stream network
Recently Published Documents


TOTAL DOCUMENTS

515
(FIVE YEARS 275)

H-INDEX

36
(FIVE YEARS 7)

2022 ◽  
Vol 40 (3) ◽  
pp. 1-36
Author(s):  
Jinyuan Fang ◽  
Shangsong Liang ◽  
Zaiqiao Meng ◽  
Maarten De Rijke

Network-based information has been widely explored and exploited in the information retrieval literature. Attributed networks, consisting of nodes, edges as well as attributes describing properties of nodes, are a basic type of network-based data, and are especially useful for many applications. Examples include user profiling in social networks and item recommendation in user-item purchase networks. Learning useful and expressive representations of entities in attributed networks can provide more effective building blocks to down-stream network-based tasks such as link prediction and attribute inference. Practically, input features of attributed networks are normalized as unit directional vectors. However, most network embedding techniques ignore the spherical nature of inputs and focus on learning representations in a Gaussian or Euclidean space, which, we hypothesize, might lead to less effective representations. To obtain more effective representations of attributed networks, we investigate the problem of mapping an attributed network with unit normalized directional features into a non-Gaussian and non-Euclidean space. Specifically, we propose a hyperspherical variational co-embedding for attributed networks (HCAN), which is based on generalized variational auto-encoders for heterogeneous data with multiple types of entities. HCAN jointly learns latent embeddings for both nodes and attributes in a unified hyperspherical space such that the affinities between nodes and attributes can be captured effectively. We argue that this is a crucial feature in many real-world applications of attributed networks. Previous Gaussian network embedding algorithms break the assumption of uninformative prior, which leads to unstable results and poor performance. In contrast, HCAN embeds nodes and attributes as von Mises-Fisher distributions, and allows one to capture the uncertainty of the inferred representations. Experimental results on eight datasets show that HCAN yields better performance in a number of applications compared with nine state-of-the-art baselines.


Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 599
Author(s):  
Yongsheng Li ◽  
Tengfei Tu ◽  
Hua Zhang ◽  
Jishuai Li ◽  
Zhengping Jin ◽  
...  

In the field of video action classification, existing network frameworks often only use video frames as input. When the object involved in the action does not appear in a prominent position in the video frame, the network cannot accurately classify it. We introduce a new neural network structure that uses sound to assist in processing such tasks. The original sound wave is converted into sound texture as the input of the network. Furthermore, in order to use the rich modal information (images and sound) in the video, we designed and used a two-stream frame. In this work, we assume that sound data can be used to solve motion recognition tasks. To demonstrate this, we designed a neural network based on sound texture to perform video action classification tasks. Then, we fuse this network with a deep neural network that uses continuous video frames to construct a two-stream network, which is called A-IN. Finally, in the kinetics dataset, we use our proposed A-IN to compare with the image-only network. The experimental results show that the recognition accuracy of the two-stream neural network model with uesed sound data features is increased by 7.6% compared with the network using video frames. This proves that the rational use of the rich information in the video can improve the classification effect.


Author(s):  
I. Yu. Chernova ◽  
◽  
D. K. Nourgaliev ◽  
O. S. Chernova ◽  
O. V. Luneva ◽  
...  

Structural and geomorphological methods are often applied to the search for small oil-producing structures. Morphometric analysis of digital elevation models has proved to be the most informative one. Morphometric surfaces can be used to evaluate the direction and amplitude of vertical movements, to outline local and regional neotectonic structures and assess their petroleum saturation. This paper shows how to enhance the traditional morphometric analysis with GIS (geographic information systems) tools. A manifold increase in the efficiency of morphometric analysis takes it to a qualitatively new level. Setting specific parameters for some geoprocessing tools (for example, stream network tools) can be very important when studying local structures in small areas. In case of large territories, the output result is almost independent of the calculation errors. The improved technique proposed in this paper was tested on a large territory located in the Volga region. As a result, high-order morphometric surfaces were obtained, which was not possible before. In addition, a statistically significant relationship was discovered between morphometric surfaces and distribution of oil deposits, which can be considered a reliable prospecting indicator in the Volga-Ural petroleum province. Keywords: neotectonics; structural and morphological methods; geoinformation systems; hydrocarbon potential assessment.


Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 244
Author(s):  
Javier Villalba-Diez ◽  
Ana González-Marcos ◽  
Joaquín B. Ordieres-Meré

The objective of this short letter is to study the optimal partitioning of value stream networks into two classes so that the number of connections between them is maximized. Such kind of problems are frequently found in the design of different systems such as communication network configuration, and industrial applications in which certain topological characteristics enhance value–stream network resilience. The main interest is to improve the Max–Cut algorithm proposed in the quantum approximate optimization approach (QAOA), looking to promote a more efficient implementation than those already published. A discussion regarding linked problems as well as further research questions are also reviewed.


Author(s):  
Wenbo Xu ◽  
Junwei Luo ◽  
Chuntao Zhu ◽  
Wei Lu ◽  
Jinhua Zeng ◽  
...  

Algorithms ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 361
Author(s):  
Chengyan Zhong ◽  
Guanqiu Qi ◽  
Neal Mazur ◽  
Sarbani Banerjee ◽  
Devanshi Malaviya ◽  
...  

Due to the variation in the image capturing process, the difference between source and target sets causes a challenge in unsupervised domain adaptation (UDA) on person re-identification (re-ID). Given a labeled source training set and an unlabeled target training set, this paper focuses on improving the generalization ability of the re-ID model on the target testing set. The proposed method enforces two properties at the same time: (1) camera invariance is achieved through the positive learning formed by unlabeled target images and their camera style transfer counterparts; and (2) the robustness of the backbone network feature extraction is improved, and the accuracy of feature extraction is enhanced by adding a position-channel dual attention mechanism. The proposed network model uses a classic dual-stream network. Comparative experimental results on three public benchmarks prove the superiority of the proposed method.


Sign in / Sign up

Export Citation Format

Share Document