Zobrazeno 1 - 10
of 495
pro vyhledávání: '"Miao, Qiguang"'
Autor:
Liu, Jiaming, Kong, Linghe, Wu, Yue, Gong, Maoguo, Li, Hao, Miao, Qiguang, Ma, Wenping, Qin, Can
Existing 3D mask learning methods encounter performance bottlenecks under limited data, and our objective is to overcome this limitation. In this paper, we introduce a triple point masking scheme, named TPM, which serves as a scalable framework for p
Externí odkaz:
http://arxiv.org/abs/2409.17547
Graph clustering is a crucial task in network analysis with widespread applications, focusing on partitioning nodes into distinct groups with stronger intra-group connections than inter-group ones. Recently, contrastive learning has achieved signific
Externí odkaz:
http://arxiv.org/abs/2408.09790
Different from large-scale classification tasks, fine-grained visual classification is a challenging task due to two critical problems: 1) evident intra-class variances and subtle inter-class differences, and 2) overfitting owing to fewer training sa
Externí odkaz:
http://arxiv.org/abs/2407.04243
Deep Neural Networks (DNNs) are known to be vulnerable to both backdoor and adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct robustness problems and solved separately, since they belong to training-t
Externí odkaz:
http://arxiv.org/abs/2405.17929
Autor:
Liu, Kang, Ma, Zhuoqi, Kang, Xiaolu, Zhong, Zhusi, Jiao, Zhicheng, Baird, Grayson, Bai, Harrison, Miao, Qiguang
The automated generation of imaging reports proves invaluable in alleviating the workload of radiologists. A clinically applicable reports generation algorithm should demonstrate its effectiveness in producing reports that accurately describe radiolo
Externí odkaz:
http://arxiv.org/abs/2405.14905
Multi-scale Information Sharing and Selection Network with Boundary Attention for Polyp Segmentation
Polyp segmentation for colonoscopy images is of vital importance in clinical practice. It can provide valuable information for colorectal cancer diagnosis and surgery. While existing methods have achieved relatively good performance, polyp segmentati
Externí odkaz:
http://arxiv.org/abs/2405.11151
A radiology report comprises presentation-style vocabulary, which ensures clarity and organization, and factual vocabulary, which provides accurate and objective descriptions based on observable findings. While manually writing these reports is time-
Externí odkaz:
http://arxiv.org/abs/2405.09586
Autor:
Feng, Guanwen, Cheng, Haoran, Li, Yunan, Ma, Zhiyuan, Li, Chaoneng, Qian, Zhihao, Miao, Qiguang, Pun, Chi-Man
Implementing fine-grained emotion control is crucial for emotion generation tasks because it enhances the expressive capability of the generative model, allowing it to accurately and comprehensively capture and express various nuanced emotional state
Externí odkaz:
http://arxiv.org/abs/2402.01422
Publikováno v:
AAAI 2024
3D Single Object Tracking (SOT) stands a forefront task of computer vision, proving essential for applications like autonomous driving. Sparse and occluded data in scene point clouds introduce variations in the appearance of tracked objects, adding c
Externí odkaz:
http://arxiv.org/abs/2312.06117
We propose a new framework that formulates point cloud registration as a denoising diffusion process from noisy transformation to object transformation. During training stage, object transformation diffuses from ground-truth transformation to random
Externí odkaz:
http://arxiv.org/abs/2312.06063