Zobrazeno 1 - 10
of 307
pro vyhledávání: '"Huang Zhilin"'
Autor:
Liang, Quanmin, Huang, Zhilin, Zheng, Xiawu, Yang, Feidiao, Peng, Jun, Huang, Kai, Tian, Yonghong
Publikováno v:
International Joint Conference on Artificial Intelligence 2024
Current Event Stream Super-Resolution (ESR) methods overlook the redundant and complementary information present in positive and negative events within the event stream, employing a direct mixing approach for super-resolution, which may lead to detai
Externí odkaz:
http://arxiv.org/abs/2406.19640
Autor:
Huang, Zhilin, Liang, Quanmin, Yu, Yijie, Qin, Chujun, Zheng, Xiawu, Huang, Kai, Zhou, Zikun, Yang, Wenming
Event Stream Super-Resolution (ESR) aims to address the challenge of insufficient spatial resolution in event streams, which holds great significance for the application of event cameras in complex scenarios. Previous works for ESR often process posi
Externí odkaz:
http://arxiv.org/abs/2405.10037
Autor:
Huang, Zhilin, Yu, Yijie, Yang, Ling, Qin, Chujun, Zheng, Bing, Zheng, Xiawu, Zhou, Zikun, Wang, Yaowei, Yang, Wenming
With the advancement of AIGC, video frame interpolation (VFI) has become a crucial component in existing video generation frameworks, attracting widespread research interest. For the VFI task, the motion estimation between neighboring frames plays a
Externí odkaz:
http://arxiv.org/abs/2404.13534
Autor:
Huang, Zhilin, Yang, Ling, Zhang, Zaixi, Zhou, Xiangxin, Bao, Yu, Zheng, Xiawu, Yang, Yuwei, Wang, Yu, Yang, Wenming
Structure-based drug design (SBDD) aims to generate 3D ligand molecules that bind to specific protein targets. Existing 3D deep generative models including diffusion models have shown great promise for SBDD. However, it is complex to capture the esse
Externí odkaz:
http://arxiv.org/abs/2402.18583
Autor:
Yang, Ling, Liu, Jingwei, Hong, Shenda, Zhang, Zhilong, Huang, Zhilin, Cai, Zheming, Zhang, Wentao, Cui, Bin
Diffusion models are a new class of generative models, and have dramatically promoted image generation with unprecedented quality and diversity. Existing diffusion models mainly try to reconstruct input image from a corrupted one with a pixel-wise or
Externí odkaz:
http://arxiv.org/abs/2401.02015
Autor:
Yang, Ling, Zheng, Jiayi, Wang, Heyuan, Liu, Zhongyi, Huang, Zhilin, Hong, Shenda, Zhang, Wentao, Cui, Bin
Out-of-distribution (OOD) graph generalization are critical for many real-world applications. Existing methods neglect to discard spurious or noisy features of inputs, which are irrelevant to the label. Besides, they mainly conduct instance-level cla
Externí odkaz:
http://arxiv.org/abs/2306.15902
Autor:
Yang, Ling, Huang, Zhilin, Song, Yang, Hong, Shenda, Li, Guohao, Zhang, Wentao, Cui, Bin, Ghanem, Bernard, Yang, Ming-Hsuan
Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images. Most existing methods address this challenge b
Externí odkaz:
http://arxiv.org/abs/2211.11138
Publikováno v:
In Energy 15 December 2024 312
Publikováno v:
In Science of the Total Environment 25 November 2024 953
Publikováno v:
In Journal of Wind Engineering & Industrial Aerodynamics February 2025 257