Zobrazeno 1 - 10
of 465
pro vyhledávání: '"Lu, Pu"'
Autor:
Yuan, Zhihang, Lu, Pu, Zhang, Hanling, Ning, Xuefei, Zhang, Linfeng, Zhao, Tianchen, Yan, Shengen, Dai, Guohao, Wang, Yu
Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to self-attention's quadratic complexity. We propose DiTFastAttn, a novel post-training compression method to alleviate DiT's computational bottlen
Externí odkaz:
http://arxiv.org/abs/2406.08552
Autor:
Zhao, Tianchen, Ning, Xuefei, Hong, Ke, Qiu, Zhongyuan, Lu, Pu, Zhao, Yali, Zhang, Linfeng, Zhou, Lipu, Dai, Guohao, Yang, Huazhong, Wang, Yu
Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. However, their significant computational and memory costs pose a challenge for their application to resource-constrained vehicles. One reaso
Externí odkaz:
http://arxiv.org/abs/2307.08209
Autor:
Yang, Mingkun, Liao, Minghui, Lu, Pu, Wang, Jing, Zhu, Shenggao, Luo, Hualin, Tian, Qi, Bai, Xiang
Existing text recognition methods usually need large-scale training data. Most of them rely on synthetic training data due to the lack of annotated real images. However, there is a domain gap between the synthetic data and real data, which limits the
Externí odkaz:
http://arxiv.org/abs/2207.00193
Publikováno v:
IET Science, Measurement & Technology, Vol 17, Iss 9, Pp 373-384 (2023)
Abstract In order to monitor the state of bushing online, an intelligent monitoring system for transformer bushing was developed. A four‐in‐one sensor integrating hydrogen sensing technology using palladium nickel alloy, pressure sensing technolo
Externí odkaz:
https://doaj.org/article/cd5280f17fa04f1cbc006365afa18f68
Publikováno v:
Energy Reports, Vol 9, Iss , Pp 904-911 (2023)
With the increase of cable operating age, various latent defects gradually appear, so it is important to identify and locate the defects accurately for power operation and maintenance. The common methods for cable failure detection primarily work wit
Externí odkaz:
https://doaj.org/article/8806a156ed354db599641ed7d38f969f
Publikováno v:
In International Review of Economics and Finance January 2024 89 Part A:1569-1582
Publikováno v:
In Engineering Geology 5 December 2023 326
Autor:
Song Gu, Shao‐Dong Xu, Jia‐Hui Lu, Xiao‐Lu Pu, Qing‐Ruo Ren, Yan‐Fang Xiao, Yu‐Zhong Wang, Li Chen
Publikováno v:
EcoMat, Vol 5, Iss 9, Pp n/a-n/a (2023)
Abstract Dynamic covalent chemistry offers a solution to tackle the recycling issue of epoxy resins (EPs) and their carbon fiber‐reinforced composites; however, the vulnerability to creep associated with the inflammable nature of the EPs are the ke
Externí odkaz:
https://doaj.org/article/14ad262c054e408bb77e132459e737b5
Autor:
Wang, Hao, Lu, Pu, Zhang, Hui, Yang, Mingkun, Bai, Xiang, Xu, Yongchao, He, Mengchao, Wang, Yongpan, Liu, Wenyu
Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision. Different from the existing approaches that formulate text detection as boun
Externí odkaz:
http://arxiv.org/abs/1911.09550