Challenge of Recognizing One Million Celebrities in the Real World

Learn More ...


We provide training and benchmark testing dataset for the following task: recognizing one million celebrities from their face images and link them to the corresponding entity keys in a knowledge base. More specifically, we provide,

  • MS-Celeb-1M Training v1: about 10M images for 100K celebrities
  • Concrete measurement to evaluate the performance of recognizing one million celebrities
  • Lowshot learning setup and testbed


  • 03/16/2018 More challenges will be hosted this year!
  • 03/16/2018 Azure blob download link updated!

News from last year

Important Updates

  • 07/11 We send out download links for test data for both the challenges to all the emails registered here. If you have not received the data or registered, please contact us!
  • 07/17 (11:59 am) is the final due time to submit results for both/either of the challenges.
  • 08/08 is the final due time to submit papers. Please note that we accept papers on either of the challenges, or other interesting topics on face recognition. Please refer to our **call for papers** for more details.

Important Dates

  • 04/07 Dataset for challenage-1 Recognizing 1M Celebrities release
  • 04/16 Dataset for challenage-2 Low-shot face recogntion release
  • 05/23 Challenge Registration Open
  • 07/14 Results Submission (changed to 7/17)
  • 07/31 Paper Submission - update to 08/08
  • 08/11 Notification of Acceptance
  • 08/25 Camera Ready Submission (won't be changed due ICCV requirement)


If you are reporting results of the challenge or using the dataset, please cite the paper "MS-Celeb-1M: A Dataset and Benchmark for Large Scale Face Recognition".

        @INPROCEEDINGS { guo2016msceleb,
            author = {Guo, Yandong and Zhang, Lei and Hu, Yuxiao and He, Xiaodong and Gao, Jianfeng},
            title = {M{S}-{C}eleb-1{M}: A Dataset and Benchmark for Large Scale Face Recognition},
            booktitle = {European Conference on Computer Vision},
            year = {2016},

A paper defines the low-shot face recognition benchmark, with a baseline method: "One-shot Face Recognition by Promoting Underrepresented Classes".

        @article { lowshotface,
            author = {Guo, Yandong and Zhang, Lei},
            title = {One-shot Face Recognition by Promoting Underrepresented Classes},
            Journal   = {arXiv preprint arXiv:1707.05574},
            Year      = {2017}}