Search Results for author:
Found 55 papers, 24 papers with code
Image Denoising via Style Disentanglement
This leads to the separation of clean contents from noise, effectively denoising the image.
Latent Degradation Representation Constraint for Single Image Deraining
Since rain streaks show a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining.
Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoising
By considering the deep variational image posterior with a Gaussian form, score priors are extracted based on easily accessible minimum MSE Non-$i. i. d$ Gaussian denoisers and variational samples, which in turn facilitate optimizing the variational image posterior.
ELFNet: Evidential Local-global Fusion for Stereo Matching
Although existing stereo matching models have achieved continuous improvement, they often face issues related to trustworthiness due to the absence of uncertainty estimation.
Empower Your Model with Longer and Better Context Comprehension
Recently, with the emergence of numerous Large Language Models (LLMs), the implementation of AI has entered a new era.
MUVF-YOLOX: A Multi-modal Ultrasound Video Fusion Network for Renal Tumor Diagnosis
In addition, we design an object-level temporal aggregation (OTA) module that can automatically filter low-quality features and efficiently integrate temporal information from multiple frames to improve the accuracy of tumor diagnosis.
Multi-IMU with Online Self-Consistency for Freehand 3D Ultrasound Reconstruction
Ultrasound (US) imaging is a popular tool in clinical diagnosis, offering safety, repeatability, and real-time capabilities.
D3L: Decomposition of 3D Rotation and Lift from 2D Joint to 3D for Human Mesh Recovery
However, these methods present rotation semantic ambiguity, rotation error accumulation, and shape estimation overfitting, which also leads to errors in the estimated pose.
Human-imperceptible, Machine-recognizable Images
Massive human-related data is collected to train neural networks for computer vision tasks.
HQDec: Self-Supervised Monocular Depth Estimation Based on a High-Quality Decoder
To this end, we propose a high-quality decoder (HQDec), with which multilevel near-lossless fine-grained information, obtained by the proposed adaptive axial-normalized position-embedded channel attention sampling module (AdaAxialNPCAS), can be adaptively incorporated into a low-resolution feature map with high-level semantics utilizing the proposed adaptive information exchange scheme.
Diffusion Probabilistic Priors for Zero-Shot Low-Dose CT Image Denoising
The results demonstrate that our method outperforms the state-of-the-art unsupervised method and surpasses several supervised deep learning-based methods.
No-Reference Point Cloud Quality Assessment via Weighted Patch Quality Prediction
Then, we gather the features of all the patches of a point cloud for correlation analysis, to obtain the correlation weights.
Ranked #1 on
Point Cloud Quality Assessment
on WPC
Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition
Unifying the MSST module, a multi-scale spatial–temporal convolutional neural network (MSSTNet) is proposed to capture high-level spatial–temporal semantic features for action recognition.
Ranked #2 on
Skeleton Based Action Recognition
on UAV-Human
Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes.
Class-Aware Patch Embedding Adaptation for Few-Shot Image Classification
This could significantly reduce the efficiency of a large family of few-shot learning algorithms, which have limited data and highly rely on the comparison of image patches.
Spectral Bayesian Uncertainty for Image Super-Resolution
In this paper, we propose to quantify spectral Bayesian uncertainty in image SR. To achieve this, a Dual-Domain Learning (DDL) framework is first proposed.
CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose
Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos.
$\textbf{P$^2$A}$: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
Personalized Diagnostic Tool for Thyroid Cancer Classification using Multi-view Ultrasound
Furthermore, finding an optimal way to integrate multi-view information also relies on the experience of clinicians and adds further difficulty to accurate diagnosis.
A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.
Structure Unbiased Adversarial Model for Medical Image Segmentation
It consists of a spatial transformation block followed by an intensity distribution rendering module.
HASA: Hybrid Architecture Search with Aggregation Strategy for Echinococcosis Classification and Ovary Segmentation in Ultrasound Images
The hybrid framework consists of a pre-trained backbone and several searched cells (i. e., network building blocks), which takes advantage of the strengths of both NAS and the expert knowledge from existing convolutional neural networks.
Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis
Our main contributions include: 1) we present the first work that can synthesize realistic B-mode US images with high-resolution and customized texture editing features; 2) to enhance structural details of generated images, we propose to introduce auxiliary sketch guidance into a conditional GAN.
Text-to-Image Synthesis Based on Object-Guided Joint-Decoding Transformer
Object-guided text-to-image synthesis aims to generate images from natural language descriptions built by two-step frameworks, i. e., the model generates the layout and then synthesizes images from the layout and captions.
MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation
Very often, the pose is estimated after the face detection.
Proxy-bridged Image Reconstruction Network for Anomaly Detection in Medical Images
To mitigate this problem, in this paper, we propose a novel Proxy-bridged Image Reconstruction Network (ProxyAno) for anomaly detection in medical images.
