说笑
发表于 2025-3-28 17:49:57
http://reply.papertrans.cn/28/2798/279737/279737_41.png
行乞
发表于 2025-3-28 18:48:50
An Image Dehazing Algorithm Based on Adaptive Correction and Red Dark Channel Priorch as halo effect, color distortion and so on. In view of the above problems, we proposes a method based on the red channel prior algorithm to estimate the transmission maps of different color channels. After defogging, it will reduce the brightness and contrast of the image, resulting in the loss o
GLIB
发表于 2025-3-29 02:26:07
http://reply.papertrans.cn/28/2798/279737/279737_43.png
粘土
发表于 2025-3-29 05:46:19
UAV Aerial Image Detection Based on Improved FCOS Algorithmer and the problem of positive and negative sample balance are improved. GIOU is used to improve the loss function, the training scale is modified and multi-scale training strategy is used. At the same time, because the pre-selection box is not used, the training parameter adjustment time is greatly
COLON
发表于 2025-3-29 09:54:56
FaceCode: An Artistic Face Image with Invisible Hyperlinkack and white blocks of QR code cannot attract users in social software, thus some popular software like Wechat beautify the QR code to improve its visual appeal. Inspired by the mentioned fact, this paper proposes a novel 2D image code named FaceCode. FaceCode is a Convolution Neural Network (CNN)
原谅
发表于 2025-3-29 12:44:44
Single Image Deraining via Multi-scale Gated Feature Enhancement Networkdeep-learning based algorithms are designed for single image rain steak removal, deraining performance is still limited due to the insufficient utilization of multi-scale features, which either fails to remove rain steaks completely or damages the original image content. In our paper, a novel derain
原始
发表于 2025-3-29 19:05:51
Cancelable Face Recognition with Mask methods of cancelable biometrics are implemented by irreversible transformation or encryption of biometrics. In this paper, we propose a method that we add a mask to face image to realize cancelable biometrics. We use relative entropy to study the statistical relationship between the face images wi
PARA
发表于 2025-3-29 23:09:25
http://reply.papertrans.cn/28/2798/279737/279737_48.png
冷淡一切
发表于 2025-3-30 02:19:09
http://reply.papertrans.cn/28/2798/279737/279737_49.png
值得尊敬
发表于 2025-3-30 04:43:46
Accelerated Object Detection for Autonomous Driving in CVIS Based on Pruned CNN Architecturegies based on pruned network has widely studied. More efficient pruned architecture can be accomplished by considering prior information like motion feature prediction (optical flow, etc.) to achieve optimized feature computing. With consideration of continuous features backward propagation methods,