8,414 Result(s)
within
Le**g Wang
Pattern Recognition
-
Article
Hugs Bring Double Benefits: Unsupervised Cross-Modal Hashing with Multi-granularity Aligned Transformers
Unsupervised cross-modal hashing (UCMH) has been commonly explored to support large-scale cross-modal retrieval of unlabeled data. Despite promising progress, most existing approaches are developed on convolut...
-
Article
ConDA: state-based data augmentation for context-dependent text-to-SQL
The context-dependent text-to-SQL task has profound real-world implications, as it facilitates users in extracting knowledge from vast databases, which allows users to acquire the information interactively for...
-
Article
Open AccessTraining Object Detectors from Scratch: An Empirical Study in the Era of Vision Transformer
Modeling in computer vision has long been dominated by convolutional neural networks (CNNs). Recently, in light of the excellent performance of self-attention mechanism in the language field, transformers tail...
-
Article
A general framework for improving cuckoo search algorithms with resource allocation and re-initialization
Cuckoo search (CS) has currently become one of the most favorable meta-heuristic algorithms (MHAs). In this article, a simple yet effective framework is proposed for CS algorithms to reinforce their performanc...
-
Article
Fast Shrinking parents-children learning for Markov blanket-based feature selection
High-dimensional data leads to degraded performance of machine learning algorithms and weak generalization of models, so feature selection is of great importance. In a Bayesian network (BN), the Markov blanket...
-
Article
Combining core points and cluster-level semantic similarity for self-supervised clustering
Contrastive learning utilizes data augmentation to guide network training. This approach has attracted considerable attention for clustering, object detection, and image segmentation. However, previous studies...
-
Article
Cross-Modal Fusion and Progressive Decoding Network for RGB-D Salient Object Detection
Most existing RGB-D salient object detection (SOD) methods tend to achieve higher performance by integrating additional modules, such as feature enhancement and edge generation. There is no doubt that these mo...
-
Article
Dual flow fusion graph convolutional network for traffic flow prediction
In recent decades, motor vehicle ownership has increased worldwide year by year, which causes that the accurate prediction of traffic flow on urban road networks becomes more important. However, the dual depen...
-
Article
Dual stage black-box adversarial attack against vision transformer
Relying on wide receptive fields, Vision Transformers (ViTs) are more robust than Convolutional Neural Networks (CNNs). Consequently, some transfer-based attack methods that perform well on CNNs perform poorly...
-
Article
Robust Heterogeneous Model Fitting for Multi-source Image Correspondences
Traditional feature detection and description methods, such as scale-invariant feature transform, are susceptible to nonlinear radiation distortions (NRDs) and geometric distortions (GDs), which in turn genera...
-
Article
A Survey on Global LiDAR Localization: Challenges, Advances and Open Problems
Knowledge about the own pose is key for all mobile robot applications. Thus pose estimation is part of the core functionalities of mobile robots. Over the last two decades, LiDAR scanners have become the stand...
-
Article
An evolutionary feature selection method based on probability-based initialized particle swarm optimization
Feature selection is a common data preprocessing technique that aims to construct better models by selecting the most predictive features. Existing particle swarm optimization-based feature selection algorithm...
-
Article
SplatFlow: Learning Multi-frame Optical Flow via Splatting
The occlusion problem remains a crucial challenge in optical flow estimation (OFE). Despite the recent significant progress brought about by deep learning, most existing deep learning OFE methods still struggl...
-
Article
Novel multi-label feature selection via label enhancement and relative maximal discernibility pairs
Multi-label feature selection is an effective solution to the multi-label data dimensionality disaster problem. However, there are few studies on multi-label feature selection considering label enhancement met...
-
Article
Deep bilinear Koopman realization for dynamics modeling and predictive control
The data-driven approaches based on the Koopman operator theory have promoted the analysis and control of the nonlinear dynamics by providing an equivalent Koopman-based linear system associated with nonlinear...
-
Article
A resource-efficient partial 3D convolution for gesture recognition
3DCNNs have shown impressive capabilities in extracting spatiotemporal features from videos. However, in practical applications, the numerous trainable parameters in most 3DCNN models result in longer latency ...
-
Article
CD-iNet: Deep Invertible Network for Perceptual Image Color Difference Measurement
Image color difference (CD) measurement, a crucial concept in color science and imaging technology, aims to quantify the perceived difference between two colors. Most widely recognized CD formulae are recommen...
-
Article
Multi-modal Prototypes for Open-World Semantic Segmentation
In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existin...
-
Article
Industrial product surface defect detection via the fast denoising diffusion implicit model
In the age of intelligent manufacturing, surface defect detection plays a pivotal role in the automated quality control of industrial products, constituting a fundamental aspect of smart factory evolution. Con...
-
Article
Exploiting Diffusion Prior for Real-World Image Super-Resolution
We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. Specifically, by employing our time-aware encoder, we can achieve ...
