Yin Cui

Research Scientist at Google


Hi, I am Yin Cui (崔崟 in Chinese, pronounced as /yin tsui/), a Research Scientist at Google. Before joining Google, I received my Ph.D. in Computer Science from Cornell University and Cornell Tech in 2019, advised by Professor Serge Belongie. My research interests are Computer Vision and Machine Learning.



  • Rui Qian*, Tianjian Meng*, Boqing Gong, Ming-Hsuan Yang, Huisheng Wang, Serge Belongie, Yin Cui. Spatiotemporal Contrastive Video Representation Learning. arXiv:2008.03800 [arXiv]

  • Barret Zoph*, Golnaz Ghiasi*, Tsung-Yi Lin*, Yin Cui, Hanxiao Liu, Ekin D. Cubuk, Quoc V. Le. Rethinking Pre-training and Self-training. NeurIPS 2020 (Oral) [arXiv] [Code]

  • Menglin Jia*, Mengyun Shi*, Mikhail Sirotenko*, Yin Cui*, Claire Cardie, Bharath Hariharan, Hartwig Adam, Serge Belongie. Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset. ECCV 2020 (Oral) [Website] [arXiv] [Code] [Kaggle Challenge]

  • Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Yin Cui, Mingxing Tan, Quoc V. Le, Xiaodan Song. Efficient Scale-Permuted Backbone with Learned Resource Distribution. ECCV 2020 [arXiv]

  • Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Golnaz Ghiasi, Mingxing Tan, Yin Cui, Quoc V. Le, Xiaodan Song. SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization. CVPR 2020 [arXiv] [Code] [Google AI Blog]

  • Xuhong Li, Yves Grandvalet, Franck Davoine, Jingchun Cheng, Yin Cui, Hang Zhang, Serge Belongie, Yi-Hsuan Tsai, Ming-Hsuan Yang. Transfer learning in computer vision tasks: Remember where you come from. Image and Vision Computing 2020 [Link]


  • Yin Cui. Learning from Fine-Grained and Long-Tailed Visual Data. Cornell University Theses and Dissertations [Link]

  • Yin Cui*, Zeqi Gu*, Dhruv Mahajan, Laurens van der Maaten, Serge Belongie, Ser-Nam Lim. Measuring Dataset Granularity. arXiv:1912.10154 [arXiv]

  • Sheng Guo, Weilin Huang, Xiao Zhang, Prasanna Srikhanta, Yin Cui, Yuan Li, Hartwig Adam, Matthew R Scott, Serge Belongie. The iMaterialist Fashion Attribute Dataset. ICCV Workshop on Computer Vision for Fashion, Art, and Design 2019 (Best Paper Award) [arXiv] [Code]

  • Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, Serge Belongie. Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019 [arXiv] [Code] [Poster]


  • Longqi Yang, Yin Cui, Yuan Xuan, Chenyang Wang, Serge Belongie, Deborah Estrin. Unbiased Offline Recommender Evaluation for Missing-Not-At-Random Implicit Feedback. ACM Conference on Recommender Systems (RecSys) 2018 [Link] [Code] [Slides]

  • Guandao Yang, Yin Cui, Serge Belongie, Bharath Hariharan. Learning Single-View 3D Reconstruction with Limited Pose Supervision. ECCV 2018 [Link] [Code] [Poster]

  • Yin Cui, Yang Song, Chen Sun, Andrew Howard, Serge Belongie. Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning. CVPR 2018 [arXiv] [Data] [Code] [Poster] [Tensorflow Hub]

  • Yin Cui, Guandao Yang, Andreas Veit, Xun Huang, Serge Belongie. Learning to Evaluate Image Captioning. CVPR 2018 [arXiv] [Code] [Poster]

  • Grant Van Horn, Oisin Mac Aodha, Yang Song, Yin Cui, Chen Sun, Alex Shepard, Hartwig Adam, Pietro Perona, Serge Belongie. The iNaturalist Species Classification and Detection Dataset. CVPR 2018 (Spotlight) [arXiv] [Data] [Tensorflow Object Detection API] [Google AI Blog] [TechCrunch]


  • Yin Cui, Feng Zhou, Jiang Wang, Xiao Liu, Yuanqing Lin, Serge Belongie. Kernel Pooling for Convolutional Neural Networks. CVPR 2017 [Link] [Poster]

  • Cheng-Kang Hsieh, Longqi Yang, Yin Cui, Tsung-Yi Lin, Serge Belongie, Deborah Estrin. Collaborative Metric Learning. International Conference on World Wide Web (WWW) 2017 [Link] [Code] [Slides]


  • Yin Cui, Feng Zhou, Yuanqing Lin, Serge Belongie. Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop. CVPR 2016 [Link] [arXiv] [Poster]


  • Longqi Yang, Yin Cui, Fan Zhang, John P Pollak, Serge Belongie, Deborah Estrin. PlateClick: Bootstrapping Food Preferences Through an Adaptive Visual Interface. ACM International on Conference on Information and Knowledge Management (CIKM) 2015 [Link] [Data] [Slides]

  • Tsung-Yi Lin, Yin Cui, Serge Belongie, James Hays. Learning Deep Representations for Ground-to-Aerial Geolocalization. CVPR 2015 (Oral) [Link] [Data] [Extended Abstract] [Poster]


  • Tao Chen, Felix X Yu, Jiawei Chen, Yin Cui, Yan-Ying Chen, Shih-Fu Chang. Object-based visual sentiment concept analysis and application. ACM international conference on Multimedia (MM) 2014 [Link]

  • Yin Cui, Dong Liu, Jiawei Chen, Shih-Fu Chang. Building a large concept bank for representing events in video. arXiv:1403.7591 [arXiv]

  • Jiawei Chen*, Yin Cui*, Guangnan Ye, Dong Liu, Shih-Fu Chang (*equal contribution). Event-driven semantic concept discovery by exploiting weakly tagged internet images. International Conference on Multimedia Retrieval (ICMR) 2014 [Link] [Slides]

  • Yin Cui, Yongzhou Xiang, Kun Rong, Rogerio Feris, Liangliang Cao. A spatial-color layout feature for content-based galaxy image retrieval. Winter Conference on Applications of Computer Vision (WACV) 2014 [Link] [Poster]


Professional Activities

  • Organizing Committee of ImageNet and COCO Visual Recognition Workshop at ICCV 2015, ECCV 2016
  • Organizing Committee of Joint Workshop of the COCO and Places Challenges at ICCV 2017
  • Organizing Committee of Joint COCO and Mapilary Recognition Challenge Workshop at ECCV 2018, ICCV 2019
  • Organizing Committee of Joint COCO and LVIS Recognition Challenge Workshop at ECCV 2020
  • Organizing Committee of Fine-Grained Visual Categorization Workshop at CVPR 2017, CVPR 2018
  • Organizing Committee of Large-scale Scene Understanding Workshop (COCO Captioning Challenge) at CVPR 2015
  • Member of Common Visual Data Foundation (CVDF), 2016 - Present
  • Reviewer for CVPR, ICCV, ECCV, NeurIPS and ICML

Selected Honors

  • McMullen Fellowship (Sep 2014)
  • Edwin Howard Armstrong Memorial Award (May 2014)
  • Wei Family Private Foundation Special Scholarship (Oct 2013)
  • National Scholarship (Oct 2010)