Optimizing Facial-Landmark Estimation for Embedded Systems through Iterative Autolabeling and Model Pruning

[2024 IEEE International Conference on Multimedia and Expo] [IEEE ICME 2024 Grand Challenges] [Qualification] [Final] [ICME 2024 GC PAIR Competition Final Rankings] Official Dataset Release for the IEEE ICME 2024 Grand Challenge: Low-power Efficient and Accurate Facial-Landmark Detection for Embedded Systems. ivslab_facial_train.zip ivslab_facial_test_private_qualification.zip ivslab_facial_test_private_qualification.zip.001 ivslab_facial_test_private_qualification.zip.002 ivslab_facial _testing_example_private_final.zip ICME2024_Submission_example.zip ICME2024_Submission_mutiple_example.zip Processed Dataset (Used for Training/Validation) yolo_labels.zip conf_0.2.zip f3.zip t0.zip