Zobrazeno 1 - 10
of 1 727
pro vyhledávání: '"HU Qinghua"'
Publikováno v:
Guoji Yanke Zazhi, Vol 24, Iss 5, Pp 753-757 (2024)
Laser photocoagulation is one of the important methods for treating retinal diseases, and retinal laser technology continues to advance. For decades, researchers have been striving to find a laser treatment that can minimize tissue damage while achie
Externí odkaz:
https://doaj.org/article/b21a800aff4a4d02a7754bb14935d3fb
Publikováno v:
Dizhi lixue xuebao, Vol 29, Iss 1, Pp 1-20 (2023)
The geological circle has been studying the South China Ocean for 40 years. Based on the existing studies, the geological features of the middle Neogene South China Ocean and related geological structures and mineralization issues have been further u
Externí odkaz:
https://doaj.org/article/b078c94205144e3e8584e21c79c80514
Out-of-distribution (OOD) detection is crucial for ensuring reliable deployment of machine learning models. Recent advancements focus on utilizing easily accessible auxiliary outliers (e.g., data from the web or other datasets) in training. However,
Externí odkaz:
http://arxiv.org/abs/2411.14049
The dynamic imbalance of the fore-background is a major challenge in video object counting, which is usually caused by the sparsity of foreground objects. This often leads to severe under- and over-prediction problems and has been less studied in exi
Externí odkaz:
http://arxiv.org/abs/2411.13056
Publikováno v:
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence,Main Track,Pages 1317-1325, 2024
Infrared and visible image fusion aim to integrate modality strengths for visually enhanced, informative images. Visible imaging in real-world scenarios is susceptible to dynamic environmental brightness fluctuations, leading to texture degradation.
Externí odkaz:
http://arxiv.org/abs/2411.04697
The inherent challenge of image fusion lies in capturing the correlation of multi-source images and comprehensively integrating effective information from different sources. Most existing techniques fail to perform dynamic image fusion while notably
Externí odkaz:
http://arxiv.org/abs/2411.02840
Image fusion aims to integrate complementary information from multiple input images acquired through various sources to synthesize a new fused image. Existing methods usually employ distinct constraint designs tailored to specific scenes, forming fix
Externí odkaz:
http://arxiv.org/abs/2411.01573
Time series forecasting, which aims to predict future values based on historical data, has garnered significant attention due to its broad range of applications. However, real-world time series often exhibit complex non-uniform distribution with vary
Externí odkaz:
http://arxiv.org/abs/2410.09836
Autor:
Zhang, Qingyang, Feng, Qiuxuan, Zhou, Joey Tianyi, Bian, Yatao, Hu, Qinghua, Zhang, Changqing
Out-of-distribution (OOD) detection is essential for model trustworthiness which aims to sensitively identify semantic OOD samples and robustly generalize for covariate-shifted OOD samples. However, we discover that the superior OOD detection perform
Externí odkaz:
http://arxiv.org/abs/2410.11576
Autor:
Han, Zongbo, Yang, Jialong, Li, Junfan, Hu, Qinghua, Xu, Qianli, Shou, Mike Zheng, Zhang, Changqing
Vision-language foundation models (e.g., CLIP) have shown remarkable performance across a wide range of tasks. However, deploying these models may be unreliable when significant distribution gaps exist between the training and test data. The training
Externí odkaz:
http://arxiv.org/abs/2409.19375