Shiqian Wu
YOU?
Author Swipe
View article: Quaternion-Based Robust PCA for Efficient Moving Target Detection and Background Recovery in Color Videos
Quaternion-Based Robust PCA for Efficient Moving Target Detection and Background Recovery in Color Videos Open
Moving target detection is a challenging computer vision task aimed at generating accurate segmentation maps in diverse in-the-wild color videos captured by static cameras. If backgrounds and targets can be simultaneously extracted and rec…
View article: Seeing Beyond Words: MatVQA for Challenging Visual-Scientific Reasoning in Materials Science
Seeing Beyond Words: MatVQA for Challenging Visual-Scientific Reasoning in Materials Science Open
The emergence of Multimodal Large Language Models (MLLMs) that integrate vision and language modalities has unlocked new potentials for scientific reasoning, outperforming prior benchmarks in both natural language and coding domains. Curre…
View article: Research on Chaoyang Yingge Dance from the Perspective of Critical Heritage
Research on Chaoyang Yingge Dance from the Perspective of Critical Heritage Open
View article: Single image de-raining by multi-scale Fourier Transform network
Single image de-raining by multi-scale Fourier Transform network Open
Removing rain streaks from a single image presents a significant challenge due to the spatial variability of the streaks within the rainy image. While data-driven rain removal algorithms have shown promising results, they remain constraine…
View article: 基于透射式液晶显示屏的高反光表面三维重建方法
基于透射式液晶显示屏的高反光表面三维重建方法 Open
View article: Collateral Sensitivity to β-Lactam Antibiotics in Evolved Apramycin-Resistant MRSA
Collateral Sensitivity to β-Lactam Antibiotics in Evolved Apramycin-Resistant MRSA Open
Collateral sensitivity is an evolutionary trade-off for bacteria where acquiring resistance to one antibiotic results in an increased sensitivity to another antibiotic. This study was designed to evaluate the collateral sensitivity of meth…
View article: Unsupervised Learning Based Multi-Scale Exposure Fusion
Unsupervised Learning Based Multi-Scale Exposure Fusion Open
Unsupervised learning based multi-scale exposure fusion (ULMEF) is efficient for fusing differently exposed low dynamic range (LDR) images into a higher quality LDR image for a high dynamic range (HDR) scene. Unlike supervised learning, lo…
View article: Neural Augmentation Based Panoramic High Dynamic Range Stitching
Neural Augmentation Based Panoramic High Dynamic Range Stitching Open
Due to saturated regions of inputting low dynamic range (LDR) images and large intensity changes among the LDR images caused by different exposures, it is challenging to produce an information enriched panoramic LDR image without visual ar…
View article: Fast Noise Level Estimation via the Similarity within and between Patches
Fast Noise Level Estimation via the Similarity within and between Patches Open
Patch level-based noise level estimation (NLE) is often inaccurate and inefficient because of the harsh criteria required to select a small number of homogeneous patches. In this paper, a fast image NLE method based on a global search for …
View article: Outlier Detection by Energy Minimization in Quantized Residual Preference Space for Geometric Model Fitting
Outlier Detection by Energy Minimization in Quantized Residual Preference Space for Geometric Model Fitting Open
Outliers significantly impact the accuracy of geometric model fitting. Previous approaches to handling outliers have involved threshold selection and scale estimation. However, many scale estimators assume that the inlier distribution foll…
View article: Genetically predicted major depression causally increases the risk of temporomandibular joint disorders
Genetically predicted major depression causally increases the risk of temporomandibular joint disorders Open
Objective Observational studies have reported that mental disorders are comorbid with temporomandibular joint disorder (TMD). However, the causal relationship remains uncertain. To clarify the causal relationship between three common menta…
View article: Outlier Detection by Energy Minimization in Quantized Residual Preference Space for Geometric Model Fitting
Outlier Detection by Energy Minimization in Quantized Residual Preference Space for Geometric Model Fitting Open
Outliers seriously affect the accuracy in geometric model fitting. Previous works in coping with outliers involve threshold selection and scale estimation. However most scale estimators suppose the inlier distribution as a Gaussian model, …
View article: LERE: Learning-Based Low-Rank Matrix Recovery with Rank Estimation
LERE: Learning-Based Low-Rank Matrix Recovery with Rank Estimation Open
A fundamental task in the realms of computer vision, Low-Rank Matrix Recovery (LRMR) focuses on the inherent low-rank structure precise recovery from incomplete data and/or corrupted measurements given that the rank is a known prior or acc…
View article: Single Image De-Raining by Multi Scale Fourier Transform Network
Single Image De-Raining by Multi Scale Fourier Transform Network Open
View article: 基于邻接跳变德布鲁因序列的结构光编解码算法
基于邻接跳变德布鲁因序列的结构光编解码算法 Open
德布鲁因序列常被用于结构光条纹的编码,但是序列中相邻的相同码元会导致在相同颜色区域内难以确定码元个数以及每个码元的确切编码范围。为了解决这一问题,提出一种邻接跳变德布鲁因序列,该序列在保留子序列唯一性的基础上保证了相邻码元的相异性。首先,证明了所提出序列的存在性,并给出了其生成方式。然后,将该序列用于相位周期级次编码,结合正弦相移条纹设计了一种彩色条纹编码方法。在解码阶段,按颜色通道分别提取、计算得到包裹相位和相位周期级次,最终获得展开相位。实验结果表明,所提方法与传统相移…
View article: Adjacency-hopping de Bruijn Sequences for Non-repetitive Coding
