Results 11 to 20 of about 13,581,527 (336)
Scientific Reports, 2023 In the past 2 years, three earthquakes of magnitude 6.0 and above occurred consecutively in Qinghai province, China, i.e., the 22 May 2021 M s7.4 Maduo, 8 January 2022 M s6.9 Menyuan, and 26 March 2022 M s6.0 Delingha earthquakes.
Huaizhong Yu +9 more
doaj +1 more source
Ocean Networks Canada: From Geohazards Research Laboratories to Smart Ocean Systems [PDF]
Oceanography, 2014 Ocean Networks Canada (ONC; http://www.oceannetworks.ca) operates the NEPTUNE and VENUS cabled ocean observatories off the western coast of Canada (Figure 1) and an increasing number of miniature ocean observatories, such as in the Canadian Arctic. These
Martin Heesemann +4 more
doaj +1 more source
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks [PDF]
Conference on Empirical Methods in Natural Language Processing, 2019 BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the network, which causes
Nils Reimers, Iryna Gurevych
semanticscholar +1 more source
A Style-Based Generator Architecture for Generative Adversarial Networks [PDF]
Computer Vision and Pattern Recognition, 2018 We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and ...
Tero Karras, S. Laine, Timo Aila
semanticscholar +1 more source
Nature Communications, 2022 Existing neural network potentials are generally designed for narrow target materials. Here the authors develop a neural network potential which is able to handle any combination of 45 elements and show its applicability in multiple domains.
So Takamoto +21 more
doaj +1 more source
Enhanced Deep Residual Networks for Single Image Super-Resolution [PDF]
2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017 Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance.
Bee Lim +4 more
semanticscholar +1 more source
Squeeze-and-Excitation Networks [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017 Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local receptive fields.
Jie Hu +4 more
semanticscholar +1 more source
A summary of seismic activities in and around China in 2021
Earthquake Research Advances, 2022 In this article, we review the general characteristics of seismicity in and around China and the overall statistics of earthquake damage in 2021, focusing on several significant events and related scientific topics.
Yanyan Han +6 more
doaj +1 more source
SlowFast Networks for Video Recognition [PDF]
IEEE International Conference on Computer Vision, 2018 We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution ...
Christoph Feichtenhofer +3 more
semanticscholar +1 more source
A Comprehensive Survey on Graph Neural Networks [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2019 Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding.
Zonghan Wu +5 more
semanticscholar +1 more source