| CARVIEW |
A research scientist @ Waymo
About Me
Hi! I am a research scientist at Waymo. I received my Ph.D. degree from Computer Science department at Johns Hopkins University, advised by Bloomberg Distinguished Professor Dr. Alan Yuille.
I obtained B.S. in Computer Science at Fudan University in 2018. I also spent time at Google Research, Waymo, ByteDance, NTU, and TuSimple.
My research interests mainly lie in computer vision, especially in autonomous driving, robust representation learning, multi-modality fusion, automated machine learning, and medical machine intelligence.
News
NEW [02/27/2022] One paper is accepted by CVPR 2023.
[10/10/2022] One paper is accepted by WACV 2023.
[09/17/2022] One paper is accepted by ACM CCS 2022.
[07/03/2022] One paper is accepted by ECCV 2022.
[06/06/2022] Begin my full-time work journey!
[05/05/2022] I finally passed my PhD thesis defense!
[04/12/2022] I will join Waymo as a research scientist.
[03/02/2022] Three papers are accepted by CVPR 2022.
[01/31/2022] One paper is accepted by ICRA 2022.
[01/20/2022] R4D is accepted by ICLR 2022.
[01/20/2022] Fast AdvProp is accepted by ICLR 2022.
Selected Publications
MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences
Yingwei Li*, Charles R. Qi*, Yin Zhou, Chenxi Liu, Dragomir Anguelov
CVPR, 2023
[Paper] [Supplementary] [Bibtex]@InProceedings{Li_2023_CVPR, author = {Li, Yingwei and Qi, Charles R. and Zhou, Yin and Liu, Chenxi and Anguelov, Dragomir}, title = {MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {9329-9339}} |
Context Enhanced Stereo Transformer
Weiyu Guo, Zhaoshuo Li, Yongkui Yang, Zheng Wang, Russ Taylor, Mathias Unberath, Alan Yuille, Yingwei Li
ECCV, 2022
[Paper] [Code] [Bibtex]@inproceedings{guo2022context,title={Context Enhanced Stereo Transformer},author={Guo, Weiyu and Li, Zhaoshuo and Yang, Yongkui and Wang, Zheng and Taylor, Russ and Unberath, Mathias and Yuille, Alan and Li, Yingwei},booktitle={ECCV},year={2022}} |
DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection
Yingwei Li*, Adams Yu*, Tianjian Meng, Ben Caine, Jiquan Ngiam, Daiyi Peng, Junyang Shen, Bo Wu, Yifeng Lu, Denny Zhou, Quoc Le, Alan Yuille, Mingxing Tan
CVPR, 2022
[Paper] [Code] [Website] [Bibtex]@article{li2022deepfusion,title={DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection},author={Li, Yingwei and Yu, Adams Wei and Meng, Tianjian and Caine, Ben and Ngiam, Jiquan and Peng, Daiyi and Shen, Junyang and Wu, Bo and Lu, Yifeng and Zhou, Denny and others},journal={arXiv preprint arXiv:2203.08195},year={2022}} |
Learning from Temporal Gradient for Semi-supervised Action Recognition
Junfei Xiao, Longlong Jing, Lin Zhang, Ju He, Qi She, Zongwei Zhou, Alan Yuille, Yingwei Li
CVPR, 2022
[Paper] [Code] [Bibtex]@article{xiao2021learning,title={Learning from Temporal Gradient for Semi-supervised Action Recognition},author={Xiao, Junfei and Jing, Longlong and Zhang, Lin and He, Ju and She, Qi and Zhou, Zongwei and Yuille, Alan and Li, Yingwei},journal={arXiv preprint arXiv:2111.13241},year={2021}} |
R4D: Utilizing Reference Objects for Long-Range Distance Estimation
Yingwei Li, Tiffany Chen*, Maya Kabkab*, Ruichi Yu, Longlong Jing, Yurong You, Hang Zhao
ICLR, 2022
[Paper] [Supplementary] [Bibtex]@inproceedings{li2021r4d,title={R4D: Utilizing Reference Objects for Long-Range Distance Estimation},author={Li, Yingwei and Chen, Tiffany and Kabkab, Maya and Yu, Ruichi and Jing, Longlong and You, Yurong and Zhao, Hang},booktitle={International Conference on Learning Representations},year={2021}} |