Adjacency-hopping de Bruijn Sequences for Non-repetitive Coding Open
A special type of cyclic sequences named adjacency-hopping de Bruijn sequences is introduced in this paper. It is theoretically proved the existence of such sequences, and the number of such sequences is derived. These sequences guarantee …
View article: Part Aware Contrastive Learning for Self-Supervised Action Recognition
Part Aware Contrastive Learning for Self-Supervised Action Recognition Open
In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represent…
View article: Genome-based analysis for the biosynthetic potential of Streptomyces sp. FIM 95-F1 producing antifungal antibiotic Scopafungin
Genome-based analysis for the biosynthetic potential of Streptomyces sp. FIM 95-F1 producing antifungal antibiotic Scopafungin Open
Background: Marine microbial members of the genus Streptomyces are an excellent source for novel secondary metabolites. However, publicly available complete genome sequences of marine streptomycetes are still limited. Here, 16S rRNA phylog…
View article: Single Image Deraining via Feature-based Deep Convolutional Neural Network
Single Image Deraining via Feature-based Deep Convolutional Neural Network Open
It is challenging to remove rain-steaks from a single rainy image because the rain steaks are spatially varying in the rainy image. Although the CNN based methods have reported promising performance recently, there are still some defects, …
View article: Part Aware Contrastive Learning for Self-Supervised Action Recognition
Part Aware Contrastive Learning for Self-Supervised Action Recognition Open
In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represent…
View article: A Hybrid Method for Implicit Intention Inference Based on Punished-Weighted Naïve Bayes
A Hybrid Method for Implicit Intention Inference Based on Punished-Weighted Naïve Bayes Open
Gaze-based implicit intention inference provides a new human-robot interaction for people with disabilities to accomplish activities of daily living independently. Existing gaze-based intention inference is mainly implemented by the data-d…
View article: 基于相移轮廓术的多核异构三维测量系统
基于相移轮廓术的多核异构三维测量系统 Open
在充分兼顾嵌入式三维测量系统对高效性、集成性、通用性以及灵活性等需求的基础上，设计了一种由3个异构核心构成的结构光三维测量系统架构。该多核异构架构层次清晰、结构灵活、通用性强，能兼容多种通用接口的光学器件（相机、投影仪等）。在此架构基础上，结合现场可编程门阵列并行流水优化方法，设计并实现了一种涵盖相位解调、解包裹以及相位深度映射等模块的全流程结构光三维测量系统。实验结果表明，所提方法在测量精度与传统PC平台相当的情况下，大大提高了测量效率，处理13幅1280×800分辨率的…
View article: Adaptive Single Low-Light Image Enhancement by Fractional Stretching in Logarithmic Domain
Adaptive Single Low-Light Image Enhancement by Fractional Stretching in Logarithmic Domain Open
Low-light image enhancement is a challenging task that aims to improve the visibility and quality of images captured in dark environments. However, existing methods often introduce undesirable artifacts such as color distortion, halo effec…
View article: Single Image Deraining via Rain-Steaks Aware Deep Convolutional Neural Network
Single Image Deraining via Rain-Steaks Aware Deep Convolutional Neural Network Open
It is challenging to remove rain-steaks from a single rainy image because the rain steaks are spatially varying in the rainy image. This problem is studied in this paper by combining conventional image processing techniques and deep learni…
View article: Dual-Scale Single Image Dehazing Via Neural Augmentation
Dual-Scale Single Image Dehazing Via Neural Augmentation Open
Model-based single image dehazing algorithms restore haze-free images with sharp edges and rich details for real-world hazy images at the expense of low PSNR and SSIM values for synthetic hazy images. Data-driven ones restore haze-free ima…
View article: A Content-Aware Non-Local Means Method for Image Denoising
A Content-Aware Non-Local Means Method for Image Denoising Open
Parameter setting and information redundancy are essential issues for the non-local means (NLM) algorithm. This paper introduces a new factor based on the Hessian matrix to adapt the smoothing parameter. Then, a strategy is proposed to imp…
View article: SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition
SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition Open
Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised …
View article: Hessian-based weighted guided image filtering
Hessian-based weighted guided image filtering Open
Guided image filtering (GIF) is a popular edge-preserving smoothing technique, and the regularization parameter selection plays an important role in the performance of GIF. In this paper, we propose a new guided image filter based on Hessi…
View article: A 6D Pose Estimation for Robotic Bin-Picking Using Point-Pair Features with Curvature (Cur-PPF)
A 6D Pose Estimation for Robotic Bin-Picking Using Point-Pair Features with Curvature (Cur-PPF) Open
Pose estimation is a particularly important link in the task of robotic bin-picking. Its purpose is to obtain the 6D pose (3D position and 3D posture) of the target object. In real bin-picking scenarios, noise, overlap, and occlusion affec…
View article: A gamma self‐correction method via chord distribution coding in fringe projection profilometry
A gamma self‐correction method via chord distribution coding in fringe projection profilometry Open
This paper presents a gamma self‐correction method via chord distribution coding to eliminate the system's gamma effect. For this purpose, the prior gamma‐Gaussian characteristic value, which is extracted by chord distribution Gaussian fit…