Kai Su, Dongdong Yu, Zhenqi Xu, Xin Geng et al.
Multi-person pose estimation is an important but challenging problem in computer vision. Although current approaches have achieved significant progress by fusing the multi-scale feature maps, they pay little attention to enhancing the channel-wise and spatial information of the feature maps. In this...
Xin Geng, Wenjun Zhang, Malte F. Stuecker, Fei‐Fei Jin
East Asia experienced a record-breaking cold event during the 2015/16 boreal winter, with pronounced impacts on livelihood in the region. We find that this large-scale cold spell can be attributed to the concurrent super El Niño event in the tropical Pacific. Our analysis reveals that all super El N...
Xin Geng, Kate Smith‐Miles, Zhi-Hua Zhou, Liang Wang
Multilinear subspace analysis (MSA) is a promising methodology for pattern-recognition problems due to its ability in decomposing the data formed from the interaction of multiple factors. The MSA requires a large training set, which is well organized in a single tensor, which consists of data sample...
Biyuan Zheng, Dong Li, Chenguang Zhu, Jianyue Lan et al.
Abstract Layered semiconductor heterostructures are essential elements in modern electronic and optoelectronic devices. Dynamically engineering the composition of these heterostructures may enable the flexible design of the properties of heterostructure‐based electronics and optoelectronics as well ...
Bing Wei, Ming-liang Ji, Yucheng Lin, Shanzheng Wang et al.
Abstract Background Although mesenchymal stem cells (MSCs) have been effective in tendinopathy, the mechanisms by which MSCs promote tendon healing have not been fully elucidated. In this study, we tested the hypothesis that MSCs transfer mitochondria to injured tenocytes in vitro and in vivo to pro...
Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu et al.
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed learning objectives as constrained optimizations that must be solve...
Chuanyu Han, Sheng Li Fang, Yi Cui, Weihua Liu et al.
Abstract For the first time, a configurable NbO x memristor is achieved that can be configured as an artificial synapse or neuron after fabrication by controlling the forming compliance current (FCC). When the FCC ≤ 2 mA, the memristors exhibit the resistive‐switching (RS) property, enabling multipl...
Jing Wang, Xin Geng, Hui Xue
Label ambiguity has attracted quite some attention among the machine learning community. The latterly proposed Label Distribution Learning (LDL) can handle label ambiguity and has found wide applications in real classification problems. In the training phase, an LDL model is learned first. In the te...
Haoyun Wang, Yang Sun, Xingkun Zhou, Chengyuan Zhu et al.
Strain JUST-3, exhibiting high-efficiency simultaneous nitrogen and phosphorus removal under aerobic conditions, was isolated and identified as Paracoccus versutus based on 16S rDNA gene sequencing and comprehensive physiological and biochemical analysis. The strain demonstrated optimal performance ...
Xin Geng, Wenjun Zhang, Fei‐Fei Jin, Malte F. Stuecker
Abstract We here propose a new statistical method to interpret nonstationary running correlations by decomposing them into a stationary part and a first‐order Taylor expansion approximation for the nonstationary part. Then, this method is applied to investigate the nonstationary behavior of the El N...
Ke Wang, Ning Xu, Miaogen Ling, Xin Geng
Label Distribution Learning (LDL) has attracted increasing research attentions due to its potential to address the label ambiguity problem in machine learning and success in many real-world applications. In LDL, it is usually expensive to obtain the ground-truth label distributions of data, but it i...
Xin Geng, Renyi Zheng, Jiaqi Lv, Yu Zhang
While most existing multilabel ranking methods assume the availability of a single objective label ranking for each instance in the training set, this paper deals with a more common case where only subjective inconsistent rankings from multiple rankers are associated with each instance. Two ranking ...
Jiajia Li, Qinan Ban, Min Xu, Shu Wang et al.
Developing bioelectronic sensors with exceptional physicochemical properties, such as strong adhesion to wet biological tissues, high mechanical strength and stretchability, transparency, self-healing ability, biocompatibility, and degradability remains a significant challenge in meeting the complex...
Wenjing Wu, Xinshuai Geng, Rui Han, Haiqian Zhao et al.
Microplastic pollution has become a global environmental issue, particularly pronounced in traffic-dense urban areas as the urbanization accelerates. Notably, under high temperatures (daily maximum temperature > 35 °C), the generation and diffusion of traffic-sourced microplastics may undergo signif...
Jiaming Li, Mengmeng Jiang, Qiaoran Wang, Zikai Zheng et al.
The global surge in the population of people 60 years and older, including that in China, challenges healthcare systems with rising age-related diseases. To address this demographic change, the Aging Biomarker Consortium (ABC) has launched the X-Age Project to develop a comprehensive aging evaluatio...