2 citations · 6 across the 4 of their papers we have counts for
4 papers
MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images
Weihao Liu, Fangyu Lei, Tongxu Luo +4
In the real world, knowledge often exists in a multimodal and heterogeneous form. Addressing the task of question answering with hybrid data types, including text, tables, and imag…
GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials
Xun Liu, Alex Hay-Man Ng, Fangyuan Lei +2
Graph Neural Networks (GNNs) are a promising deep learning approach for circumventing many real-world problems on graph-structured data. However, these models usually have at least…
PatentNet: A Large-Scale Incomplete Multiview, Multimodal, Multilabel Industrial Goods Image Database
Fangyuan Lei, Da Huang, Jianjian Jiang +5
In deep learning area, large-scale image datasets bring a breakthrough in the success of object recognition and retrieval. Nowadays, as the embodiment of innovation, the diversity…
Hybrid Low-order and Higher-order Graph Convolutional Networks
FangYuan Lei, Xun Liu, QingYun Dai +3
With higher-order neighborhood information of graph network, the accuracy of graph representation learning classification can be significantly improved. However, the current higher…