Zobrazeno 1 - 10
of 350
pro vyhledávání: '"Zhang, Jianshu"'
Autor:
Ma, Jiefeng, Wang, Yan, Liu, Chenyu, Du, Jun, Hu, Yu, Zhang, Zhenrong, Hu, Pengfei, Wang, Qing, Zhang, Jianshu
Accurately identifying and organizing textual content is crucial for the automation of document processing in the field of form understanding. Existing datasets, such as FUNSD and XFUND, support entity classification and relationship prediction tasks
Externí odkaz:
http://arxiv.org/abs/2406.08757
Image description datasets play a crucial role in the advancement of various applications such as image understanding, text-to-image generation, and text-image retrieval. Currently, image description datasets primarily originate from two sources. One
Externí odkaz:
http://arxiv.org/abs/2406.07502
This paper introduces a novel perspective to significantly mitigate catastrophic forgetting in continuous learning (CL), which emphasizes models' capacity to preserve existing knowledge and assimilate new information. Current replay-based methods tre
Externí odkaz:
http://arxiv.org/abs/2402.01348
Autor:
Pi, Renjie, Han, Tianyang, Zhang, Jianshu, Xie, Yueqi, Pan, Rui, Lian, Qing, Dong, Hanze, Zhang, Jipeng, Zhang, Tong
The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such attacks. Compa
Externí odkaz:
http://arxiv.org/abs/2401.02906
Jailbreak vulnerabilities in Large Language Models (LLMs), which exploit meticulously crafted prompts to elicit content that violates service guidelines, have captured the attention of research communities. While model owners can defend against indiv
Externí odkaz:
http://arxiv.org/abs/2309.05274
Recently, handwritten Chinese character error correction has been greatly improved by employing encoder-decoder methods to decompose a Chinese character into an ideographic description sequence (IDS). However, existing methods implicitly capture and
Externí odkaz:
http://arxiv.org/abs/2307.16253
The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page, neglectin
Externí odkaz:
http://arxiv.org/abs/2303.13839
Autor:
Zhang, Zhenrong, Hu, Pengfei, Ma, Jiefeng, Du, Jun, Zhang, Jianshu, Zhu, Huihui, Yin, Baocai, Yin, Bing, Liu, Cong
Table structure recognition is an indispensable element for enabling machines to comprehend tables. Its primary purpose is to identify the internal structure of a table. Nevertheless, due to the complexity and diversity of their structure and style,
Externí odkaz:
http://arxiv.org/abs/2303.04384
Table of contents (ToC) extraction aims to extract headings of different levels in documents to better understand the outline of the contents, which can be widely used for document understanding and information retrieval. Existing works often use han
Externí odkaz:
http://arxiv.org/abs/2212.02896
Document intelligence as a relatively new research topic supports many business applications. Its main task is to automatically read, understand, and analyze documents. However, due to the diversity of formats (invoices, reports, forms, etc.) and lay
Externí odkaz:
http://arxiv.org/abs/2203.13530