Zobrazeno 1 - 10
of 796
pro vyhledávání: '"HUANG Yulong"'
Publikováno v:
Chengshi guidao jiaotong yanjiu, Vol 27, Iss 8, Pp 227-233 (2024)
Objective Due to the characteristics of strong permeability and high water content in water-rich sand layer, the poor muck improvement can easily cause accidents such as spout spilling of screw conveyor and mud cake formation on the cutter plate duri
Externí odkaz:
https://doaj.org/article/7bcf6c88a2f94f209ba3d495f000630f
Autor:
Huang, Yulong, Liu, Zunchang, Feng, Changchun, Lin, Xiaopeng, Ren, Hongwei, Fu, Haotian, Zhou, Yue, Xing, Hong, Cheng, Bojun
Recently, there is growing demand for effective and efficient long sequence modeling, with State Space Models (SSMs) proving to be effective for long sequence tasks. To further reduce energy consumption, SSMs can be adapted to Spiking Neural Networks
Externí odkaz:
http://arxiv.org/abs/2410.03530
Although deep learning based models for underwater image enhancement have achieved good performance, they face limitations in both lightweight and effectiveness, which prevents their deployment and application on resource-constrained platforms. Moreo
Externí odkaz:
http://arxiv.org/abs/2405.16197
Autor:
Ren, Hongwei, Zhou, Yue, Zhu, Jiadong, Fu, Haotian, Huang, Yulong, Lin, Xiaopeng, Fang, Yuetong, Ma, Fei, Yu, Hao, Cheng, Bojun
Event cameras, drawing inspiration from biological systems, efficiently detect changes in ambient light with low latency and high dynamic range while consuming minimal power. The most current approach to processing event data often involves convertin
Externí odkaz:
http://arxiv.org/abs/2405.06116
Event cameras exhibit remarkable attributes such as high dynamic range, asynchronicity, and low latency, making them highly suitable for vision tasks that involve high-speed motion in challenging lighting conditions. These cameras implicitly capture
Externí odkaz:
http://arxiv.org/abs/2403.19412
Publikováno v:
Jixie qiangdu, Vol 40, Pp 687-694 (2018)
J-integral is an important fracture parameter which quantitatively describes the stress and strain fields near a crack tip. Accurate and efficient measurement of J-integral is of great significance for the evaluation of crack stability and propagatio
Externí odkaz:
https://doaj.org/article/b47798735e9749329ebcc6d5889ef6cf
Autor:
Huang, Yulong, Lin, Xiaopeng, Ren, Hongwei, Fu, Haotian, Zhou, Yue, Liu, Zunchang, Pan, Biao, Cheng, Bojun
Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Compared to conventional deep Artificial Neural Networks (ANNs), SNNs exhibit superior efficiency and capability to process temporal information. However, it remains
Externí odkaz:
http://arxiv.org/abs/2402.04663
Event cameras are bio-inspired sensors that respond to local changes in light intensity and feature low latency, high energy efficiency, and high dynamic range. Meanwhile, Spiking Neural Networks (SNNs) have gained significant attention due to their
Externí odkaz:
http://arxiv.org/abs/2310.07189
Event cameras have gained popularity in computer vision due to their data sparsity, high dynamic range, and low latency. As a bio-inspired sensor, event cameras generate sparse and asynchronous data, which is inherently incompatible with the traditio
Externí odkaz:
http://arxiv.org/abs/2308.09993
Sequential recommender models typically generate predictions in a single step during testing, without considering additional prediction correction to enhance performance as humans would. To improve the accuracy of these models, some researchers have
Externí odkaz:
http://arxiv.org/abs/2304.14050