3D Model Retrieval Using Bipartite Graph Matching Based on Attention

作     者：Sun, Shanlin Li, Yun Xie, Yunfeng Tan, Zhicheng Yao, Xing Zhang, Rongyao 

作者机构：Guilin Univ Aerosp Technol Coll Elect Informat & Automat Guilin 541004 Guangxi Peoples R China Guilin Univ Elect Technol Coll Informat & Commun Guilin 541004 Guangxi Peoples R China 

出 版 物：《NEURAL PROCESSING LETTERS》 (神经处理通讯)

年 卷 期：2020年第52卷第2期

页      面：1043-1055页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China Guangxi Nature Science Fund [2016GXNSFAA380226] Guangxi Science and Technology Project [AC16380094, AA17204086] Guangxi Nature Science Fund Key Project [2016 GXNSFDA380031] Guangxi University Science Research Project [ZD 2014146] 

主　　题：3D model retrieval Bipartite graph matching Attention mechanism 

摘      要：In this paper, we propose an attention-based bipartite graph 3D model retrieval algorithm, where many-to-many matching method, the weighted bipartite graph matching, is employed for comparison between two 3D models. Considering the panoramic views can donate the spatial and structural information, in this work, we use panoramic views to represent each 3D model. Attention mechanism is used to generate the weight of all views of each model. And then, we construct a weighted bipartite graph with the views of those models and the weight of each view. According to the bipartite graph, the matching result is used to measure the similarity between two 3D models. We experiment our method on ModelNet, NTU and ETH datasets, and the experimental results and comparison with other methods show the effectiveness of our method.