{"type":"ScholarlyArticle","title":"Hierarchical Graph Structure Learning for Multi-View 3D Model Retrieval","authors":[{"name":"Yuting Su","slug":"yuting-su","given":"Yuting","family":"Su","affiliation":"School of Electrical and Information Engineering , Tianjin University , China"},{"name":"Wenhui Li","slug":"wenhui-li","given":"Wenhui","family":"Li","affiliation":"School of Electrical and Information Engineering , Tianjin University , China"},{"name":"Anan Liu","slug":"anan-liu","given":"Anan","family":"Liu","affiliation":"School of Electrical and Information Engineering , Tianjin University , China"},{"name":"Weizhi Nie","slug":"weizhi-nie","given":"Weizhi","family":"Nie","affiliation":"School of Electrical and Information Engineering , Tianjin University , China"}],"abstract":"3D model retrieval has been widely utilized in numerous domains, such as computer-aided design, digital entertainment and virtual reality. Recently, many graph-based methods have been proposed to address this task by using multiple views of 3D models. However, these methods are always constrained by the many-to-many graph matching for similarity measure between pair-wise models. In this paper, we propose an hierarchical graph structure learning method (HGS) for 3D model retrieval. The proposed method can decompose the complicated multi-view graph-based similarity measure into multiple single-view graph-based similarity measures. In the bottom hierarchy, we present the method for single-view graph generation and further propose the novel method for similarity measure in single-view graph by leveraging both node-wise context and model-wise context. In the top hierarchy, we fuse the similarities in single-view graphs with respect to different viewpoints to get the multi-view similarity between pair-wise models. In this way, the proposed method can avoid the difficulty in  definition and computation in the traditional high-order graph. Moreover, this method is unsupervised and is independent of large-scale 3D dataset for model learning. We conduct extensive evaluation on three popular and challenging datasets. The comparison demonstrates the superiority and effectiveness of the proposed method comparing with the state of the arts. Especially, this unsupervised method can achieve competing performance against the most recent supervised & deep learning method.","doi":"10.24963/ijcai.2018/127","url":"https://ijcai.org/proceedings/2018/127","pdf":"https://ijcai.org/proceedings/2018/0127.pdf","markdown":"https://ijcai.org/proceedings/2018/127.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/127","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Computer Vision","track":"Main track","number":127,"pages":{"first":913,"last":919},"keywords":["Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Machine Learning Applications: Applications of Unsupervised Learning"],"videos":[],"references":[{"position":1,"raw":"[Ankerst et al., 1999] Mihael Ankerst, Gabi Kastenmüller, Hans-Peter Kriegel, and Thomas Seidl. 3d shape his- tograms for similarity search and classification in spatial databases. In Advances in Spatial Databases, 6th Interna- tional Symposium, pages 207-226, 1999.","title":"3d shape histograms for similarity search and classification in spatial databases","authors":"Mihael Ankerst, Gabi Kastenmüller, Hans-Peter Kriegel, Thomas Seidl","year":"1999","venue":"Advances in Spatial Databases, 6th International Symposium","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ansary et al., 2007] Tarik Filali Ansary, Mohamed Daoudi, and Jean-Philippe Vandeborre. A bayesian 3-d search en- gine using adaptive views clustering. TMM, 9(1):78-88, 2007.","title":"A bayesian 3-d search engine using adaptive views clustering","authors":"Tarik Filali Ansary, Mohamed Daoudi, Jean-Philippe Vandeborre","year":"2007","venue":"TMM","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bai et al., 2016] Song Bai, Xiang Bai, Zhichao Zhou, Zhaoxiang Zhang, and Longin Jan Latecki. GIFT: A real- time and scalable 3d shape search engine. In