Zobrazeno 1 - 10
of 592
pro vyhledávání: '"Cai Yuanqiang"'
Removing multiple degradations, such as haze, rain, and blur, from real-world images poses a challenging and illposed problem. Recently, unified models that can handle different degradations have been proposed and yield promising results. However, th
Externí odkaz:
http://arxiv.org/abs/2307.05075
Generally pre-training and long-time training computation are necessary for obtaining a good-performance text detector based on deep networks. In this paper, we present a new scene text detection network (called FANet) with a Fast convergence speed a
Externí odkaz:
http://arxiv.org/abs/2207.01342
Recent video text spotting methods usually require the three-staged pipeline, i.e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results. These methods typically follow
Externí odkaz:
http://arxiv.org/abs/2203.10539
Filtering properties of locally resonant periodic foundations (LRPFs) have inspired an innovative direction towards the mitigation of structural vibrations. To mitigate the structure-borne vibrations from subways, this study proposes an LRPF equipped
Externí odkaz:
http://arxiv.org/abs/2201.06295
Autor:
Wu, Weijia, Cai, Yuanqiang, Zhang, Debing, Wang, Sibo, Li, Zhuang, Li, Jiahong, Tang, Yejun, Zhou, Hong
Publikováno v:
NeurIPS 2021 Track on Datasets and Benchmarks
Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset(BOVText). There are four features for BOVT
Externí odkaz:
http://arxiv.org/abs/2112.04888
Publikováno v:
In Journal of Rock Mechanics and Geotechnical Engineering August 2024 16(8):3327-3338
Publikováno v:
In Soil Dynamics and Earthquake Engineering July 2024 182
Publikováno v:
In Computers and Geotechnics July 2024 171
Publikováno v:
In Composite Structures 1 June 2024 337