Yushen LIU-School of Software, Tsinghua University

Faculty

Name: Yushen LIU

Title: Associate Professor

Email: liuyushen@tsinghua.edu.cn

Telephone: +86-10-62795455

Research Fields: 3D Computer Vision, Shape Analysis, 3D Deep Learning, Point Cloud Understanding. Information Retrieval, Cross-model Retrieval, Semantic Search. Smart Building, Building Information Modeling (BIM). Digital Geometry Processing (DGP), Computer Graphics, Computer Aided Design.

Homepage: https://yushen-liu.github.io/

Education background

2000 - 2006: Tsinghua University. Ph.D. in Computer Science and Technology.

1996 - 2000: Jilin University. B.Sc. in Mathematics.

Experience

2009 - present: School of Software at Tsinghua University, Beijing, China.

2006 - 2009: Purdue University, West Lafayette, IN, USA. Postdoctoral researcher in School of Mechanical Engineering.

Social service

Senior Program Committee member at IJCAI 2021

Program Committee member at ACM Multimedia 2020, ACM Multimedia 2019

Program Committee member at AAAI 2021, AAAI 2020

Program Committee member at LCLR 2021 Program Committee member at IJCAI 2020, IJCAI 2019

Program Committee member at WACV 2020, GDC 2019, CAD&CG 2019, ACM Multimedia Asia 2019

Program Committee of EG-ICE 2019(European Group for Intelligent Computing in Engineering)

The editorial team of Construction Innovation, 2018 ~ present

Co-chairs of PLM Smart Manufacturing Workshop, 2018 Asian Conference on Design and Digital Engineering (ACDDE2018).

The program committee of AUAPAF2018 (Asian Universities Alliance Postgraduate Academic Forum).

The member on IFC Alignment 1.1 Expert Panel in buildingSMART.

Working on the group of buildingSMART IFC Roads and Railway Standard.

Editorial Board Member on the international journal Smart Construction Research, 2017 ~ present.

Lead Guest Editor: Special Issue on Recent Advances on Building Information Modeling (BIM). The Scientific World Journal, 2014.

Guest Editor: Special Issue on Advances in Conceptual Design Theories, Methodologies, and Applications. Advances in Mechanical Engineering, 2013.

Research Status

National Key R&D Program of China (2018YFB0505403), 2018.05-2022.04, PI.

NSF: Studies on semantic retrieval for building information modeling (BIM) resources based on IFC (61472202), 2015.01-2018.12, PI.

NSF: Studies on shape matching for 3D articulated models based on metric geometry (61272229), 2013.01-2016.12, PI.

NSF: Study of non-rigid 3D shape retrieval (61003095), 2011.01-2013.12, PI. National Technological Support Program for the 12th-Five-Year Plan of China (2012BAJ03B07), 2012.01-2015.09, Major Researcher.

NSF: China building information technology strategic research (U0970155), 2009, Major Researcher.

Teaching Courses

《Fundamental of Programming》 (#34100063), the undergraduate course.

《Digital Multimedia》 (#44100415), the undergraduate course.

《Digital Geometry Processing》 (#84100272), the graduate course.

《Business Process and Asset Management》 (#84108033), the graduate course.

Honors And Awards

On 2019, "Tsinghua University Annual Teaching Excellence" Award.

On 2017, "Tsinghua University Excellent Award Class (Grade) Teacher" Award (the first prize).

On 2016, Highly Cited Research Award, by the journal of Advanced Engineering Informatics (the Elsevier journal), 2016. Dr. Yu-Shen Liu is the corresponding author of this paper.

On 2016, Best Student Presentation Award, at the 16th International Conference on Computing in Civil and Building Engineering (ICCCBE2016), Osaka, Japan, 2016. Dr. Yu-Shen Liu is the corresponding author of this paper, and Ge Gao is the first author.

On 2015, Best Student Paper Award, at the Proceedings of the Ninth International Conference on Computer Aided Design and Computer Graphics (CAD-CG'05), Hong Kong, China, 2005.

On 2006, Excellent Doctoral Dissertation Award of Tsinghua University in 2006.

On 2005, Intel scholarship 2005.

On 2004, Excellent Mentor Award of Tsinghua University, 2004.

