障碍物
发表于 2025-3-30 09:10:54
Reverse Attention U-Net for Brain Grey Matter Nuclei Segmentation,ns while highlighting background, which guides the network to explore the missing nuclei parts sequentially. Experimental results on our nuclei dataset imply that the RAU-Net performs favorably against the state-of-the-art methods.
有权威
发表于 2025-3-30 12:24:53
http://reply.papertrans.cn/17/1625/162406/162406_52.png
食道
发表于 2025-3-30 16:56:19
Small-Object Detection with Super Resolution Embedding,f-the-art detector (YOLOv3). Extensive experiments on a public (car overhead with context) dataset and another self-assembled airport surface dataset show superior performance of our method compared to the standalone state-of-the-art object detectors.
contradict
发表于 2025-3-31 00:27:11
http://reply.papertrans.cn/17/1625/162406/162406_54.png
Ringworm
发表于 2025-3-31 04:26:20
Autoencoder-Based Baseline Parameterized by Central Limit Theorem for ICS Cybersecurity,d has stable interactive features. In the paper, we analyze the ICS network interaction and construct a parameterized baseline by an autoencoder to detect the intrusion. The experiment with an open ICS dataset shows that this baseline could achieve intrusion detection accuracy above 90% and the false alarm rate below 5%.
熔岩
发表于 2025-3-31 06:33:13
Image Compression Based on Mixed Matrix Decomposition of NMF and SVD,work on images. The experimental results demenstrated that this approach based on mixed matrix decomposition had a CR with larger dynamic range through flexible parameter adjustment and the PSNR of the restored image is 29 dB–36 dB. It verifiy that this method is effective.
Peculate
发表于 2025-3-31 12:01:10
Information Extraction of Air-Traffic Control Instructions via Pre-trained Models,ts of handcraft annotations. The large scale pre-trained model (PTMs) can solve this problem by “pre-training” and “fine-tuning”. This paper proposes: 1) pre-trained models to extract information from few scale ATC instructions; 2) the probing task to find which layer of model achieves the best performance of information extraction task.
ethereal
发表于 2025-3-31 16:40:35
Medical Image Segmentation Using Transformer,amed TransHarDNet. HarDNet, which is a low memory traffic CNN. We combine it as backbone with Transformer. Our network enables the global semantic context information and low-level spatial details of the input image to be captured more effectively. We evaluate the effectiveness of the proposed network on five medical image datasets.
大气层
发表于 2025-3-31 19:31:52
http://reply.papertrans.cn/17/1625/162406/162406_59.png
myalgia
发表于 2025-3-31 22:45:00
http://reply.papertrans.cn/17/1625/162406/162406_60.png