- 2020/09/03: The deadline of the challenge has been extended! Please pay attention to the new dates.
- 2020/08/08: The leaderboard has been updated. Welcome to submit results for evaluation!
- 2020/08/08: The 1st International Workshop on Human and Vehicle Analysis for Intelligent Urban Computing is open https://havaiuc.github.io/. Welcome to submit papers!
- 2020/07/13: The challenge starts now！You can register and download the training data from here.
- 2020/03/26: Given the COVID-19 situation in Italy and all over the globe, the ICPR 2020 Chairs have decided to shift the Conference schedule to 10-15 January 2021, and our competition is also decided to be postponed. The new schedule will be announced ASAP.
- 2020/03/16: The webpage is available, and we will announce the registration URL on March 30, 2020.
Facial landmark localization is a very crucial step in numerous face related applications, such as face alignment for recognition, facial pose estimation, face image synthesis, etc. We are hosting the 2nd 106-point facial landmark localization challenge in conjunction with ICPR 2020. The purpose is to make effort towards benchmarking lightweight facial landmark localization, which enables efficient system deployment. Different to the 1st challenge, the challenging dataset contains more than 24,000 images with larger variations in identity, pose, expression and occlusion. Besides, a strict limit of model weights is employed for computational efficiency. We sincerely invite academia and industrial practitioners to participate and together push the frontier along this direction.
Fig.1 Examples of the challenging dataset.
- 2020/07/13: Open registration & Release training set
- 2020/07/27: Release validation set & Evaluate
2020/09/152020/10/09: Release test set 2020/09/162020/10/10: Deadline for test results submission 2020/09/292020/10/17: Announcement of the final decision 2020/10/072020/10/24: Deadline for paper submission
During the validation phase (2020/07/27 - 2020/10/09), the participants could sent the results on the validation set to us, and we will return the performance to the participants and update the leaderboard. Each team could only submit once one day. To prevent cheating on the test set, the test images will be released on Oct. 09, 2020 [00:00 a.m. UTC+1], and each team will have 24 hours to predict the test results. Both the predicted test results and the training materials (codes, models and technical reports) need to be sent to us before Sep. 16, 2020 [00:00 a.m. UTC+1].
If you have any questions, please contact us: FLLC_ICPR2020@163.com