Search
Search Results
-
Mining profitable alpha factors via convolution kernel learning
An automatic alpha factor mining method is proposed in this paper to assist expert traders in finding profitable alpha factors efficiently. Unlike...
-
Multi-task aided face recognition network with convolution kernel spatial collaboration
Most face recognition networks based on convolutional neural networks are easily affected by nonlinear factors of expression and posture, and the...
-
CKR-Calibrator: Convolution Kernel Robustness Evaluation and Calibration
Recently, Convolution Neural Networks (CNN) have achieved excellent performance in some areas of computer vision, including face recognition,... -
Learning local contextual features for 3D point clouds semantic segmentation by attentive kernel convolution
Unlike 2D images that are represented in regular grids, 3D point clouds are irregular and unordered, hence directly applying convolution neural...
-
KernelFlexSR: a self-adaptive super-resolution algorithm with multi-path convolution and residual network for dynamic kernel enhancement
Machine learning-based image super-resolution (SR) has garnered increasing research interest in recent years. However, there are two issues that have...
-
DS-UNeXt: depthwise separable convolution network with large convolutional kernel for medical image segmentation
Accurate automatic segmentation of medical images is required in computer-aided diagnosis systems in clinical medicine. Convolutional neural networks...
-
An adaptive bilateral filtering method based on improved convolution kernel used for infrared image enhancement
Smoothing filters are widely used in computer vision and computer graphics. Bilateral filtering is a typical edge-preserving filter, which has the...
-
Dynamic convolution-based image dehazing network
Convolutional neural networks use a convolutional kernel with static weights for processing non-uniform haze or dense fog, which may lead to...
-
PLKA-MVSNet: Parallel Multi-view Stereo with Large Kernel Convolution Attention
In this paper, we propose PLKA-MVSNet to address the remaining challenges in the in-depth estimation of learning-based multi-view stereo (MVS)... -
Falcon: lightweight and accurate convolution based on depthwise separable convolution
How can we efficiently compress convolutional neural network (CNN) using depthwise separable convolution, while retaining their accuracy on...
-
Attention-enabled adaptive Markov graph convolution
GNNs (Graph Neural Networks) have attracted increasing attention for their strong power on dealing with the graph structures. However, it remains a...
-
Multi-scale adaptive atrous graph convolution for point cloud analysis
Traditional GCNs have limitations due to fixed convolutional kernels with a narrow receptive field, which prevent them from adequately learning the...
-
Multiscale deformable convolution for RGB-FIR multimodal visibility estimation
Fog concentration, area, and boundary shape have a strong ability to distinguish various visibility ranges. However, standard convolution is...
-
Lane line detection and departure estimation in a complex environment by using an asymmetric kernel convolution algorithm
Deep learning has made tremendous advances in the domains of image segmentation and object classification. However, real-time lane line detection and...
-
Optimizing Winograd Convolution on GPUs via Partial Kernel Fusion
Convolution operations are the essential components in modern CNNs (Convolutional Neural Networks), which are also the most time-consuming. Several... -
Enhanced edge convolution-based spatial-temporal network for network traffic prediction
Accurately predicting network traffic is helpful for improving a variety of spatial-temporal data mining applications, such as intelligent traffic...
-
Im2win: An Efficient Convolution Paradigm on GPU
Convolution is the most time-consuming operation in deep neural network operations, so its performance is critical to the overall performance of the... -
Clustering using graph convolution networks
Graph convolution networks (GCNs) have emerged as powerful approaches for semi-supervised classification of attributed graph data. In this paper, we...
-
Pathological brain classification using multiple kernel-based deep convolutional neural network
Conventionally, fine-tuning or transfer learning using a pre-trained convolutional network is adopted to design a classifier. However, when the...
-
Point Cloud Registration Network Based on Convolution Fusion and Attention Mechanism
In 3D vision, point cloud registration remains a major challenge, especially in end-to-end deep learning, where low-quality point pairs will directly...