Zobrazeno 1 - 10
of 10 778
pro vyhledávání: '"Guocheng An"'
Publikováno v:
Hydrology Research, Vol 55, Iss 5, Pp 519-536 (2024)
Due to the uncertainty in output caused by environmental changes, significant discrepancies are expected between the surface flow velocities predicted using deep learning methods and the instantaneous flow velocities. In this paper, a two-stage deep
Externí odkaz:
https://doaj.org/article/84180ea1ec0843fcae32ee9d47fc2fbd
Publikováno v:
Water, Vol 16, Iss 19, p 2784 (2024)
Accurate assessment of water surface velocity (WSV) is essential for flood prevention, disaster mitigation, and erosion control within hydrological monitoring. Existing image-based velocimetry techniques largely depend on correlation principles, requ
Externí odkaz:
https://doaj.org/article/58b3a325241e4615a1c93733763a69ac
Publikováno v:
River, Vol 2, Iss 4, Pp 506-517 (2023)
Abstract Due to the diversity of climate and environment in China, the frequent occurrence of extreme rainfall events has brought great challenges to flood prevention. Water level measurement is one of the important research topics of flood preventio
Externí odkaz:
https://doaj.org/article/fa78294ed30d4f7fbfba4947e65665a6
Point cloud frame interpolation is a challenging task that involves accurate scene flow estimation across frames and maintaining the geometry structure. Prevailing techniques often rely on pre-trained motion estimators or intensive testing-time optim
Externí odkaz:
http://arxiv.org/abs/2410.19573
Autor:
Liu, Xiaoqian, Du, Yangfan, Wang, Jianjin, Ge, Yuan, Xu, Chen, Xiao, Tong, Chen, Guocheng, Zhu, Jingbo
Simultaneous Speech Translation (SimulST) involves generating target language text while continuously processing streaming speech input, presenting significant real-time challenges. Multi-task learning is often employed to enhance SimulST performance
Externí odkaz:
http://arxiv.org/abs/2409.15911
Autor:
Mai, Jinjie, Zhu, Wenxuan, Rojas, Sara, Zarzar, Jesus, Hamdi, Abdullah, Qian, Guocheng, Li, Bing, Giancola, Silvio, Ghanem, Bernard
Neural radiance fields (NeRFs) generally require many images with accurate poses for accurate novel view synthesis, which does not reflect realistic setups where views can be sparse and poses can be noisy. Previous solutions for learning NeRFs with s
Externí odkaz:
http://arxiv.org/abs/2408.10739
Autor:
Bahmani, Sherwin, Skorokhodov, Ivan, Siarohin, Aliaksandr, Menapace, Willi, Qian, Guocheng, Vasilkovsky, Michael, Lee, Hsin-Ying, Wang, Chaoyang, Zou, Jiaxu, Tagliasacchi, Andrea, Lindell, David B., Tulyakov, Sergey
Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is critical for downstream applicatio
Externí odkaz:
http://arxiv.org/abs/2407.12781
Collaborative Edge Computing (CEC) is an emerging paradigm that collaborates heterogeneous edge devices as a resource pool to compute DNN inference tasks in proximity such as edge video analytics. Nevertheless, as the key knob to improve network util
Externí odkaz:
http://arxiv.org/abs/2406.19613
The noisy permutation channel is a useful abstraction introduced by Makur for point-to-point communication networks and biological storage. While the asymptotic capacity results exist for this model, the characterization of the second-order asymptoti
Externí odkaz:
http://arxiv.org/abs/2406.15031
Autor:
Qiu, Yanqi, Zhen, Guocheng
We study the limiting spectral measure of large random Helson matrices and large random matrices of certain patterned structures. Given a real random variable $X \in L^{2+ \varepsilon}(\mathbb{P}) $ for some $\varepsilon > 0$ and $\mathrm{Var}(X) = 1
Externí odkaz:
http://arxiv.org/abs/2405.18796