fine-tuning of generative models and outperforms state-of-the-art approaches on multiple evaluation metrics.
- SAH-SCI: Self-supervised Adapter for Efficient Hyperspectral Snapshot Compressive Imaging5
A novel approach that combines spectral and spatial adaptation to enhance an image model’s capacity for spatial-spectral reasoning is proposed, offering simplicity and adaptability to any end-to-end or un-folding methods.
- Double High-Order Correlation Preserved Robust Multi-View Ensemble Clustering5
This work proposes a novel Double High-Order Correlation Preserved Robust Multi-View Ensemble Clustering (DC-RMEC) method, which preserves the high-order inter-view correlation and thehigh-order correlation of original data simultaneously, and develops a unified framework to jointly optimize the representation tensor and the result matrix.
- 5
- Elastic Shape Analysis of Functions, Curves and Trajectories4
A Riemannian framework for geometric shape analysis of curves, functions, and trajectories on nonlinear manifolds is presented using several applications from computer vision and medical imaging including the analysis of curve growth, human growth, bird migration patterns, and human actions from video surveillance images and skeletons from depth images.
- 3
- 3
- 3
- 3
- Statistical analysis of the community lockdown for COVID-19 pandemic3
A statistical analysis of the effectiveness of community lockdown measures based on the Agent-Level Pandemic Simulation (ALPS) model is performed and the model has been evaluated using the real data of COVID-19.
- 3
- Lightweight Quad Bayer HybridEVS Demosaicing via State Space Augmented Cross-Attention2
TSANet demonstrates excellent demosaicing performance on both simulated and real data of HybridEVS while maintaining a lightweight model, averaging better results than the previous state-of-the-art method DemosaicFormer across seven diverse datasets in both PSNR and SSIM, while respectively reducing parameter and computation costs by $1.86 and $3.29.
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- Elastic statistical analysis of interval-valued time series1
The proposed phase-amplitude separation method provides a new way of PCA and modeling for interval-valued time series, and enables shape clustering of interval- valued time series.
- Kernel nearest-farthest subspace classifier for face recognition1
A novel classifier named Kernel Nearest-Farthest Subspace (KNFS) classifier is proposed for face recognition that can make the sample points to be linear separable by utilizing the kernel function to map linear inseparable sample points in low-dimensional space to high-dimensional kernel space.
- 1
- –
- –
- –
- –
- –
- Enhancing Local Cognition of CLIP for Training-Free Open Vocabulary Semantic Segmentation–
This work proposes CLIPtrase, a novel training-free semantic segmentation strategy, which enhances local cognition through recalibrated self-correlation among patches and quadrant mask ensemble strategy, which demonstrates significant improvements in segmentation accuracy and the ability to maintain semantic coherence between objects.
- –
- –
- –
- –
- Gradient of White Matter Functional Variability via fALFF Differential Identifiability–
Fractional amplitude of low-frequency fluctuation (fALFF) is introduced to measure the intensity of spontaneous neural activity and analyze functional variability in WM and it is discovered that WM functional variability demonstrates a spatial gradient ascending from the brainstem to the cortex by hypothesis testing, which aligns well with the evolutionary expansion.
- SlowFast-SCI: Slow-Fast Deep Unfolding Learning for Spectral Compressive Imaging–
SlowFast-SCI is the first testtime adaptation-driven deep unfolding framework for efficient, self-adaptive spectral reconstruction, and its dual-stage design unites offline robustness with on-the-fly per-sample calibration-yielding over 70% reduction in parameters and FLOPs.
- Electroconvulsive Therapy Regulates the Interhemispheric Functional Connectivity of the Dorsomedial Prefrontal Cortex in Depressive Patients: Evidence from 2 Independent Samples–
Results show that ECT regulates interhemispheric functional connectivity in depressed patients, and significantly increases the VMHC values in the dmPFC, a validated methodology for investigating interhemispheric coordination.
- –
- –
- –
- –
- –
- Application Research of Ripley’s K-function in Point Cloud Data Shape Analysis–
Judging by the randomness of the experiment, Ripley’s K-function has a considerable effect on judging existence of point cloud data shape through relevant experimental verification analysis.
- Statistical Analysis of Trajectories of Multi-Modality Data–
A proper Riemannian metric is proposed, which is a weighted average of distances on product spaces that allows for joint comparison and registration of multi-modality data.
- Video Event Understanding with Pattern Theory–
This work presents a combinatorial approach based on Grenander’s pattern theory, which aims to generate high-probability interpretations given a set of features and describes how to leverage the success of these methods into building a detailed semantic description of a complex event.
- Shape Estimation from 3D Point Clouds–
This work addresses shape estimation using a template object under a fully statistical model, where the data is assumed to be modeled using a Poisson process on the object’s boundary (surfaces), corrupted by additive noise and a clutter process.
- –
- –
- Joint Registration and Shape Analysis of Curves and Surfaces–
Novel mathematical representations are discussed, of both curves and surfaces, that reduce shape spaces to standard Hilbert spaces and many of the existing algorithmic tools can be applied.
Publication data from OpenAlex; 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.