Zobrazeno 1 - 10
of 338
pro vyhledávání: '"Wang, Feiyang"'
In this paper, we propose an improved Unet model for brain tumor image segmentation, which combines coordinate attention mechanism and ASPP module to improve the segmentation effect. After the data set is divided, we do the necessary preprocessing to
Externí odkaz:
http://arxiv.org/abs/2409.08588
The shift from professionally generated content (PGC) to user-generated content (UGC) has revolutionized various media formats, from text to video. With the rapid advancements in generative AI, a similar shift is set to transform the game industry, p
Externí odkaz:
http://arxiv.org/abs/2407.08195
Many machine learning models are susceptible to adversarial attacks, with decision-based black-box attacks representing the most critical threat in real-world applications. These attacks are extremely stealthy, generating adversarial examples using h
Externí odkaz:
http://arxiv.org/abs/2406.04998
The sequential interaction network usually find itself in a variety of applications, e.g., recommender system. Herein, inferring future interaction is of fundamental importance, and previous efforts are mainly focused on the dynamics in the classic z
Externí odkaz:
http://arxiv.org/abs/2401.01243
Graphs are typical non-Euclidean data of complex structures. In recent years, Riemannian graph representation learning has emerged as an exciting alternative to Euclidean ones. However, Riemannian methods are still in an early stage: most of them pre
Externí odkaz:
http://arxiv.org/abs/2401.01232
Image reconstruction-based anomaly detection models are widely explored in industrial visual inspection. However, existing models usually suffer from the trade-off between normal reconstruction fidelity and abnormal reconstruction distinguishability,
Externí odkaz:
http://arxiv.org/abs/2309.07068
SINCERE: Sequential Interaction Networks representation learning on Co-Evolving RiEmannian manifolds
Sequential interaction networks (SIN) have been commonly adopted in many applications such as recommendation systems, search engines and social networks to describe the mutual influence between users and items/products. Efforts on representing SIN ar
Externí odkaz:
http://arxiv.org/abs/2305.03883
Graph clustering is a longstanding research topic, and has achieved remarkable success with the deep learning methods in recent years. Nevertheless, we observe that several important issues largely remain open. On the one hand, graph clustering from
Externí odkaz:
http://arxiv.org/abs/2305.03555
Autor:
Wang, Zihan, Wang, Feiyang, Vovrosh, Joseph, Knolle, Johannes, Mintert, Florian, Mukherjee, Rick
The phenomenon of confinement is well known in high-energy physics and can also be realized for low-energy domain-wall excitations in one-dimensional quantum spin chains. A bound state consisting of two domain-walls can behave like a meson, and in a
Externí odkaz:
http://arxiv.org/abs/2304.12623
Continual graph learning routinely finds its role in a variety of real-world applications where the graph data with different tasks come sequentially. Despite the success of prior works, it still faces great challenges. On the one hand, existing meth
Externí odkaz:
http://arxiv.org/abs/2211.17068