Academic Achievement

Selected Publications：

[1] Xin Wen, Peng Xiang, Zhizhong Han, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Yu-Shen Liu. PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[2] Xin Wen, Zhizhong Han, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Yu-Shen Liu. Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[3] Xinhai Liu, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker. Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions. IEEE Transactions on Image Processing, 2021, 30: 1744-1758. (SCI, 2019 Impact factor: 9.34)

[4] Xin Wen, Zhizhong Han, Xinhai Liu, Yu-Shen Liu. Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules. IEEE Transactions on Image Processing, 2020, 29: 8855-8869. (SCI, 2019 Impact factor: 9.34)

[5] Zhizhong Han, Baorui Ma, Yu-Shen Liu, Matthias Zwicker. Reconstructing 3D Shapes from Multiple Sketches using Direct Shape Optimization. IEEE Transactions on Image Processing, 2020, 29: 8721-8734. (SCI, 2019 Impact factor: 9.34)

[6] Xin Wen, Zhizhong Han, Yu-Shen Liu. CMPD: Using Cross Memory Network with Pair Discrimination for Image-Text Retrieval. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020.

[7] Xin Wen, Zhizhong Han, Geunhyuk Youk, Yu-Shen Liu. CF-SIS: Semantic-Instance Segmentation of 3D Point Clouds by Context Fusion with Self-Attention. Proceedings of the 28th ACM International Conference on Multimedia (ACM MM'20), pp. 1661-1669.

[8] Zhizhong Han, Chao Chen, Yu-Shen Liu, Matthias Zwicker. ShapeCaptioner: Generative Caption Network for 3D Shapes by Learning a Mapping from Parts Detected in Multiple Views to Sentences. Proceedings of the 28th ACM International Conference on Multimedia (ACM MM'20), pp. 1018-1027.

[9] Zhizhong Han, Guanhui Qiao, Yu-Shen Liu, Matthias Zwicker. SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates. European Conference on Computer Vision (ECCV), 2020, LNCS 12369, pp. 607–625.

[10] Zhizhong Han, Chao Chen, Yu-Shen Liu, Matthias Zwicker. DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Images. Proceedings of the 37th International Conference on Machine Learning (ICML), 2020, PMLR 119:3994-4005.

[11] Xin Wen, Tianyang Li, Zhizhong Han, Yu-Shen Liu. Point Cloud Completion by Skip-attention Network with Hierarchical Folding. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

[12] Xinhai Liu, Zhizhong Han, Fangzhou Hong, Yu-Shen Liu, Matthias Zwicker. LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts. The 14th International Conference on Geometric Modeling and Processing (GMP), 2020. (Special issue in the journal of Computer-Aided Geometric Design (Elsevier)).

[13] Nanxing Li, Qian Li, Yu-Shen Liu, Wenlong Lu, Wanqi Wang. BIMSeek++: Retrieving BIM Components using Similarity Measurement of Attributes. Computers in Industry, 2020, 116:103186, 1-12.

[14] Zhizhong Han, Honglei Lu, Zhenbao Liu, Chi-Man Vong, Yu-Shen Liu, Matthias Zwicker, Junwei Han, C.L. Philip Chen. 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN with Hierarchical Attention Aggregation. IEEE Transactions on Image Processing, 2019, 28(8): 3986-3999.

[15] Zhizhong Han, Mingyang Shang, Zhenbao Liu, Chi-Man Vong, Yu-Shen Liu, Matthias Zwicker, Junwei Han, C.L. Philip Chen. SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN with Attention. IEEE Transactions on Image Processing, 2019, 28(2): 658-672.

[16] Han Liu, Zhizhong Han, Yu-Shen Liu, Ming Gu. Fast Low-rank Metric Learning for Large-scale and High-dimensional Data. Neural Information Processing Systems (NeurIPS), 2019, pp. 819-829, Vancouver, Canada.

[17] Zhizhong Han, Xiyang Wang, Yu-Shen Liu, Matthias Zwicker. Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction. IEEE International Conference on Computer Vision (ICCV), 2019, pp. 10441-10450.

[18] Xinhai Liu, Zhizhong Han, Xin Wen, Yu-Shen Liu, Matthias Zwicker. L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention. Proceedings of the 27th ACM International Conference on Multimedia (ACM MM'19), 2019, pp. 989-997.

[19] Zhizhong Han, Xinhai Liu, Yu-Shen Liu, Matthias Zwicker. Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views. International Joint Conference on Artificial Intelligence (IJCAI), 2019, pp. 766-773.

[20] Zhizhong Han, Xiyang Wang, Chi-Man Vong, Yu-Shen Liu, Matthias Zwicker, C.L. Philip Chen. 3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention. International Joint Conference on Artificial Intelligence (IJCAI), 2019, pp. 758-765.

[21] Zhizhong Han, Mingyang Shang, Yu-Shen Liu, Matthias Zwicker. View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019, 33(01): 8376-8384.

[22] Zhizhong Han, Mingyang Shang, Xiyang Wang, Yu-Shen Liu, Matthias Zwicker. Y2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019, 33(01): 126-133.

