D2
Computer Vision and Machine Learning

Shaoshuai Shi (Postdoc)

Dr. Shaoshuai Shi

Address
Max-Planck-Institut für Informatik
Saarland Informatics Campus
Campus E1 4
66123 Saarbrücken
Location
E1 4 - 613
Phone
+49 681 9325 2140
Fax
+49 681 9325 2099

Personal Information

Publications

Shi, S., Jiang, L., Dai, D., & Schiele, B. (n.d.). Motion Transformer with Global Intention Localization and Local Movement Refinement. In Advances in Neural Information Processing Systems 35 (NeurIPS 2022). New Orleans, LO, USA.
(Accepted/in press)
Export
BibTeX
@inproceedings{Shi_Neurips22, TITLE = {Motion Transformer with Global Intention Localization and Local Movement Refinement}, AUTHOR = {Shi, Shaoshuai and Jiang, Li and Dai, Dengxin and Schiele, Bernt}, LANGUAGE = {eng}, YEAR = {2022}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)}, ADDRESS = {New Orleans, LO, USA}, }
Endnote
%0 Conference Proceedings %A Shi, Shaoshuai %A Jiang, Li %A Dai, Dengxin %A Schiele, Bernt %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T Motion Transformer with Global Intention Localization and Local Movement Refinement : %G eng %U http://hdl.handle.net/21.11116/0000-000C-1853-C %D 2022 %B 36th Conference on Neural Information Processing Systems %Z date of event: 2022-11-28 - 2022-12-09 %C New Orleans, LO, USA %B Advances in Neural Information Processing Systems 35 %U https://openreview.net/forum?id=9t-j3xDm7_Q
Shi, S., Jiang, L., Dai, D., & Schiele, B. (2022). MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction. Retrieved from https://arxiv.org/abs/2209.10033
(arXiv: 2209.10033)
Abstract
In this report, we present the 1st place solution for motion prediction track<br>in 2022 Waymo Open Dataset Challenges. We propose a novel Motion Transformer<br>framework for multimodal motion prediction, which introduces a small set of<br>novel motion query pairs for generating better multimodal future trajectories<br>by jointly performing the intention localization and iterative motion<br>refinement. A simple model ensemble strategy with non-maximum-suppression is<br>adopted to further boost the final performance. Our approach achieves the 1st<br>place on the motion prediction leaderboard of 2022 Waymo Open Dataset<br>Challenges, outperforming other methods with remarkable margins. Code will be<br>available at https://github.com/sshaoshuai/MTR.<br>
Export
BibTeX
@online{Shi2209.10033, TITLE = {{MTR}-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction}, AUTHOR = {Shi, Shaoshuai and Jiang, Li and Dai, Dengxin and Schiele, Bernt}, LANGUAGE = {eng}, URL = {https://arxiv.org/abs/2209.10033}, EPRINT = {2209.10033}, EPRINTTYPE = {arXiv}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, ABSTRACT = {In this report, we present the 1st place solution for motion prediction track<br>in 2022 Waymo Open Dataset Challenges. We propose a novel Motion Transformer<br>framework for multimodal motion prediction, which introduces a small set of<br>novel motion query pairs for generating better multimodal future trajectories<br>by jointly performing the intention localization and iterative motion<br>refinement. A simple model ensemble strategy with non-maximum-suppression is<br>adopted to further boost the final performance. Our approach achieves the 1st<br>place on the motion prediction leaderboard of 2022 Waymo Open Dataset<br>Challenges, outperforming other methods with remarkable margins. Code will be<br>available at https://github.com/sshaoshuai/MTR.<br>}, }
Endnote
