Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Yingmei Wei"'
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 6, Pp 8249-8272 (2024)
Abstract Most previous few-shot action recognition works tend to process video temporal and spatial features separately, resulting in insufficient extraction of comprehensive features. In this paper, a novel hybrid attentive prototypical network (HAP
Externí odkaz:
https://doaj.org/article/4e639100028647ec93ebf6ba19e839c1
Publikováno v:
Humanities & Social Sciences Communications, Vol 11, Iss 1, Pp 1-15 (2024)
Abstract An increasing number of Chinese tourists exhibit reluctance in trusting and using Official Tourism Destination Websites (OTDWs). To address this hesitancy, our study developed an integrated framework and structural model based on Hofstede’
Externí odkaz:
https://doaj.org/article/fd27d069fc264a61a999324edc35afa5
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 3, Pp 3541-3556 (2024)
Abstract Nowadays, Artificial Intelligence Generated Content (AIGC) has shown promising prospects in both computer vision and natural language processing communities. Meanwhile, as an essential aspect of AIGC, image to captions has received much more
Externí odkaz:
https://doaj.org/article/301815a10ae24ec58c1221da31b9f2ab
Publikováno v:
CAAI Transactions on Intelligence Technology, Vol 8, Iss 4, Pp 1464-1479 (2023)
Abstract Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently. However, there are still two challenges. First, most of the real‐word syst
Externí odkaz:
https://doaj.org/article/de017e4de93544d2ab23f3c7efef1b6a
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 1, Pp 613-626 (2023)
Abstract In recent years, a surge of criminal activities with cross-cryptocurrency trades have emerged in Ethereum, the second-largest public blockchain platform. Most of the existing anomaly detection methods utilize the traditional machine learning
Externí odkaz:
https://doaj.org/article/78c8eff59f654eecac9c047d6660bbad
Publikováno v:
Mathematics, Vol 12, Iss 9, p 1290 (2024)
Accurate traffic prediction is pivotal when constructing intelligent cities to enhance urban mobility and to efficiently manage traffic flows. Traditional deep learning-based traffic prediction models primarily focus on capturing spatial and temporal
Externí odkaz:
https://doaj.org/article/376496066bc14d71b93ec8a109ebeec4
Publikováno v:
Mathematics, Vol 11, Iss 8, p 1830 (2023)
Graph-embedding learning is the foundation of complex information network analysis, aiming to represent nodes in a graph network as low-dimensional dense real-valued vectors for the application in practical analysis tasks. In recent years, the study
Externí odkaz:
https://doaj.org/article/4df55d948dcf481188e3ea2c77f87726
Publikováno v:
Frontiers in Physics, Vol 9 (2022)
Node classification, as a central task in the graph data analysis, has been studied extensively with network embedding technique for single-layer graph network. However, there are some obstacles when extending the single-layer network embedding techn
Externí odkaz:
https://doaj.org/article/6dcd43eb15a64bc581f60e4c88740dbd
Combining Convolutional Neural Network and Photometric Refinement for Accurate Homography Estimation
Publikováno v:
IEEE Access, Vol 7, Pp 109460-109473 (2019)
Homography estimation refers to the problem of computing a 3 × 3 matrix which transfers image points between two images of a planar scene or two images captured from the same location. While existing algorithms exploiting hand-crafted sparse image f
Externí odkaz:
https://doaj.org/article/d908abdd2e684d69bc50b50f527ddeb4
Publikováno v:
Applied Sciences, Vol 10, Iss 2, p 618 (2020)
Precise 3D hand pose estimation can be used to improve the performance of human−computer interaction (HCI). Specifically, computer-vision-based hand pose estimation can make this process more natural. Most traditional computer-vision-based hand pos
Externí odkaz:
https://doaj.org/article/3f9519d1838e40bb94d839de5bf16ad4