Yandong Li  (李延东)

Google
lyndon.leeseu@outlook.com
Google Scholar / Github / LinkedIn
CV

Education

  • 2017.08 - 2021.05
    Ph.D. in Computer Science, University of Central Florida (UCF), Orlando, USA
    advised by Prof. Liqiang Wang at UCF and Dr. Boqing Gong (remote) at Google Research.
  • 2012.09 - 2016.07
    Bachelor in Computer Software Engineering, Southeast University (SEU), Nanjing, China
    GPA: 3.70/4.8  Rank: 3/123
    Awarded the Outstanding Undergraduate Student and National Scholarship

Experiences

I am an engineer/researcher at Google. My primary research areas include machine learning and computer vision. My recent works mainly investigate object detection, the distributions of adversarial examples for deep neural networks, multi-task learning, visual question answering and segmentation, action recognition, and video summarization.
  • Google Research   Seattle, USA  2020.01 - 2020.11
    Self-supervised learning
  • Google Cloud&&AI   Sunnyvale, USA  2019.09 - 2019-12
    Object Detection: Improving object detection with selective self-supervised self-training
  • Microsoft Cloud&&AI   Seattle, USA  2019.5 - 2019-8
    Generative model: High-resolution image generation
  • IBM Thomas J. Watson Research Center   New York, USA  2018.5 - 2018-8
    Multi-task learning
  • Baidu Institute of Deep Learning (IDL)   Beijing, China  2017.2 - 2017-8
    Action Recognition: Our team won the 3rd place in Youtube-8M competition and 1st place in ActivityNet challenge which are prestigious competitions for action recognition
  • Microsoft Reseach Asia (MSRA)   Beijing, China  2015.8 - 2016-7
    Video Thumbnail Tools: I have taken part in the development of Microsoft Cognitive Service.
    Hashing: Deep cross-modal hashing won the outstanding dissertation for a Bachelor’s degree.

Publications

  • [ECCV 2020]  Improving Object Detection with Selective Self-supervised Self-training
    Yandong Li, Di Huang, Danfeng Qin, Liqiang Wang, Boqing Gong

  • [CVPR 2020 Oral]  Neural Networks Are More Data-Efficient Teachers Than Human Raters: Active Mixup for Knowledge Distillation from a Blackbox Teacher Model
    Yandong Li*, Dongdong Wang*, Liqiang Wang, Boqing Gong (* Equal Contribution)

  • [CVPR 2020]  BachGAN: High-Resolution Image Synthesis from Salient Object Layout
    Yandong Li, Yu Cheng, Zhe Gan, Licheng Yu, Liqiang Wang, Jingjing Liu

  • [WSDM 2020]  Robust Graph Neural Network against Poisoning Attacks via Transfer Learning
    Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, Suhang Wang

  • [AAAI 2020]  AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning
    Yunhui Guo, Yandong Li, Liqiang Wang, Tajana Rosing

  • [ICML 2019]  NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-BoxAttack on Deep Neural Networks
    Yandong Li*, Lijun Li*, Liqiang Wang, Tong Zhang, Boqing Gong (* Equal Contribution)

  • [AAAI 2019]  Depthwise Convolution is All You Need for Learning Multiple Visual Domains
    Yandong Li*, Yunhui Guo*, Rogerio Feris, Liqiang Wang, Tajana Rosing (* Equal Contribution)

  • [AAAI 2019]  Multimodal Keyless Attention Fusion for Video Classification
    Xiang Long*, Chuang Gan, Gerard De melo, Xiao Liu, Yandong Li, Fu Li, Shilei Wen

  • [ECCV 2018]  How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization
    Yandong Li, Liqiang Wang, Tianbao Yang, Boqing Gong.

  • [CVPR 2017 WORKSHOP]  Revisiting the Efectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
    Yunlong Bian, Chuang Gan , Xiao Liu, Fu Li, Xiang Long, Yandong Li, Heng Qi, Jie Zhou, Shilei Wen, Yuanqing Lin
    Our team won the 1st place in the ActivityNet Kinetics Challenge. Our best single model achieves 77.7% in term of top-1 accuracy and 93.2% in term of top-5 accuracy on the validation set

  • [CVPR 2017 WORKSHOP]  Temporal Modeling Approaches for Large-scale Youtube-8M Video Understanding
    Fu Li, Chuang Gan, Xiao Liu, Yunlong Bian, Xiang Long, Yandong Li, Zhichao Li, Jie Zhou, Shilei Wen
    Our team won the 3rd place in the Google Cloud and YouTube-8M Video Understanding Challenge. Our best single model achieves 82.75% in term of GAP@20 on the Kaggle Public test set

  • [ICCV 2017]  VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation
    Chuang Gan, Yandong Li, Haoxiang Li, Chen Sun, Boqing Gong



Awards


Service

  • PC member: ICML 2020, CVPR 2020, ECCV 2020, ICLR 2020, Bigdata 2019, MM 2019, WACV 2019, Bigdata 2018, WACV 2018,
  • Reviewer: NeurIPS 2019, CVPR 2019, ICCV 2019, IJCAI 2019, IJCAI 2018

Proudly powered by Bootstrap