%0 Report %A Shi, Shaoshuai %A Jiang, Li %A Dai, Dengxin %A Schiele, Bernt %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society %T MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction : %G eng %U http://hdl.handle.net/21.11116/0000-000C-184C-5 %U https://arxiv.org/abs/2209.10033 %D 2022 %X In this report, we present the 1st place solution for motion prediction track<br>in 2022 Waymo Open Dataset Challenges. We propose a novel Motion Transformer<br>framework for multimodal motion prediction, which introduces a small set of<br>novel motion query pairs for generating better multimodal future trajectories<br>by jointly performing the intention localization and iterative motion<br>refinement. A simple model ensemble strategy with non-maximum-suppression is<br>adopted to further boost the final performance. Our approach achieves the 1st<br>place on the motion prediction leaderboard of 2022 Waymo Open Dataset<br>Challenges, outperforming other methods with remarkable margins. Code will be<br>available at https://github.com/sshaoshuai/MTR.<br> %K Computer Science, Computer Vision and Pattern Recognition, cs.CV
Yang, J., Shi, S., Ding, R., Wang, Z., & Qi, X. (n.d.). Towards Efficient 3D Object Detection with Knowledge Distillation. In Advances in Neural Information Processing Systems 35 (NeurIPS 2022). New Orleans, LO, USA.
(Accepted/in press)
Export
BibTeX
@inproceedings{Shi_Neurips22B, TITLE = {Towards Efficient {3D} Object Detection with Knowledge Distillation}, AUTHOR = {Yang, Jihan and Shi, Shaoshuai and Ding, Runyu and Wang, Zhe and Qi, Xiaojuan}, LANGUAGE = {eng}, YEAR = {2022}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)}, ADDRESS = {New Orleans, LO, USA}, }
Endnote
%0 Conference Proceedings %A Yang, Jihan %A Shi, Shaoshuai %A Ding, Runyu %A Wang, Zhe %A Qi, Xiaojuan %+ External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations %T Towards Efficient 3D Object Detection with Knowledge Distillation : %G eng %U http://hdl.handle.net/21.11116/0000-000C-72E9-D %D 2022 %B 36th Conference on Neural Information Processing Systems %Z date of event: 2022-11-28 - 2022-12-09 %C New Orleans, LO, USA %B Advances in Neural Information Processing Systems 35 %U https://openreview.net/forum?id=1tnVNogPUz9
Shi, S., Jiang, L., Deng, J., Wang, Z., Guo, C., Shi, J., … Li, H. (2022). PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection. International Journal of Computer Vision. doi:10.1007/s11263-022-01710-9
Export
BibTeX
@article{Shi2022x, TITLE = {{PV-RCNN}++: {P}oint-Voxel Feature Set Abstraction With Local Vector Representation for {3D} Object Detection}, AUTHOR = {Shi, Shaoshuai and Jiang, Li and Deng, Jiajun and Wang, Zhe and Guo, Chaoxu and Shi, Jianping and Wang, Xiaogang and Li, Hongsheng}, LANGUAGE = {eng}, ISSN = {0920-5691}, URL = {https://rdcu.be/c14JE}, DOI = {10.1007/s11263-022-01710-9}, PUBLISHER = {Springer}, ADDRESS = {New York, NY}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, JOURNAL = {International Journal of Computer Vision}, }
Endnote
%0 Journal Article %A Shi, Shaoshuai %A Jiang, Li %A Deng, Jiajun %A Wang, Zhe %A Guo, Chaoxu %A Shi, Jianping %A Wang, Xiaogang %A Li, Hongsheng %+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations External Organizations External Organizations %T PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection : %G eng %U http://hdl.handle.net/21.11116/0000-000C-11CC-B %R 10.1007/s11263-022-01710-9 %U https://rdcu.be/c14JE %7 2022 %D 2022 %J International Journal of Computer Vision %O Int. J. Comput. Vis. %I Springer %C New York, NY %@ false
Wang, H., Ding, L., Dong, S., Shi, S., Li, A., Li, J., … Wang, L. (n.d.). CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds. In Advances in Neural Information Processing Systems 35 (NeurIPS 2022). New Orleans, LO, USA.
(Accepted/in press)
Export
BibTeX
@inproceedings{Shi_Neurips22C, TITLE = {{CAGroup3D}: {C}lass-Aware Grouping for {3D} Object Detection on Point Clouds}, AUTHOR = {Wang, Haiyang and Ding, Lihe and Dong, Shaocong and Shi, Shaoshuai and Li, Aoxue and Li, Jianan and Li, Zhenguo and Wang, Liwei}, LANGUAGE = {eng}, YEAR = {2022}, PUBLREMARK = {Accepted}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {Advances in Neural Information Processing Systems 35 (NeurIPS 2022)}, ADDRESS = {New Orleans, LO, USA}, }
