no code implementations • 16 Apr 2024 • Yuqi Wang, Boran Jiang, Yi Luo, Dawei He, Peng Cheng, Liangcai Gao
Especially for the question that require a multi-hop reasoning path, frequent calls to LLM will consume a lot of computing power.
1 code implementation • 24 Nov 2023 • Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen, Yusu Wang
To efficiently encode the space of all cycles, we start with a cycle basis (i. e., a minimal set of cycles generating the cycle space) which we compute via the kernel of the 1-dimensional Hodge Laplacian of the input graph.
no code implementations • 22 Nov 2023 • Yuxuan Zhou, Liangcai Gao, Zhi Tang, Baole Wei
Scene Text Image Super-Resolution (STISR) aims to enhance the resolution and legibility of text within low-resolution (LR) images, consequently elevating recognition accuracy in Scene Text Recognition (STR).
1 code implementation • 19 Mar 2023 • Zuoyu Yan, Junru Zhou, Liangcai Gao, Zhi Tang, Muhan Zhang
Among these works, a popular way is to use subgraph GNNs, which decompose the input graph into a collection of subgraphs and enhance the representation of the graph by applying GNN to individual subgraphs.
no code implementations • CVPR 2023 • Yongshuai Huang, Ning Lu, Dapeng Chen, Yibo Li, Zecheng Xie, Shenggao Zhu, Liangcai Gao, Wei Peng
The ablation study also validates that the proposed coordinate sequence decoder and the visual-alignment loss are the keys to the success of our method.
1 code implementation • 10 Jul 2022 • Wenqi Zhao, Liangcai Gao
In this paper, we propose CoMER, a model that adopts the coverage information in the transformer decoder.
1 code implementation • 28 Jan 2022 • Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Yusu Wang, Chao Chen
Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods.
1 code implementation • 6 Oct 2021 • Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen
In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics of algebraic topology.
Graph Representation Learning Inductive Relation Prediction +1
no code implementations • 29 Sep 2021 • Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen
We propose to collect cycle bases that span the space of cycles.
1 code implementation • 6 May 2021 • Wenqi Zhao, Liangcai Gao, Zuoyu Yan, Shuai Peng, Lin Du, Ziyin Zhang
Encoder-decoder models have made great progress on handwritten mathematical expression recognition recently.
no code implementations • 2 May 2021 • Shuai Peng, Ke Yuan, Liangcai Gao, Zhi Tang
Large-scale pre-trained models like BERT, have obtained a great success in various Natural Language Processing (NLP) tasks, while it is still a challenge to adapt them to the math-related tasks.
no code implementations • 24 Apr 2021 • Ke Yuan, Zuoyu Yan, Yibo Li, Liangcai Gao, Zhi Tang
In the Selector, a Topic Relation Graph (TRG) is proposed to obtain the relevant documents which contain the comprehensive information of math expressions.
no code implementations • 27 Mar 2021 • Zhuoren Jiang, Xiaozhong Liu, Liangcai Gao, Zhi Tang
Although the content in scientific publications is increasingly challenging, it is necessary to investigate another important problem, that of scientific information understanding.
1 code implementation • 20 Feb 2021 • Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen
Link prediction is an important learning task for graph-structured data.
no code implementations • 23 Dec 2020 • Zuoyu Yan, Xiaode Zhang, Liangcai Gao, Ke Yuan, Zhi Tang
Despite the recent advances in optical character recognition (OCR), mathematical expressions still face a great challenge to recognize due to their two-dimensional graphical layout.
Optical Character Recognition Optical Character Recognition (OCR)
1 code implementation • 27 Nov 2019 • Ke Yuan, Dafang He, Zhuoren Jiang, Liangcai Gao, Zhi Tang, C. Lee Giles
Compared to conventional summarization tasks, this task has two extra and essential constraints: 1) Detailed math questions consist of text and math equations which require a unified framework to jointly model textual and mathematical information; 2) Unlike text, math equations contain semantic and structural features, and both of them should be captured together.
1 code implementation • 31 Dec 2018 • Zhuoren Jiang, Yue Yin, Liangcai Gao, Yao Lu, Xiaozhong Liu
While the volume of scholarly publications has increased at a frenetic pace, accessing and consuming the useful candidate papers, in very large digital libraries, is becoming an essential and challenging task for scholars.
no code implementations • 1 Jun 2018 • Ting-Ting Liang, Satoshi Tsutsui, Liangcai Gao, Jing-Jing Lu, Mengyan Sun
One of the time-consuming routine work for a radiologist is to discern anatomical structures from tomographic images.
no code implementations • 7 Mar 2017 • Wenhao Zhang, Liangcai Gao, Runtao Liu
The models are built on the source images are using the Caffe [4] framework.