Zobrazeno 1 - 10
of 80
pro vyhledávání: '"Xiong, Yongping"'
Autor:
Yang, Zongyuan, Liu, Baolin, Song, Yingde, Xiong, Yongping, Yi, Lan, Zhang, Zhaohe, Yu, Xunbo
Autostereoscopic display, despite decades of development, has not achieved extensive application, primarily due to the daunting challenge of 3D content creation for non-specialists. The emergence of Radiance Field as an innovative 3D representation h
Externí odkaz:
http://arxiv.org/abs/2407.14053
Multi-modal retrieval becomes increasingly popular in practice. However, the existing retrievers are mostly text-oriented, which lack the capability to process visual information. Despite the presence of vision-language models like CLIP, the current
Externí odkaz:
http://arxiv.org/abs/2406.04292
Autor:
Zhou, Junjie, Shu, Yan, Zhao, Bo, Wu, Boya, Xiao, Shitao, Yang, Xi, Xiong, Yongping, Zhang, Bo, Huang, Tiejun, Liu, Zheng
The evaluation of Long Video Understanding (LVU) performance poses an important but challenging research problem. Despite previous efforts, the existing video understanding benchmarks are severely constrained by several issues, especially the insuffi
Externí odkaz:
http://arxiv.org/abs/2406.04264
Autor:
Liu, Baolin, Yang, Zongyuan, Wang, Pengfei, Zhou, Junjie, Liu, Ziqi, Song, Ziyi, Liu, Yan, Xiong, Yongping
The goal of scene text image super-resolution is to reconstruct high-resolution text-line images from unrecognizable low-resolution inputs. The existing methods relying on the optimization of pixel-level loss tend to yield text edges that exhibit a n
Externí odkaz:
http://arxiv.org/abs/2308.06743
Autor:
Yang, Zongyuan, Liu, Baolin, Xiong, Yongping, Yi, Lan, Wu, Guibin, Tang, Xiaojun, Liu, Ziqi, Zhou, Junjie, Zhang, Xing
Removing degradation from document images not only improves their visual quality and readability, but also enhances the performance of numerous automated document analysis and recognition tasks. However, existing regression-based methods optimized fo
Externí odkaz:
http://arxiv.org/abs/2305.03892
Document binarization is a key pre-processing step for many document analysis tasks. However, existing methods can not extract stroke edges finely, mainly due to the fair-treatment nature of vanilla convolutions and the extraction of stroke edges wit
Externí odkaz:
http://arxiv.org/abs/2302.02073
Transformer models have achieved promising performances in point cloud segmentation. However, most existing attention schemes provide the same feature learning paradigm for all points equally and overlook the enormous difference in size among scene o
Externí odkaz:
http://arxiv.org/abs/2301.06869
Autor:
Wang, Bin-Guo, Huang, Shunxiang, Xiong, Yongping, Xin, Ming-Zhen, LI, Jing, Zhang, Jiangqian, Ma, Zhihui
Non-pharmaceutical interventions(NPIs) play an important role in the early stage control of COVID-19 pandemic. Vaccination is considered to be the inevitable course to stop the spread of SARS-CoV-2. Based on the mechanism, a SVEIR COVID-19 model with
Externí odkaz:
http://arxiv.org/abs/2107.02962
Publikováno v:
In Pattern Recognition February 2024 146
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.