[23] Xinhai Liu, Zhizhong Han, Yu-Shen Liu, Matthias Zwicker. Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019, 33(01): 8778-8785.

[24] Nanxing Li, Bei Liu, Zhizhong Han, Yu-Shen Liu, Jianlong Fu. Emotion Reinforced Visual Storytelling. ACM International Conference on Multimedia Retrieval (ICMR), 2019, pp.297-305, Ottawa, ON, Canada.

[25] Xin Wen, Zhizhong Han, Xinyu Yin, Yu-Shen Liu. Adversarial Cross-Modal Retrieval via Learning and Transferring Single-Modal Similarities. IEEE International Conference on Multimedia and Expo (ICME), 2019, pp.478-483.

[26] Zhizhong Han, Zhenbao Liu, Chi-Man Vong, Yu-Shen Liu, Shuhui Bu, Junwei Han, C.L. Philip Chen. Deep Spatiality: Unsupervised Learning of Spatially-Enhanced Global and Local 3D Features by Deep Neural Network with Coupled Softmax. IEEE Transactions on Image Processing, 2018, 27(6): 3049-3063.

[27] Xin Shi, Yu-Shen Liu, Ge Gao, Ming Gu, Haijiang Li. IFCdiff: A content-based automatic comparison approach for IFC files. Automation in Construction, 2018, 86: 53–68.

[28] Zhizhong Han, Zhenbao Liu, Chi-Man Vong, Yu-Shen Liu, Shuhui Bu, Junwei Han, C.L. Philip Chen. BoSCC: Bag of Spatial Context Correlations for Spatially Enhanced 3D Shape Representation. IEEE Transactions on Image Processing, 2017, 26(8): 3707-3720.

[29] Han Liu, Yu-Shen Liu, Pieter Pauwels, Hongling Guo, Ming Gu. Enhanced explicit semantic analysis for product model retrieval in construction industry. IEEE Transactions on Industrial Informatics, 2017, 13(6): 3361-3369.

[30] Ge Gao, Yu-Shen Liu, Pengpeng Lin, Meng Wang, Ming Gu, Jun-Hai Yong. BIMTag: Concept-based automatic semantic annotation of online BIM product resources. Advanced Engineering Informatics, 2017, 31: 48-61.

[31] Ge Gao, Yu-Shen Liu, Jia-Xing Wu, Ming Gu, Xu-Kun Yang, Hua-Liang Li. IFC Railway: A Semantic and Geometric Modeling Approach for Railways based on IFC. In 16th International Conference on Computing in Civil and Building Engineering (ICCCBE2016), 2016, Japan. (Best Student Presentation Award)

[32] Yu-Shen Liu, Hongchen Deng, Min Liu, Lianjie Gong. VIV: Using visible internal volume to compute junction-aware shape descriptor of 3D articulated models. Neurocomputing, 2016, 215: 32-47.

[33] Ge Gao, Yu-Shen Liu, Meng Wang, Ming Gu, Jun-Hai Yong. A query expansion method for retrieving online BIM resources based on Industry Foundation Classes. Automation in Construction, 2015, 56: 14–25.

[34] Jing Sun, Yu-Shen Liu, Ge Gao, Xiao-Guang Han. IFCCompressor: A content-based compression algorithm for optimizing Industry Foundation Classes files. Automation in Construction, 2015, 50: 1-15.

[35] Jinlong Feng, Yu-Shen Liu, Lianjie Gong. Junction-aware shape descriptor for 3D articulated models using local shape-radius variation. Signal Processing, 2015, 112: 4-16.

[36] Yu-Shen Liu, Heng Li, Haijiang Li, Pieter Pauwels, Jakob Beetz. Recent Advances on Building Information Modeling. The Scientific World Journal, vol. 2015, Article ID 786598, 2 pages, 2015. doi:10.1155/2015/786598. (Editorial)

[37] Ge Gao, Yu-Shen Liu, Meng Wang, Xiao-Guang Han. BIMTag: Semantic annotation of Web BIM product resources based on IFC ontology. In: 21st International Workshop of the European Group for Intelligent Computing in Engineering (EG-ICE 2014), July, 2014 Cardiff, United Kingdom. ISBN: 978-0-9930807-0-8 (EI: 20144900283797). (invitation for extended version submission to Advanced Engineering Informatics)

[38] Ya-Hong Lin, Yu-Shen Liu, Ge Gao, Xiao-Guang Han, Cheng-Yuan Lai, Ming Gu. The IFC-based path planning for 3D indoor spaces. Advanced Engineering Informatics, 2013; 27(2): 189–205. (Highly Cited Research Award)

[39] Dongxing Cao, Shengfeng Qin, Yu-Shen Liu. Advances in Conceptual Design Theories, Methodologies, and Applications. Advances in Mechanical Engineering, 2013; Article ID 207492, page 1-3. doi:10.1155/2013/207492. (Editorial)

[40] Chao Wang, Yu-Shen Liu, Min Liu, Jun-Hai Yong, Jean-Claude Paul. Robust shape normalization of 3D articulated volumetric models. Computer-Aided Design, 2012; 44(12): 1253–1268.

