Zobrazeno 1 - 10
of 208
pro vyhledávání: '"Xiao, Luwei"'
Autor:
Zhao, Shuai, Gan, Leilei, Guo, Zhongliang, Wu, Xiaobao, Xiao, Luwei, Xu, Xiaoyu, Nguyen, Cong-Duy, Tuan, Luu Anh
Despite being widely applied due to their exceptional capabilities, Large Language Models (LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce targeted vulnerabilities into LLMs by poisoning training samples and full-
Externí odkaz:
http://arxiv.org/abs/2409.17946
Autor:
Wu, Anran, Xiao, Luwei, Wu, Xingjiao, Yang, Shuwen, Xu, Junjie, Zhuang, Zisong, Xie, Nian, Jin, Cheng, He, Liang
Visually-situated languages such as charts and plots are omnipresent in real-world documents. These graphical depictions are human-readable and are often analyzed in visually-rich documents to address a variety of questions that necessitate complex r
Externí odkaz:
http://arxiv.org/abs/2310.18983
Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compressed evidence features as input
Externí odkaz:
http://arxiv.org/abs/2310.09696
Nowadays, with the explosive growth of multimodal reviews on social media platforms, multimodal sentiment analysis has recently gained popularity because of its high relevance to these social media posts. Although most previous studies design various
Externí odkaz:
http://arxiv.org/abs/2201.10274
Autor:
Wu, Xingjiao, Xiao, Luwei, Du, Xiangcheng, Zheng, Yingbin, Li, Xin, Ma, Tianlong, Jin, Cheng, He, Liang
The document layout analysis (DLA) aims to decompose document images into high-level semantic areas (i.e., figures, tables, texts, and background). Creating a DLA framework with strong generalization capabilities is a challenge due to document object
Externí odkaz:
http://arxiv.org/abs/2201.09407
Autor:
Wu, Xingjiao, Xiao, Luwei, Du, Xiangcheng, Zheng, Yingbin, Li, Xin, Ma, Tianlong, Jin, Cheng, He, Liang
Publikováno v:
In Expert Systems With Applications 1 July 2024 245
Publikováno v:
In Information Fusion June 2024 106
Publikováno v:
Future Generation Computer Systems,2022
Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for computers
Externí odkaz:
http://arxiv.org/abs/2108.00941
Publikováno v:
In Computer Vision and Image Understanding April 2024 241
Autor:
Wang, Jiaqian, Gu, Donghong, Yang, Chi, Xue, Yun, Song, Zhengxin, Zhao, Haoliang, Xiao, Luwei
Multimodal sentiment analysis has currently identified its significance in a variety of domains. For the purpose of sentiment analysis, different aspects of distinguishing modalities, which correspond to one target, are processed and analyzed. In thi
Externí odkaz:
http://arxiv.org/abs/2103.07659