Xiantao Cai

Prof. Dr. Xiantao Cai

Wuhan University, Wuhan, Hubei, China

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 September 2020 in IEEE Access
Verified
Journal Article
Open access
YAYong Ai
Yong Ai
CSChong Sun
Chong Sun
JTJun Tie
Jun Tie
XCXiantao Cai
Xiantao Cai
Agricultural diseases and insect pests are one of the most important factors that seriously threaten agricultural production. Early detection and identification of pests can effectively reduce the economic losses caused by pests. In this paper, convolution neural network is used to automatically identify crop diseases. The data set comes from the public data set of the AI Challenger Competition in 2018, with 27 disease images of 10 crops. In this paper, the Inception-ResNet-v2 model is used for training. The cross-layer direct edge and multi-layer convolution in the residual network unit to the model. After the combined convolution operation is completed, it is activated by the connection into the ReLu function. The experimental results show that the overall recognition accuracy is 86.1% in this model, which verifies the effectiveness. After the training of this model, we designed and implemented the Wechat applet of crop diseases and insect pests recognition. Then we carried out the actual test. The results show that the system can accurately identify crop diseases, and give the corresponding guidance.

14 March 2022 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
BNBo Ni
Bo Ni
ZLZhiyuan Liu
Zhiyuan Liu
XCXiantao Cai
Xiantao Cai
Michele NappiMichele Nappi
Michele Nappi
Shaohua WanShaohua Wan
Shaohua Wan

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
LHLiqi He
Liqi He
LZLi Zuchao
Li Zuchao
XCXiantao Cai
Xiantao Cai
PWPing Wang
Ping Wang
Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images. Previous research on multi-modal CoT has primarily focused on extracting fixed image features from off-the-shelf vision models and then fusing them with text using attention mechanisms. This approach has limitations because these vision models were not designed for complex reasoning tasks and do not align well with language thoughts. To overcome this limitation, we introduce a novel approach for multi-modal CoT reasoning that utilizes latent space learning via diffusion processes to generate effective image features that align with language thoughts. Our method fuses image features and text representations at a deep level and improves the complex reasoning ability of multi-modal CoT. We demonstrate the efficacy of our proposed method on multi-modal ScienceQA and machine translation benchmarks, achieving state-of-the-art performance on ScienceQA. Overall, our approach offers a more robust and effective solution for multi-modal reasoning in language models, enhancing their ability to tackle complex real-world problems.

11 January 2021 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
YYYiming Yuan
Yiming Yuan
XCXiantao Cai
Xiantao Cai
6G-Enabled Internet of Things (IoT) is about to open a new era of Internet of Everything (IoE). It creates favorable conditions for new application services. The human-machine dialogue system, one of the most important forms of human–machine interaction, is expected to replace mobile applications in the future. This article proposes a dialogue generation scheme named background knowledge-aware dialogue generation model with pretrained encoders (BKADGPE). Dialogue generation, which takes the context as input and response as output, is a sequence-to-sequence (Seq2Seq) task. Instead of only generating the response based on the previous sequence of utterances, background knowledge-aware dialogue generation is also relying on background knowledge documents. This is because people often communicate based on their background knowledge. This article divides it into two tasks: 1) a knowledge selection task and 2) a response generation task. One of the latest language pretraining models, a lite bidirectional encoder representations from transformers (ALBERT), is applied as the encoder. In the knowledge selection task, ALBERT adds the linear layer and softmax layer to predict the content-related knowledge span. In the response generation task, the ALBERT after fine-tuning through the knowledge selection task adds the left-context-only transformer with a copy mechanism to incorporate background knowledge span into the generated response. Empirical studies on the HOLL-E dataset show that the result of BKADGPE is better than the related works.

26 October 2023
Verified
Conference Paper
Open access
QLQiwei Li
Qiwei Li
LZLi Zuchao
Li Zuchao
XCXiantao Cai
Xiantao Cai
BDBo Du
Bo Du
HZHai Zhao
Hai Zhao
In recent years, the use of multi-modal pre-trained Transformers has led to significant advancements in visually-rich document understanding. However, existing models have mainly focused on features such as text and vision while neglecting the importance of layout relationship between text nodes. In this paper, we propose GraphLayoutLM, a novel document understanding model that leverages the modeling of layout structure graph to inject document layout knowledge into the model. GraphLayoutLM utilizes a graph reordering algorithm to adjust the text sequence based on the graph structure. Additionally, our model uses a layout-aware multi-head self-attention layer to learn document layout knowledge. The proposed model enables the understanding of the spatial arrangement of text elements, improving document comprehension. We evaluate our model on various benchmarks, including FUNSD, XFUND and CORD and it achieves state-of-the-art results among these datasets. Our experiment results demonstrate that our proposed method provides a significant improvement over existing approaches and showcases the importance of incorporating layout information into document understanding models. We also conduct an ablation study to investigate the contribution of each component of our model. The results show that both the graph reordering algorithm and the layout-aware multi-head self-attention layer play a crucial role in achieving the best performance.

1 January 2008
Verified
Conference Paper
Closed access
PDF file
SJShuxu Jing
Shuxu Jing
FHFazhi He
Fazhi He
XCXiantao Cai
Xiantao Cai
HLHuajun Liu
Huajun Liu
In this paper, a framework of full replicated collaborative solid modeling and a method for multi-user interaction to support natural, free, fast and less-constrained multi-user human-to-human interaction is proposed. Particularly, the challenges and problems of topological entity correspondence by name across collaborative modeling sites in replicated CSM system is analyzed. And a method to achieve name correspondence during collaborative modeling sessions in replicated CSM system is proposed. The proposed method is tested in a prototype system of replicated CSM, which employs ACIS as the geometric modeling kernel and adopts winsocket API for communication purpose, developed by our research group.