CVPR, pages 5023-5032, 2016.","title":"GIFT: A realtime and scalable 3d shape search engine","authors":"Song Bai, Xiang Bai, Zhichao Zhou, Zhaoxiang Zhang, Longin, Jan Latecki","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2003] Ding-Yun Chen, Xiao-Pei Tian, Yu-Te Shen, and Ming Ouhyoung. On visual similarity based 3d model retrieval. In Computer graphics forum, volume 22, pages 223-232, 2003.","title":"On visual similarity based 3d model retrieval","authors":"Ding-Yun Chen, Xiao-Pei Tian, Yu-Te Shen, Ming Ouhyoung","year":"2003","venue":"Computer graphics forum","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Daras and Axenopoulos, 2010] Petros Daras and Apostolos Axenopoulos. A 3d shape retrieval framework supporting multimodal queries. IJCV, 89(2-3):229-247, 2010.","title":"Petros Daras and Apostolos Axenopoulos. A 3d shape retrieval framework supporting multimodal queries","authors":"Axenopoulos Daras","year":"2010","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gao and Dai, 2014] Yue Gao and Qionghai Dai. View- based 3d object retrieval: Challenges and approaches. IEEE MultiMedia, 21(3):52-57, 2014.","title":"Viewbased 3d object retrieval: Challenges and approaches","authors":"Dai Gao, Yue Gao, Qionghai Dai","year":"2014","venue":"IEEE MultiMedia","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gao et al., 2011] Yue Gao, Qionghai Dai, Meng Wang, and Naiyao Zhang. 3d model retrieval using weighted bipartite graph matching. Sig. Proc.: Image Comm., 26(1):39-47, 2011.","title":"3d model retrieval using weighted bipartite graph matching","authors":"Yue Gao, Qionghai Dai, Meng Wang, Naiyao Zhang","year":"2011","venue":"Sig. Proc.: Image Comm","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gao et al., 2012a] Yue Gao, Jinhui Tang, Richang Hong, Shuicheng Yan, Qionghai Dai, Naiyao Zhang, and T-S Chua. Camera constraint-free view-based 3-d object re- trieval. TIP, 21(4):2269-2281, 2012.","title":"Camera constraint-free view-based 3-d object retrieval","authors":"Gao","year":"2012","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gao et al., 2012b] Yue Gao, Meng Wang, Dacheng Tao, Rongrong Ji, and Qionghai Dai. 3-d object retrieval and recognition with hypergraph analysis. TIP, 21(9):4290- 4303, 2012.","title":"3-d object retrieval and recognition with hypergraph analysis","authors":"Gao","year":"2012","venue":"TIP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gao et al., 2016] Zan Gao, Deyu Wang, Hua Zhang, Yan- bing Xue, and Guangping Xu. A fast 3d retrieval algorithm via class-statistic and pair-constraint model. In ACM MM, pages 117-121, 2016.","title":"A fast 3d retrieval algorithm via class-statistic and pair-constraint model","authors":"Zan Gao, Deyu Wang, Hua Zhang, Yanbing Xue, Guangping Xu","year":"2016","venue":"ACM MM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gao et al., 2018] Zan Gao, Deyu Wang, Xiangnan He, and Hua Zhang. Group-pair convolutional neural networks for multi-view based 3d object retrieval. In AAAI, 2018.","title":"Group-pair convolutional neural networks for multi-view based 3d object retrieval","authors":"Zan Gao, Deyu Wang, Xiangnan He, Hua Zhang","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hilaga et al., 2001] Masaki Hilaga, Yoshihisa Shinagawa, Taku Komura, and Tosiyasu L. Kunii. Topology match- ing for fully automatic similarity estimation of 3d shapes. In SIGGRAPH, pages 203-212, 2001.","title":"Topology matching for fully automatic similarity estimation of 3d shapes","authors":"Masaki Hilaga, Yoshihisa Shinagawa, Taku Komura, Tosiyasu L Kunii","year":"2001","venue":"SIGGRAPH","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pages 1106- 1114, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Leibe and Schiele, 2003] Bastian Leibe and Bernt Schiele. Analyzing appearance and contour based methods for ob- ject categorization. In CVPR, pages 409-415, 2003.","title":"Analyzing appearance and contour based methods for object categorization","authors":"Schiele Leibe, Bastian Leibe, Bernt