[41] Yu-Shen Liu, Meng Wang, Jean-Claude Paul, Karthik Ramani. 3DMolNavi: A web-based retrieval and navigation tool for flexible molecular shape comparison. BMC Bioinformatics, 2012, 13:95.

[42] Yu-Shen Liu, Karthik Ramani, Min Liu. Computing the inner distances of volumetric models for articulated shape description with a visibility graph. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2538-2544.

[43] Yu-Shen Liu, Qi Li, Guo-Qin Zheng, Karthik Ramani, William Benjamin. Using diffusion distances for flexible molecular shape comparison. BMC Bioinformatics, 2010, 11:480.

[44] Yu-Shen Liu, Jing Yi, Hu Zhang, Guo-Qin Zheng, Jean-Claude Paul. Surface area estimation of digitized 3D objects using quasi-Monte Carlo methods. Pattern Recognition, 2010, 43(11): 3900-3909.

[45] Yu-Shen Liu, Yi Fang, Karthik Ramani. IDSS: deformation invariant signatures for molecular shape comparison. BMC Bioinformatics, 2009, 10:157.

[46] Min Liu, Yu-Shen Liu, Karthik Ramani. Computing global visibility maps for regions on the boundaries of polyhedra using Minkowski sums. Computer-Aided Design, 2009; 41(9): 668-680.

[47] Yi Fang, Yu-Shen Liu, Karthik Ramani. Three dimensional shape comparison of flexible protein using the local-diameter descriptor. BMC Structural Biology, 2009, 9:29.

[48] Yu-Shen Liu, Yi Fang, Karthik Ramani. Using least median of squares for structural superposition of flexible proteins. BMC Bioinformatics, 2009, 10:29.

[49] Yu-Shen Liu, Karthik Ramani. Robust principal axes determination for point-based shapes using least median of squares. Computer-Aided Design, 2009; 41(4): 293-305.

[50] Ming-Cui Du, Yu-Shen Liu. An extension on robust directed projection of points onto point clouds. Computer-Aided Design, 2008; 40(5):537-553.

[51] Yu-Shen Liu, Min Liu, Daisuke Kihara, Karthik Ramani. Salient critical points for meshes. In Proceedings of the 2007 ACM symposium on Solid and physical modeling (SPM’07), 277–282, June 2007, Beijing, China.

[52] Min Liu, Yushen Liu, Karthik Ramani. Anisotropic filtering on normal field and curvature tensor field using optimal estimation theory. In Proceedings of the IEEE International Conference on Shape Modeling and Applications 2007 (SMI’07), 169–178, June 2007, Lyon, France.

[53] Yu-Shen Liu, Jean-Claude Paul, Jun-Hai Yong, Pi-Qiang Yu, Hui Zhang, Jia-Guang Sun, Karthik Ramani. Automatic least-squares projection of points onto point clouds with applications in reverse engineering. Computer-Aided Design, 2006; 38(12): 1251-1263.

[54] Yu-Shen Liu, Jun-Hai Yong, Hui Zhang, Dong-Ming Yan, Jia-Guang Sun. A quasi-Monte Carlo method for computing areas of point-sampled surfaces. Computer-Aided Design, 2006; 38(1): 55-68.

[55] Yu-Shen Liu, Hui Zhang, Jun-Hai Yong, Pi-Qiang Yu, Jia-Guang Sun. Mesh blending. The Visual Computer, 2005; 21(11): 915-927.

[56] Yu-Shen Liu, Jun-Hai Yong, Pi-Qiang Yu, Hui Zhang, Ming-Cui Du, Jia-Guang Sun. Mesh parameterization for an open connected surface without partition. In Proceedings of the Ninth International Conference on Computer Aided Design and Computer Graphics (CAD-CG'05), 306–312, September, 2005, Hong Kong, China. (Best Student Paper Award)

[57] Yu-Shen Liu, Pi-Qiang Yu, Jun-Hai Yong, Hui Zhang, Jia-Guang Sun. Bilateral filter for meshes using new predictor. International Symposium on Computational and Information Sciences (CIS'04), LNCS 3314: 1093–1099, 2004.