Shape-Texture Debiased Neural Network Training
Yingwei Li, Qihang Yu, Mingxing Tan, Jieru Mei, Peng Tang, Wei Shen, Alan Yuille, Cihang Xie
ICLR, 2021
[Paper] [Code] [Website] [Video] [Bibtex]@article{li2020shape,title={Shape-texture debiased neural network training},author={Li, Yingwei and Yu, Qihang and Tan, Mingxing and Mei, Jieru and Tang, Peng and Shen, Wei and Yuille, Alan and Xie, Cihang},journal={arXiv preprint arXiv:2010.05981},year={2020}} |
Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
Yingwei Li, Song Bai, Cihang Xie, Zhenyu Liao, Xiaohui Shen, Alan Yuille
ECCV, 2020
[Paper] [Code] [Bibtex]@inproceedings{li2020regional,title={Regional homogeneity: Towards learning transferable universal adversarial perturbations against defenses},author={Li, Yingwei and Bai, Song and Xie, Cihang and Liao, Zhenyu and Shen, Xiaohui and Yuille, Alan},booktitle={European Conference on Computer Vision},pages={795--813},year={2020},organization={Springer}} |
Neural Architecture Search for Lightweight Non-Local Networks
Yingwei Li, Xiaojie Jin, Jieru Mei, Xiaochen Lian, Linjie Yang, Cihang Xie, Qihang Yu, Yuyin Zhou, Song Bai, Alan Yuille
CVPR, 2020
[Paper] [Code] [Bibtex]@inproceedings{li2020neural,title={Neural architecture search for lightweight non-local networks},author={Li, Yingwei and Jin, Xiaojie and Mei, Jieru and Lian, Xiaochen and Yang, Linjie and Xie, Cihang and Yu, Qihang and Zhou, Yuyin and Bai, Song and Yuille, Alan L},booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},pages={10297--10306},year={2020}} |
Learning Transferable Adversarial Examples via Ghost Networks
Yingwei Li, Song Bai, Yuyin Zhou, Cihang Xie, Zhishuai Zhang, Alan Yuille
AAAI, 2020CVPR Workshop (Oral), 2019
[Paper] [Code] [Bibtex]@inproceedings{li2020learning,title={Learning Transferable Adversarial Examples via Ghost Networks},author={Li, Yingwei and Bai, Song and Zhou, Yuyin and Xie, Cihang and Zhang, Zhishuai and Yuille, Alan},booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},volume={34},year={2020}} |
Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-Fine Framework and Its Adversarial Examples
Yingwei Li*, Zhuotun Zhu* Yuyin Zhou, Yingda Xia, Wei Shen, Elliot K Fishman, Alan Yuille
Book Chapter: Deep Learning and CNN for Medical Image Computing , 2019
[Paper] [Bibtex]@Inbook{Li2019,author='Li, Yingwei and Zhu, Zhuotun and Zhou, Yuyin and Xia, Yingda and Shen, Wei and Fishman, Elliot K. and Yuille, Alan L.',title='Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-Fine Framework and Its Adversarial Examples',bookTitle='Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics',year='2019',publisher='Springer International Publishing',address='Cham',pages='69--91',isbn='978-3-030-13969-8',doi='10.1007/978-3-030-13969-8_4',url='https://doi.org/10.1007/978-3-030-13969-8_4'} |
Affiliations
2018 – 2022
2017
2014 – 2018
2020, 2022–Now
2021–2022
2019
2016
Academic Service
Co-organizer
Adversarial Robustness in the Real World @ ECCV 2022
The Art of Robustness: Devil and Angel in Adversarial Machine Learning @ CVPR 2022
Practical Deep Learning in the Wild @ AAAI 2022
Adversarial Robustness in the Real World @ ICCV 2021
Adversarial Learning for Multimedia @ ACMMM 2021
Adversarial Robustness in the Real World @ ECCV 2020
Reviewer
Journal: IEEE TIP, IEEE TDSC, Neurocomputing, Pattern Recognition.
Conference: AmlCV@CVPR2020, SRML@ICML2021, SecMl@ICLR2021, RseMl@AAAI2021 AAAI 2021, IJCAI 2021, CVPR 2021, ICCV 2021, NeurIPS 2021, AAAI 2022, ICLR 2022, CVPR 2022, ICML 2022.