Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Guan, Tongkun"'
Handwritten Mathematical Expression Recognition (HMER) has wide applications in human-machine interaction scenarios, such as digitized education and automated offices. Recently, sequence-based models with encoder-decoder architectures have been commo
Externí odkaz:
http://arxiv.org/abs/2407.07764
Existing scene text detection methods typically rely on extensive real data for training. Due to the lack of annotated real images, recent works have attempted to exploit large-scale labeled synthetic data (LSD) for pre-training text detectors. Howev
Externí odkaz:
http://arxiv.org/abs/2312.05286
When handling complicated text images (e.g., irregular structures, low resolution, heavy occlusion, and uneven illumination), existing supervised text recognition methods are data-hungry. Although these methods employ large-scale synthetic text image
Externí odkaz:
http://arxiv.org/abs/2211.00288
Autor:
Guan, Tongkun, Gu, Chaochen, Tu, Jingzheng, Yang, Xue, Feng, Qi, Zhao, Yudi, Yang, Xiaokang, Shen, Wei
The attention mechanism has become the \emph{de facto} module in scene text recognition (STR) methods, due to its capability of extracting character-level representations. These methods can be summarized into implicit attention based and supervised a
Externí odkaz:
http://arxiv.org/abs/2203.03382
Autor:
Guan, Tongkun, Gu, Chaochen, Lu, Changsheng, Tu, Jingzheng, Feng, Qi, Wu, Kaijie, Guan, Xinping
Detecting the marking characters of industrial metal parts remains challenging due to low visual contrast, uneven illumination, corroded character structures, and cluttered background of metal part images. Affected by these factors, bounding boxes ge
Externí odkaz:
http://arxiv.org/abs/2110.12663
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.