Zobrazeno 1 - 10
of 17 176
pro vyhledávání: '"An, Xingguo"'
Fast-converging algorithms are a contemporary requirement in reinforcement learning. In the context of linear function approximation, the magnitude of the smallest eigenvalue of the key matrix is a major factor reflecting the convergence speed. Tradi
Externí odkaz:
http://arxiv.org/abs/2411.06396
Long-term time series forecasting (LTSF) provides longer insights into future trends and patterns. Over the past few years, deep learning models especially Transformers have achieved advanced performance in LTSF tasks. However, LTSF faces inherent ch
Externí odkaz:
http://arxiv.org/abs/2404.15772
The image-level label has prevailed in weakly supervised semantic segmentation tasks due to its easy availability. Since image-level labels can only indicate the existence or absence of specific categories of objects, visualization-based techniques h
Externí odkaz:
http://arxiv.org/abs/2401.11122
The low-level spatial detail information and high-level semantic abstract information are both essential to the semantic segmentation task. The features extracted by the deep network can obtain rich semantic information, while a lot of spatial inform
Externí odkaz:
http://arxiv.org/abs/2312.07207
Autor:
Fangping Gong, Zhuo Li, Xiaojian Sun, Yi Fan, Yinghui Liu, Yurong Dang, Hao Li, Xingguo Zhang, Xingli Ma, Zhongfeng Li, Kai Zhao, Dongmei Yin
Publikováno v:
Oil Crop Science, Vol 9, Iss 4, Pp 265-274 (2024)
Peanut (Arachis hypogaea L.) is an important oil crop. Oleic acid is a major factor that determines the quality of peanuts. Therefore, the high oleic and high oleic to linoleic acid ratio are the target traits in an advanced peanut breeding program.
Externí odkaz:
https://doaj.org/article/896cd23639244fcdbbaf651c24e88da2
Autor:
Yuexing Zhang, Junhao Peng, Guangsong Zhang, Xingguo Zhang, Shuai Zhang, Qing Li, Guanfeng Tian, Xiaoli Wang, Ping Wu, Xue-Li Chen
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-10 (2024)
Abstract Based on the experimentally reported stable and conductive two-dimensional covalent organic frameworks with copper phthalocyanine (CuPc) as building block and cyan substituted phenyl as connector (CuCOF-CN) as an electrocatalyst for CO2 redu
Externí odkaz:
https://doaj.org/article/d96e39f7605442749ad85235fd461d25
Autor:
Fangyi Li, Ziyang He, Xinyi Zhang, Dacheng Gao, Rui Xu, Zhiwen Zhang, Xingguo Cao, Qiyuan Shan, Yali Liu, Zengguang Xu
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-11 (2024)
Abstract Lung cancer is one of the most common types of malignant cancer worldwide, causing a serious social and economic burden. It is classified into non-small cell lung cancer (NSCLC) and small cell lung cancer, with NSCLC accounting for 80–85%
Externí odkaz:
https://doaj.org/article/1a1a57839df7499cb53cc3775a832f42
Model-based offline reinforcement learning (RL), which builds a supervised transition model with logging dataset to avoid costly interactions with the online environment, has been a promising approach for offline policy optimization. As the discrepan
Externí odkaz:
http://arxiv.org/abs/2309.02157
Zero-shot video object segmentation (ZS-VOS) aims to segment foreground objects in a video sequence without prior knowledge of these objects. However, existing ZS-VOS methods often struggle to distinguish between foreground and background or to keep
Externí odkaz:
http://arxiv.org/abs/2304.03910
Due to its significant capability of modeling long-range dependencies, vision transformer (ViT) has achieved promising success in both holistic and occluded person re-identification (Re-ID) tasks. However, the inherent problems of transformers such a
Externí odkaz:
http://arxiv.org/abs/2304.01452