Zobrazeno 1 - 10
of 93
pro vyhledávání: '"Tang, Guozhi"'
Autor:
Wang, An-Lan, Shan, Bin, Shi, Wei, Lin, Kun-Yu, Fei, Xiang, Tang, Guozhi, Liao, Lei, Tang, Jingqun, Huang, Can, Zheng, Wei-Shi
This work presents ParGo, a novel Partial-Global projector designed to connect the vision and language modalities for Multimodal Large Language Models (MLLMs). Unlike previous works that rely on global attention-based projectors, our ParGo bridges th
Externí odkaz:
http://arxiv.org/abs/2408.12928
Autor:
Luo, Chuwei, Tang, Guozhi, Zheng, Qi, Yao, Cong, Jin, Lianwen, Li, Chenliang, Xue, Yang, Si, Luo
Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks. Though existing document pre-trained models have achieved excellent performance on standard benchmarks for VrD
Externí odkaz:
http://arxiv.org/abs/2206.13155
Publikováno v:
In Knowledge-Based Systems 5 September 2024 299
Publikováno v:
In Knowledge-Based Systems 5 September 2024 299
Autor:
Tang, Guozhi, Xie, Lele, Jin, Lianwen, Wang, Jiapeng, Chen, Jingdong, Xu, Zhen, Wang, Qianying, Wu, Yaqiang, Li, Hui
Visual Information Extraction (VIE) task aims to extract key information from multifarious document images (e.g., invoices and purchase receipts). Most previous methods treat the VIE task simply as a sequence labeling problem or classification proble
Externí odkaz:
http://arxiv.org/abs/2106.12940
Autor:
Wang, Jiapeng, Wang, Tianwei, Tang, Guozhi, Jin, Lianwen, Ma, Weihong, Ding, Kai, Huang, Yichao
Visual information extraction (VIE) has attracted increasing attention in recent years. The existing methods usually first organized optical character recognition (OCR) results into plain texts and then utilized token-level entity annotations as supe
Externí odkaz:
http://arxiv.org/abs/2106.10681
Autor:
Wang, Jiapeng, Liu, Chongyu, Jin, Lianwen, Tang, Guozhi, Zhang, Jiaxin, Zhang, Shuaitao, Wang, Qianying, Wu, Yaqiang, Cai, Mingxiang
Visual information extraction (VIE) has attracted considerable attention recently owing to its various advanced applications such as document understanding, automatic marking and intelligent education. Most existing works decoupled this problem into
Externí odkaz:
http://arxiv.org/abs/2102.06732
Publikováno v:
In Neurocomputing 29 January 2021 423:389-398
Autor:
Xu, Danqing, Xu, Zhiheng, Han, Li, Liu, Cheng, Zhou, Zheng, Qiu, Zongxing, Lin, Xianfeng, Tang, Guozhi, Shen, Hong, Aebi, Johannes, Riemer, Claus, Kuhn, Bernd, Stahl, Martin, Mark, David, Qin, Ning *, Ding, Haiyuan **
Publikováno v:
In SLAS Discovery April 2017 22(4):338-347
Autor:
Qiu, Ke, Deng, Zhiling, He, Taiyu, Chen, Zhi-wei, Yuan, Taichang, Tang, Guozhi, Peng, Ming-Li, Ren, Hong
Publikováno v:
In Journal of Hepatology June 2024 80 Supplement 1:S727-S727