Schiele","year":"2003","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li and An, 2017] Wenhui Li and Yang An. View-wised dis- criminative ranking for 3d object retrieval. Multimedia Tools and Applications, 1:1-15, 2017.","title":"View-wised discriminative ranking for 3d object retrieval","authors":"An ; Li, Wenhui Li, Yang An","year":"2017","venue":"Multimedia Tools and Applications","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2015] Anan Liu, Zhongyang Wang, Weizhi Nie, and Yuting Su. Graph-based characteristic view set extrac- tion and matching for 3d model retrieval. IS, 320:429-442, 2015.","title":"Graph-based characteristic view set extraction and matching for 3d model retrieval","authors":"Anan Liu, Zhongyang Wang, Weizhi Nie, Yuting Su","year":"2015","venue":"IS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2016] Anan Liu, Weizhi Nie, Yue Gao, and Yut- ing Su. Multi-modal clique-graph matching for view- based 3d model retrieval. IEEE Trans. Image Processing, 25(5):2103-2116, 2016.","title":"Multi-modal clique-graph matching for viewbased 3d model retrieval","authors":"Anan Liu, Weizhi Nie, Yue Gao, Yuting Su","year":"2016","venue":"IEEE Trans. Image Processing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2017] AnAn Liu, Weizhi Nie, Yue Gao, and Yut- ing Su. View-based 3-d model retrieval: A benchmark. IEEE Transactions on Cybernetics, 2017.","title":"View-based 3-d model retrieval: A benchmark","authors":"Anan Liu, Weizhi Nie, Yue Gao, Yuting Su","year":"2017","venue":"IEEE Transactions on Cybernetics","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Nie et al., 2013] Liqiang Nie, Meng Wang, Yue Gao, Zheng-Jun Zha, and Tat-Seng Chua. Beyond text QA: multimedia answer generation by harvesting web informa- tion. IEEE Trans. Multimedia, 15(2):426-441, 2013.","title":"Beyond text QA: multimedia answer generation by harvesting web information","authors":"Liqiang Nie, Meng Wang, Yue Gao, Zheng-Jun Zha, Tat-Seng Chua","year":"2013","venue":"IEEE Trans. Multimedia","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Nie et al., 2016] Liqiang Nie, Xuemeng Song, and Tat-Seng Chua. Learning from Multiple Social Networks. Synthe- sis Lectures on Information Concepts, Retrieval, and Ser- vices. Morgan & Claypool Publishers, 2016.","title":"Learning from Multiple Social Networks","authors":"Liqiang Nie, Xuemeng Song, Tat-Seng Chua","year":"2016","venue":"Synthesis Lectures on Information Concepts, Retrieval, and Services","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Savva et al., 2016] Manolis Savva, Fisher Yu, Hao Su, Masaki Aono, Baoquan Chen, and et al. Large-scale 3d shape retrieval from shapenet core55. In 9th Eurographics Workshop on 3D Object Retrieval, 3DOR, 2016.","title":"Large-scale 3d shape retrieval from shapenet core55","authors":"Manolis Savva, Fisher Yu, Hao Su, Masaki Aono, Baoquan Chen","year":"2016","venue":"9th Eurographics Workshop on 3D Object Retrieval","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Su et al., 2015] Hang Su, Subhransu Maji, Evangelos Kalogerakis, and Erik G. Learned-Miller. Multi-view con- volutional neural networks for 3d shape recognition. In ICCV, pages 945-953, 2015.","title":"Learned-Miller. Multi-view convolutional neural networks for 3d shape recognition","authors":"Su","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Webber et al., 2010] William Webber, Alistair Moffat, and Justin Zobel. A similarity measure for indefinite rankings. ACM Trans. Inf. Syst., 28(4):20:1-20:38, 2010.","title":"A similarity measure for indefinite rankings","authors":"William Webber, Alistair Moffat, Justin Zobel","year":"2010","venue":"ACM Trans. Inf. Syst","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang et al., 2018] Jianbai Yang, Jian Zhao, and Qiang Sun. 3d model retrieval using constructive-learning for cross- model correlation. Neurocomputing, 275:1-9, 2018.","title":"3d model retrieval using constructive-learning for crossmodel correlation","authors":"Yang","year":"2018","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}