SM-SGE: A Self-Supervised Multi-Scale Skeleton Graph Encoding Framework for Person Re-Identification
In this paper, we for the first time propose a Self-supervised Multi-scale Skeleton Graph Encoding (SM-SGE) framework that comprehensively models human body, component relations, and skeleton dynamics from unlabeled skeleton graphs of various scales to learn an effective skeleton representation for person Re-ID.
VEGN: Variant Effect Prediction with Graph Neural Networks
In contrast, we propose VEGN, which models variant effect prediction using a graph neural network (GNN) that operates on a heterogeneous graph with genes and variants.
Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification
To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID.
CPP-Net: Context-aware Polygon Proposal Network for Nucleus Segmentation
Each polygon is represented by a set of centroid-to-boundary distances, which are in turn predicted by features of the centroid pixel for a single nucleus.
CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging
Automated detection of curvilinear structures, e. g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases.
A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification
This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.
Self-Supervised Gait Encoding with Locality-Aware Attention for Person Re-Identification
Unlike previous methods, we for the first time propose a generic gait encoding approach that can utilize unlabeled skeleton data to learn gait representations in a self-supervised manner.
Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images
In the end, we further utilize the reconstructed image to extract the structure and measure the difference between structure extracted from original and the reconstructed image.
Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised manner.
Deep Potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors
It has been a challenge to accurately simulate Li-ion diffusion processes in battery materials at room temperature using {\it ab initio} molecular dynamics (AIMD) due to its high computational cost.
Computational Physics Materials Science Chemical Physics
RiFeGAN: Rich Feature Generation for Text-to-Image Synthesis From Prior Knowledge
Text-to-image synthesis is a challenging task that generates realistic images from a textual sequence, which usually contains limited information compared with the corresponding image and so is ambiguous and abstractive.
Real-time Semantic Segmentation via Spatial-detail Guided Context Propagation
In SGCPNet, we propose the strategy of spatial-detail guided context propagation.
Unsupervised Deformable Medical Image Registration via Pyramidal Residual Deformation Fields Estimation
In fact, due to the limitation of the receptive field, the 3 x 3 kernel has difficulty in covering the corresponding features at high/original resolution.
BioNet: Infusing Biomarker Prior into Global-to-Local Network for Choroid Segmentation in Optical Coherence Tomography Images
Firstly, our method trains a biomarker prediction network to learn the features of the biomarker.
Sparse-GAN: Sparsity-constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Image
With the development of convolutional neural network, deep learning has shown its success for retinal disease detection from optical coherence tomography (OCT) images.
Dense Dilated Network with Probability Regularized Walk for Vessel Detection
Many methods have been proposed for vessel detection.
The Channel Attention based Context Encoder Network for Inner Limiting Membrane Detection
The optic disc segmentation is an important step for retinal image-based disease diagnosis such as glaucoma.
SkrGAN: Sketching-rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis
Generative Adversarial Networks (GANs) have the capability of synthesizing images, which have been successfully applied to medical image synthesis tasks.
CE-Net: Context Encoder Network for 2D Medical Image Segmentation
In this paper, we propose a context encoder network (referred to as CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation.
Ranked #1 on
Optic Disc Segmentation
on Messidor
Towards Query Efficient Black-box Attacks: An Input-free Perspective
First, we initialize an adversarial example with a gray color image on which every pixel has roughly the same importance for the target model.
Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading
To considering the relationships of images with different stages, we propose a \textbf{Multi-Task} learning strategy which predicts the label with both classification and regression.
Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image
Specifically, a novel Disc-aware Ensemble Network (DENet) for automatic glaucoma screening is proposed, which integrates the deep hierarchical context of the global fundus image and the local optic disc region.
Structure-preserving Guided Retinal Image Filtering and Its Application for Optic Disc Analysis
It often obscures the details in the retinal images and posts challenges in retinal image processing and analysing tasks.
Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks
Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible.
Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation
The proposed M-Net mainly consists of multi-scale input layer, U-shape convolutional network, side-output layer, and multi-label loss function.
Ranked #4 on
Optic Disc Segmentation
on REFUGE
Learning Scene-specific Object Detectors Based on a Generative-Discriminative Model with Minimal Supervision
In this paper, the proposed framework takes a remarkably different direction to resolve the multi-scene detection problem in a bottom-up fashion.
Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition
Since human actions can be characterized by multiple feature representations extracted from Kinect and inertial sensors, multiview features must be encoded into a unified space optimal for human action recognition.
A Low-Dimensional Step Pattern Analysis Algorithm With Application to Multimodal Retinal Image Registration
These customized step patterns are robust to non-linear intensity changes, which are well-suited for multimodal retinal image registration.
Multiview Hessian Discriminative Sparse Coding for Image Annotation
In particular, mHDSC exploits Hessian regularization to steer the solution which varies smoothly along geodesics in the manifold, and treats the label information as an additional view of feature for incorporating the discriminative power for image annotation.
