Latest News


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 (the upper bound of computational complexity is 1 GFLOPs, and the upper bound of model size is 20MB). We sincerely invite academia and industrial practitioners to participate and together push the frontier along this direction. Examples of the challenging dataset

              Fig.1 Examples of the challenging dataset.

Important Dates

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 Oct. 10, 2020 [00:00 a.m. UTC+1].






If you have any questions, please contact us: