袁粒

实验室网站:
职称 助理教授 电话 0755-26032269
办公室 A308 Email yuanli-ece@pku.edu.cn
研究方向 1、计算机视觉;2、深度神经网络架构设计;3、机器学习 实验室网站

​导师与研究领域、方向:

袁粒,博士,十大网赌正规信誉网址助理教授、博士生导师,深圳市海外高层次人才。分别在中国科学技术大学 (2017年)、 新加坡国立大学(2021年)获得本科和博士学位。其研究方向为计算机视觉与神经网络架构设计,相关工作已经发表于多个顶级计算机会议和期刊,包括CVPR/ICCV/ICML/NeurIPS/AAAI/IEEE TPAMI等,担任IEEE IROS 2022副主编(Associate Editor)和多个会议和期刊的(高级)程序委员会委员/审稿人,包括IEEE TPAMI /TNNLS/TMM/Cell Patterns等。袁粒博士的代表性学术工作包括VOLO, T2T-ViT等深度神经网络框架和知识蒸馏相关工作,他在博士期间曾于哈佛大学从事访问研究工作。

欢迎优秀的本科生和硕士生保送和报考十大网赌正规信誉网址的硕士和博士研究生,课题组博士后职位也已开放,更多招生、实习以及科研最新信息请查看个人主页:https://yuanli2333.github.io/

代表性学术工作

完整列表请访问 Google Scholar(https://scholar.google.com/citations?user=-5juAR0AAAAJ&hl=en)

  1. Li Yuan, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Zihang Jiang, Francis EH Tay, Jiashi Feng, Shuicheng Yan. Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet. International Conference on Computer Vision (ICCV), 2021.

  2. Li Yuan,Francis EH Tay, Guilin Li, Tao Wang, Jiashi Feng. Revisiting Knowledge Distillation via Label Smoothing Regularization. IEEE Computer Vision and Pattern Recognition (CVPR), 2020 (Oral).

  3. Li Yuan, Tao Wang, Xiaopeng Zhang, Francis EH Tay, Zequn Jie, Wei Liu, Jiashi Feng. Central Similarity Quantization for Efficient Image and Video Retrieval. IEEE Computer Vision and Pattern Recognition (CVPR), 2020.

  4. Li Yuan, Yichen Zhou, Shuning Chang, Ziyuan Huang, Yupeng Chen, Xuecheng Nie, Tao Wang, Jiashi Feng, Shuicheng Yan. Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes. ACM International Conference on Multimedia (ACM MM), 2020.

  5. Li Yuan, Shuning Chang, Ziyuan Huang, Yichen Zhou, Yupeng Chen, Xuecheng Nie, Francis Tay, Jiashi Feng, Shuicheng Yan. A Simple Baseline for Pose Tracking in Videos of Crowed Scenes. ACM International Conference on Multimedia (ACM MM), 2020.

  6. Li Yuan, Francis Eng Hock Tay, Ping Li, Li Zhou, Jiashi Feng . Cycle-SUM: Cycle-Consistent Adversarial LSTM Networks for Unsupervised Video Summarization. AAAI Conference on Artificial Intelligence (AAAI), 2019.

  7. Li Yuan, Francis Eng Hock Tay, Ping Li, Jiashi Feng. Unsupervised Video Summarization with Cycle-Consistent Adversarial LSTM Networks. IEEE Transactions on Multimedia (IEEE TMM), 2019.

  8. Tao Wang,Li Yuan*, Yunpeng Chen, Jiashi Feng, Shuicheng Yan. PnP-DETR: Towards Efficient Visual Analysis with Transformers. International Conference on Computer Vision (ICCV), 2021.

  9. Yujun Shi,Li Yuan*, Yunpeng Chen, Jiashi Feng. Continual Learning via Bit-Level Information Preservin. IEEE Computer Vision and Pattern Recognition (CVPR), 2021.

  10. Li Yuan, Qibin Hou, Zihang Jiang, Jiashi Feng, Shuicheng Yan. VOLO: Vision Outlooker for Visual Recognition. arxiv preprint arXiv:2106.13112 (2021).

  11. Qibin Hou, Zihang Jiang,Li Yuan, Ming-Ming Cheng, Shuicheng Yan, Jiashi Feng. Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.

  12. Ziyu Wang, Wenhao Jiang, Yiming Zhu,Li Yuan, Yibing Song, Wei Liu. DynaMixer: A Vision MLP Architecture with Dynamic Mixing. International Conference on Machine Learning (ICML), 2022.

  13. Zeke Xie,Li Yuan, Zhanxing Zhu, Masashi Sugiyama. Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization. International Conference on Machine Learning (ICML), 2021 (Spotlight).

  14. Zihang Jiang, Qibin Hou,Li Yuan, Daquan Zhou, Yujun Shi, Xiaojie Jin, Anran Wang, Jiashi Feng. All Tokens Matter: Token Labeling for Training Better Vision Transformers. Conference on Neural Information Processing Systems (NeurIPS), 2021.

  15. Tao Wang,Li Yuan, Xiaopeng Zhang, Jiashi Feng. Distilling Object Detectors With Fine-Grained Feature Imitation. IEEE Computer Vision and Pattern Recognition (CVPR), 2019.

  16. Tao Wang, Xiaopeng Zhang,Li Yuan, Jiashi Feng. Few-shot adaptive faster r-cnn. IEEE Computer Vision and Pattern Recognition (CVPR), 2019.

发明专利:

  1. IMAGE PROCESSING METHOD AND APPARATUS, AND STORAGE MEDIUM, 2020-05-08, 美国, US20210382937A1.

  2. VIDEO-BASED POSE ESTIMATION METHOD AND APPARATUS, MEDIUM, AND ELECTRONIC DEVICE, 2020-10-01, 新加坡, SG10202009760XA.

  3. VIDEO-BASED HUMAN ACTION RECOGNITION METHOD AND APPARATUS, A MEDIUM AND AN ELECTRONIC DEVICE, 2020-10-01, 新加坡, SG10202009757XA.

对计划招收研究生的基本要求:

  1. 专业范围:计算机科学技术、数学、电子信息技术、自动化、其他相关学科,跨专业员工需成绩非常优异且自我驱动力强;

  2. 外语能力:英语六级,或托福90+/雅思6.5+;

  3. 研究/开发能力:熟练的程序设计能力,具有一定的探索能力和创新精神;

  4. 其他要求:自我驱动力强,对做科研工作有热情和兴趣,能专注于科研。