Zobrazeno 1 - 10
of 130
pro vyhledávání: '"Xuguang LAN"'
Publikováno v:
智能科学与技术学报, Vol 4, Pp 308-323 (2022)
One of the limitations of robotics is that it is difficult for robots to adapt to fickle tasks.A robot will inevitably forget the knowledge from old environments or tasks when facing new environments or tasks.In order to summarize research in continu
Externí odkaz:
https://doaj.org/article/c56036ba03214b32ab14d95148a9d339
Autor:
Fang Yuan, Min Zhang, Chunrong Zhu, Xiaoyun Liu, Chenjing Zhao, Jinfei Dai, Hua Dong, Bo Jiao, Xuguang Lan, Zhaoxin Wu
Publikováno v:
Frontiers in Chemistry, Vol 10 (2022)
Recently, perovskite light-emitting diodes (PeLEDs) have drew widespread attention due to their high efficiencies. However, because of the sensitivity to moisture and oxygen, perovskite luminescent layers are usually prepared in high-purity nitrogen
Externí odkaz:
https://doaj.org/article/012ee7bc48c24cccaae2025e03fe14e8
Publikováno v:
PLoS ONE, Vol 15, Iss 7, p e0235352 (2020)
Generative adversarial networks (GANs) have been used to obtain super-resolution (SR) videos that have improved visual perception quality and more coherent details. However, the latest methods perform poorly in areas with dense textures. To better re
Externí odkaz:
https://doaj.org/article/ad549af8406d439f846eb5875ea2ae56
Publikováno v:
Sensors, Vol 14, Iss 12, Pp 23398-23418 (2014)
Compressive Sensing Imaging (CSI) is a new framework for image acquisition, which enables the simultaneous acquisition and compression of a scene. Since the characteristics of Compressive Sensing (CS) acquisition are very different from traditional i
Externí odkaz:
https://doaj.org/article/fca42c0cc9894d1c9975de43fa9133c7
Publikováno v:
IET Computer Vision, Vol 8, Iss 1, Pp 16-25 (2014)
In this study, the authors present a method to extract moving objects in image sequences. The proposed approach is based on a graph cuts algorithm defined on a spatiotemporal superpixel neighbourhood. Presegmented superpixels are partitioned into for
Externí odkaz:
https://doaj.org/article/e94adb3c338c46b880a465efdfaff026
Publikováno v:
Sensors, Vol 13, Iss 3, Pp 3409-3431 (2013)
Salient object perception is the process of sensing the salient information from the spatio-temporal visual scenes, which is a rapid pre-attention mechanism for the target location in a visual smart sensor. In recent decades, many successful models o
Externí odkaz:
https://doaj.org/article/fb2f833aad20473c897888bcb6949875
Publikováno v:
In Fundamental Research September 2022
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:3598-3611
Many data sources, such as human poses, lie on low-dimensional manifolds that are smooth and bounded. Learning low-dimensional representations for such data is an important problem. One typical solution is to utilize encoder-decoder networks. However
Publikováno v:
IEEE Robotics and Automation Letters. 7:2929-2936
Despite the impressive progress achieved in robotic grasping, robots are not skilled in sophisticated tasks (e.g. search and grasp a specified target in clutter). Such tasks involve not only grasping but the comprehensive perception of the world (e.g
Publikováno v:
IEEE Transactions on Multimedia. 24:177-187
The visual-semantic gap between the visual space (visual features) and semantic space (semantic attributes) is one of the main problems in the Generalized Zero-Shot Learning (GZSL) task. The essence of this problem is that the structure of manifolds