Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Zhu, Shenggao"'
Autor:
Huang, Yongshuai, Lu, Ning, Chen, Dapeng, Li, Yibo, Xie, Zecheng, Zhu, Shenggao, Gao, Liangcai, Peng, Wei
Table structure recognition aims to extract the logical and physical structure of unstructured table images into a machine-readable format. The latest end-to-end image-to-text approaches simultaneously predict the two structures by two decoders, wher
Externí odkaz:
http://arxiv.org/abs/2303.06949
Online and offline handwritten Chinese text recognition (HTCR) has been studied for decades. Early methods adopted oversegmentation-based strategies but suffered from low speed, insufficient accuracy, and high cost of character segmentation annotatio
Externí odkaz:
http://arxiv.org/abs/2207.14801
Autor:
Yang, Mingkun, Liao, Minghui, Lu, Pu, Wang, Jing, Zhu, Shenggao, Luo, Hualin, Tian, Qi, Bai, Xiang
Existing text recognition methods usually need large-scale training data. Most of them rely on synthetic training data due to the lack of annotated real images. However, there is a domain gap between the synthetic data and real data, which limits the
Externí odkaz:
http://arxiv.org/abs/2207.00193
Autor:
Kong, Yuxin, Luo, Canjie, Ma, Weihong, Zhu, Qiyuan, Zhu, Shenggao, Yuan, Nicholas, Jin, Lianwen
Automatic font generation remains a challenging research issue due to the large amounts of characters with complicated structures. Typically, only a few samples can serve as the style/content reference (termed few-shot learning), which further increa
Externí odkaz:
http://arxiv.org/abs/2205.00146
Autor:
Huang, Mingxin, Liu, Yuliang, Peng, Zhenghao, Liu, Chongyu, Lin, Dahua, Zhu, Shenggao, Yuan, Nicholas, Ding, Kai, Jin, Lianwen
End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition. However, recent state-of-the-art methods usually incorporate detection an
Externí odkaz:
http://arxiv.org/abs/2203.10209
Autor:
Peng, Dezhi, Wang, Xinyu, Liu, Yuliang, Zhang, Jiaxin, Huang, Mingxin, Lai, Songxuan, Zhu, Shenggao, Li, Jing, Lin, Dahua, Shen, Chunhua, Bai, Xiang, Jin, Lianwen
Existing scene text spotting (i.e., end-to-end text detection and recognition) methods rely on costly bounding box annotations (e.g., text-line, word-level, or character-level bounding boxes). For the first time, we demonstrate that training scene te
Externí odkaz:
http://arxiv.org/abs/2112.07917
Autor:
Gao, Yuzhe, Li, Xing, Zhang, Jiajian, Zhou, Yu, Jin, Dian, Wang, Jing, Zhu, Shenggao, Bai, Xiang
Publikováno v:
[J]. IEEE Transactions on Image Processing, 2021, 30: 9321-9331
Text tracking is to track multiple texts in a video,and construct a trajectory for each text. Existing methodstackle this task by utilizing the tracking-by-detection frame-work, i.e., detecting the text instances in each frame andassociating the corr
Externí odkaz:
http://arxiv.org/abs/2111.04987
In this paper, we abandon the dominant complex language model and rethink the linguistic learning process in the scene text recognition. Different from previous methods considering the visual and linguistic information in two separate structures, we
Externí odkaz:
http://arxiv.org/abs/2108.09661
Scene text retrieval aims to localize and search all text instances from an image gallery, which are the same or similar to a given query text. Such a task is usually realized by matching a query text to the recognized words, outputted by an end-to-e
Externí odkaz:
http://arxiv.org/abs/2104.01552
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.