Zobrazeno 1 - 10
of 104
pro vyhledávání: '"Chen, Jinyue"'
Autor:
Wei, Haoran, Liu, Chenglong, Chen, Jinyue, Wang, Jia, Kong, Lingyu, Xu, Yanming, Ge, Zheng, Zhao, Liang, Sun, Jianjian, Peng, Yuang, Han, Chunrui, Zhang, Xiangyu
Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters. In this paper, we collectively refer to all artificial optical signals (e.g., plain
Externí odkaz:
http://arxiv.org/abs/2409.01704
Autor:
Liu, Chenglong, Wei, Haoran, Chen, Jinyue, Kong, Lingyu, Ge, Zheng, Zhu, Zining, Zhao, Liang, Sun, Jianjian, Han, Chunrui, Zhang, Xiangyu
Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages. Accordingly, this paper propos
Externí odkaz:
http://arxiv.org/abs/2405.14295
Autor:
Chen, Jinyue, Kong, Lingyu, Wei, Haoran, Liu, Chenglong, Ge, Zheng, Zhao, Liang, Sun, Jianjian, Han, Chunrui, Zhang, Xiangyu
Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of parameters struggle to handle such tasks satisfactorily. To address this, we
Externí odkaz:
http://arxiv.org/abs/2404.09987
Autor:
Wei, Haoran, Kong, Lingyu, Chen, Jinyue, Zhao, Liang, Ge, Zheng, Yu, En, Sun, Jianjian, Han, Chunrui, Zhang, Xiangyu
Playing Large Vision Language Models (LVLMs) in 2023 is trendy among the AI community. However, the relatively large number of parameters (more than 7B) of popular LVLMs makes it difficult to train and deploy on consumer GPUs, discouraging many resea
Externí odkaz:
http://arxiv.org/abs/2401.12503
Autor:
Wei, Haoran, Kong, Lingyu, Chen, Jinyue, Zhao, Liang, Ge, Zheng, Yang, Jinrong, Sun, Jianjian, Han, Chunrui, Zhang, Xiangyu
Modern Large Vision-Language Models (LVLMs) enjoy the same vision vocabulary -- CLIP, which can cover most common vision tasks. However, for some special vision task that needs dense and fine-grained vision perception, e.g., document-level OCR or cha
Externí odkaz:
http://arxiv.org/abs/2312.06109
Autor:
Hou, Wenlong, Chen, Jinyue, He, Maoxia, Ren, Shilong, Fang, Lei, Wang, Chongyang, Jiang, Peng, Wang, Wanting
Publikováno v:
In Marine Environmental Research June 2024 198
Publikováno v:
In Journal of Contaminant Hydrology February 2024 261
Publikováno v:
In Journal of Contaminant Hydrology November 2023 259
Autor:
Hao, Min, Chen, Jing, Chen, Jinyue, Wang, Kexin, Wang, Jiale, Lei, Fengcai, Hao, Pin, Sun, Xu, Xie, Junfeng, Tang, Bo
Publikováno v:
In Journal of Colloid And Interface Science 15 July 2023 642:41-52
Publikováno v:
In Process Safety and Environmental Protection January 2023 169:238-251