Endnote
%0 Conference Proceedings %A Wang, Haiyang %A Ding, Lihe %A Dong, Shaocong %A Shi, Shaoshuai %A Li, Aoxue %A Li, Jianan %A Li, Zhenguo %A Wang, Liwei %+ External Organizations External Organizations External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations %T CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds : %G eng %U http://hdl.handle.net/21.11116/0000-000C-72EC-A %D 2022 %B 36th Conference on Neural Information Processing Systems %Z date of event: 2022-11-28 - 2022-12-09 %C New Orleans, LO, USA %B Advances in Neural Information Processing Systems 35 %U https://openreview.net/forum?id=nLKkHwYP4Au
Chen, X., Shi, S., Zhu, B., Cheung, K. C., Xu, H., & Li, H. (2022). MPPNet: Multi-frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection. In Computer Vision -- ECCV 2022. Tel Aviv, Israel: Springer. doi:10.1007/978-3-031-20074-8_39
Export
BibTeX
@inproceedings{Chen_ECCV2022x, TITLE = {{MPPNet}: {M}ulti-frame Feature Intertwining with Proxy Points for {3D} Temporal Object Detection}, AUTHOR = {Chen, Xuesong and Shi, Shaoshuai and Zhu, Benjin and Cheung, Ka Chun and Xu, Hang and Li, Hongsheng}, LANGUAGE = {eng}, ISBN = {978-3-031-20073-1}, DOI = {10.1007/978-3-031-20074-8_39}, PUBLISHER = {Springer}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, DATE = {2022}, BOOKTITLE = {Computer Vision -- ECCV 2022}, EDITOR = {Avidan, Shai and Brostow, Gabriel and Ciss{\'e}, Moustapha and Farinella, Giovanni Maria and Hassner, Tal}, PAGES = {680--697}, SERIES = {Lecture Notes in Computer Science}, VOLUME = {13668}, ADDRESS = {Tel Aviv, Israel}, }
Endnote
%0 Conference Proceedings %A Chen, Xuesong %A Shi, Shaoshuai %A Zhu, Benjin %A Cheung, Ka Chun %A Xu, Hang %A Li, Hongsheng %+ External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations %T MPPNet: Multi-frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection : %G eng %U http://hdl.handle.net/21.11116/0000-000C-72F6-E %R 10.1007/978-3-031-20074-8_39 %D 2022 %B 17th European Conference on Computer Vision %Z date of event: 2022-10-23 - 2022-10-27 %C Tel Aviv, Israel %B Computer Vision -- ECCV 2022 %E Avidan, Shai; Brostow, Gabriel; Ciss&#233;, Moustapha; Farinella, Giovanni Maria; Hassner, Tal %P 680 - 697 %I Springer %@ 978-3-031-20073-1 %B Lecture Notes in Computer Science %N 13668 %U https://rdcu.be/c33Eb
Wang, H., Shi, S., Yang, Z., Fang, R., Qian, Q., Li, H., … Wang, L. (2022). RBGNet: Ray-based Grouping for 3D Object Detection. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022). New Orleans, LA, USA: IEEE. doi:10.1109/CVPR52688.2022.00118
Export
BibTeX
@inproceedings{Wang_CVPR22c, TITLE = {{RBGNet}: {R}ay-based Grouping for {3D} Object Detection}, AUTHOR = {Wang, Haiyang and Shi, Shaoshuai and Yang, Ze and Fang, Rongyao and Qian, Qi and Li, Hongsheng and Schiele, Bernt and Wang, Liwei}, LANGUAGE = {eng}, ISBN = {978-1-6654-6946-3}, DOI = {10.1109/CVPR52688.2022.00118}, PUBLISHER = {IEEE}, YEAR = {2022}, MARGINALMARK = {$\bullet$}, BOOKTITLE = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2022)}, PAGES = {1100--1109}, ADDRESS = {New Orleans, LA, USA}, }
Endnote
%0 Conference Proceedings %A Wang, Haiyang %A Shi, Shaoshuai %A Yang, Ze %A Fang, Rongyao %A Qian, Qi %A Li, Hongsheng %A Schiele, Bernt %A Wang, Liwei %+ External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations External Organizations External Organizations External Organizations Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society External Organizations %T RBGNet: Ray-based Grouping for 3D Object Detection : %G eng %U http://hdl.handle.net/21.11116/0000-000C-1833-0 %R 10.1109/CVPR52688.2022.00118 %D 2022 %B 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition %Z date of event: 2022-06-19 - 2022-06-24 %C New Orleans, LA, USA %B IEEE/CVF Conference on Computer Vision and Pattern Recognition %P 1100 - 1109 %I IEEE %@ 978-1-6654-6946-3