Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Qin, Tiexin"'
Understanding protein dynamics are essential for deciphering protein functional mechanisms and developing molecular therapies. However, the complex high-dimensional dynamics and interatomic interactions of biological processes pose significant challe
Externí odkaz:
http://arxiv.org/abs/2410.02847
The vector field of a controlled differential equation (CDE) describes the relationship between a control path and the evolution of a solution path. Neural CDEs (NCDEs) treat time series data as observations from a control path, parameterise a CDE's
Externí odkaz:
http://arxiv.org/abs/2402.18512
This paper focuses on representation learning for dynamic graphs with temporal interactions. A fundamental issue is that both the graph structure and the nodes own their own dynamics, and their blending induces intractable complexity in the temporal
Externí odkaz:
http://arxiv.org/abs/2302.11354
Domain generalization aims to improve the generalization capability of machine learning systems to out-of-distribution (OOD) data. Existing domain generalization techniques embark upon stationary and discrete environments to tackle the generalization
Externí odkaz:
http://arxiv.org/abs/2205.07649
Autor:
Li, Wenbin, Ziyi, Wang, Yang, Xuesong, Dong, Chuanqi, Tian, Pinzhuo, Qin, Tiexin, Huo, Jing, Shi, Yinghuan, Wang, Lei, Gao, Yang, Luo, Jiebo
Few-shot learning, especially few-shot image classification, has received increasing attention and witnessed significant advances in recent years. Some recent studies implicitly show that many generic techniques or ``tricks'', such as data augmentati
Externí odkaz:
http://arxiv.org/abs/2109.04898
Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current works heavily rely on a large-scale labeled auxiliary set to train their
Externí odkaz:
http://arxiv.org/abs/2004.05805
Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation. However, the data generated by these
Externí odkaz:
http://arxiv.org/abs/2002.09703
Aiming to produce sufficient and diverse training samples, data augmentation has been demonstrated for its effectiveness in training deep models. Regarding that the criterion of the best augmentation is challenging to define, we in this paper present
Externí odkaz:
http://arxiv.org/abs/1910.08343
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.